google ads
Search
CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning CTisus CT Scanning Ask the Fish

Everything you need to know about Computed Tomography (CT) & CT Scanning

December 2018 Imaging Pearls - Educational Tools | CT Scanning | CT Imaging | CT Scan Protocols - CTisus
Imaging Pearls ❯ December 2018

-- OR --

3D and Workflow

    • “With emerging virtual reality technologies, application of new tools in forensic medicine and anthropology will require adjustments, technical optimization, and validation. This study serves as an example of the anticipated level of efficacy and some of the limitations of virtual skeletons using current technology. Technical improvements should focus on searching for appropriate 3D-rendering parameters and minimization of stair-step artifacts. When virtual pelvic bones are used in an assessment, the cinematic volume rendering 3D CT has a high level of efficacy in revealing relevant details on the pubic bone, but remains unsuitable for evaluation of the auricular surface because of the poor demonstration of transverse organization and porosity.”
      Technical note: Efficacy of three-dimensional cinematic rendering computed tomography images in visualizing features related to age estimation in pelvic bones
      Nuttaya Pattamapaspong et al. Forensic Science International (in press)
    • - Virtual skeletons created from 3D CT images have the potential to be used as a substitute for real bones. 
      - For age estimation, 3D CT can reveal relevant details on the pubic symphyses. 
      - 3D CT cannot effectively display the transverse organization or the porosity of the auricular surface. 
      - Appropriate rendering parameters and reduction of artifacts in 3D CT are required.
      Technical note: Efficacy of three-dimensional cinematic rendering computed tomography images in visualizing features related to age estimation in pelvic bones
      Nuttaya Pattamapaspong et al. Forensic Science International (in press)
    • “Cinematic volume rendering is a newly introduced technique inspired by the photorealistic appearance of some animation movies. Owing to advances in computer technology, cinematic volume rendering resembles casting billons light rays from all possible directions to create an image. This technique integrates natural light effects which improves the rendering of shape, depth, and shading on the surface of 3D images.”
      Technical note: Efficacy of three-dimensional cinematic rendering computed tomography images in visualizing features related to age estimation in pelvic bones
      Nuttaya Pattamapaspong et al. Forensic Science International (in press)
Chest

    • Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning. Building a highly accurate prediction model for these tasks usually requires a large number of images manually annotated with labels and finding sites of abnormalities. In reality, however, such annotated data are expensive to acquire, especially the ones with location annotations. We need methods that can work well with only a small amount of location annotations. To address this challenge, we present a unified approach that simultaneously performs disease identification and localization through the same underlying model for all images. We demonstrate that our approach can effectively leverage both class information as well as limited location annotation, and significantly outperforms the comparative reference baseline in both classification and localization tasks.
      Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al arVIX March 2018 (in press)
    • “We propose a unified model that jointly models disease identification and localization with limited localization annotation data. This is achieved through the same underlying prediction model for both tasks. Quantitative and qualitative results demonstrate that our method significantly outperforms the state-of-the-art algorithm”
      Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al arVIX March 2018 (in press)

    • Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al
      arVIX March 2018 (in press)c


    • Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al
      arVIX March 2018 (in press)c

Deep Learning


    • Artificial Intelligence- The Next Digital Frontier McKinsey Global Institute(2017)

    • Artificial Intelligence- The Next Digital Frontier McKinsey Global Institute(2017)
    • Hospitals also could improve their capacity utilization by employing AI solutions to optimize many ordinary business tasks. Virtual agents could automate routine patient interactions. Speech recognition software has been used in client services, where it has reduced the expense of processing patients by handling routine tasks such as scheduling appointments and registering people when they enter a hospital. Natural language processing can analyze journal articles and other documents and digest their contents for quick access by doctors. These kinds of applications can have a significant impact without needing to pass a regulatory review.
      Artificial Intelligence- The Next Digital Frontier
      McKinsey Global Institute(2017)
    • We have found that if a sector was slow to adopt digital technologies, it tends to trail the pack in putting AI to use, too. Our report Digital America found that almost one-quarter of the nation’s hospitals and more than 40 percent of its office-based physicians have not yet adopted electronic health record systems.63 Even those that do have electronic record systems may not be sharing data seamlessly with the patient or with other providers; tests are repeated needlessly and patients are required to recount their medical histories over and over because these systems are not interoperable. Another MGI report, The age of analytics, found that the US health-care sector has realized only 10 to 20 percent of its opportunities to use advanced analytics and machine learning.
      Artificial Intelligence- The Next Digital Frontier
      McKinsey Global Institute(2017)
    • Patients also can benefit directly from the rise of AI in health care. Standardized treatments do not work for every patient, given the complexity of each person’s history and genetic makeup, so researchers are using advanced analytics to personalize regimens. Decisions can be based on data analysis and patient monitoring with use of remote diagnostic devices. A startup called Turbine uses AI to design personalized cancer-treatment regimens. The technology models cell biology on the molecular level and seeks to identify the best drug to use for specific tumors. It can also identify complex biomarkers and search for combination therapies by performing millions of simulated experiments each day .
      Artificial Intelligence- The Next Digital Frontier
      McKinsey Global Institute(2017)
    • Medical practices have taken small steps toward incorporating AI into patient management, introducing speech recognition and other language AI technologies to automate steps in the process. In the future, virtual assistants equipped with speech recognition, image recognition, and machine learning tools will be able to conduct consultations, make diagnoses, and even prescribe drugs. If these systems lack enough information to reach a conclusion, a virtual agent could order additional tests and schedule them with the patient. In rural areas, virtual agents will be able to conduct remote consultations. However, this scenario would require patients, providers, and regulators to become comfortable with fully automated diagnosis and prescriptions.
      Artificial Intelligence- The Next Digital Frontier
      McKinsey Global Institute(2017)
    • Prediction Machines The Simple Economics of Artificial Intelligence
      Agrawal A, Gans J, Goldfarb A
      Harvard Business Review Press 2018
    • AI and its developments and its impact are not always obvious
      - How many saw Steve Jobs introduction of the iPhone in 2007 mean the end of the beginning for the ”Yellow Cab” industry? Uber and Lyft rely on the iPhone.
      - Do you realize that Google is only 20 years old?
    • AI in Medicine: Diagnosis vs Prediction
      - If I read a CT and find a body of the pancreas mass that looks like an PDAC am I making a prediction or a diagnosis?
      - This may help reduce the burden of proof for the FDA if it is a prediction system and not a diagnosis machine
    • Should we stop training Radiologists?
      “whether Radiologists have a future depends on whether they are best positioned to undertake these roles, if other specialists will replace them, or if new job classes will develop, such as a combined radiologist/pathologist (i.e., a role where the radiologist also analyzes biopsies, perhaps performed immediately after imaging.”
    • Should we stop training Radiologists?
      ”Therefore five clear roles for humans in the use of medical imaging will remain, at least in the short and medium term; choosing the image, using real time images in medical procedures, interpreting machine output, training machines on new technologies, and employing judgement that may lead to overriding the prediction machines recommendation, perhaps on information unavailable to the machine.”
    • “We have shown that radiological scores can be predicted to an excellent standard using only the disc-specific assessments as a reference set. The proposed method is quite general, and although we have implemented it here for sagittal T2 scans, it could easily be applied to T1 scans or axial scans, and for radiological features not studied here or indeed to any medical task where label/grading might be available only for a small region or a specific anatomy of an image. One benefit of automated reading is to produce a numerical signal score that would provide a scale of degeneration and so avoid an arbitrary categorization into artificial grades.”
      Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist
      Jamaludin A et al.
      Eur Spine J 2018; DOI 10.1007/s00586-017-4956-3
    • “Automation of radiological grading is now on par with human performance. The system can be beneficial in aiding clinical diagnoses in terms of objectivity of gradings and the speed of analysis. It can also draw the attention of a radiologist to regions of degradation. This objectivity and speed is an important stepping stone in the investigation of the relationship between MRIs and clinical diagnoses of back pain in large cohorts.”
      Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist
      Jamaludin A et al.
      Eur Spine J 2018; DOI 10.1007/s00586-017-4956-3
    • The process in a flow chart
    • One of the biggest potential bottlenecks that could inhibit or derail AI development and adoption in health care is the availability of sufficient quantities of high-quality data in standardized formats. As noted earlier, information today is highly fragmented and spread across the industry, residing in diverse, mostly uncoordinated repositories like electronic medical records, laboratory and imaging systems, physician notes, and health-insurance claims. Merging this information into large, integrated databases, which is required to empower AI to develop the deep understanding of diseases and their cures, is difficult.
      Artificial Intelligence- The Next Digital Frontier
      McKinsey Global Institute(2017)
    • Brain Tumors: Pathology
      We here demonstrate that DNA methylation-based CNS tumour classification using a comprehensive machine-learning approach is a valuable asset for clinical decision-making. In particular, the high level of standardization has great promise to reduce the substantial inter-observer variability observed in current CNS tumour diagnostics.
    • “We here demonstrate that DNA methylation-based CNS tumour classification using a comprehensive machine-learning approach is a valuable asset for clinical decision-making. In particular, the high level of standardization has great promise to reduce the substantial inter-observer variability observed in current CNS tumour diagnostics.”
      DNA methylation-based classification of central nervous system tumours
      Pfister SM et al.
      Nature 2018 (in press)
    • “We here demonstrate that DNA methylation-based CNS tumour classification using a comprehensive machine-learning approach is a valuable asset for clinical decision-making. In particular, the high level of standardization has great promise to reduce the substantial inter-observer variability observed in current CNS tumour diagnostics. Furthermore, in contrast to traditional pathology, where there is a pressure to assign all tumours to a described entity even for atypical or challenging cases, the objective measure that we provide here allows for ‘no match’ to a defined class.”
      DNA methylation-based classification of central nervous system tumours
      Nature 2018 (in press)
    • Through the application of AI, information-intensive domains such as marketing, health care, financial services, education, and professional services could become simultaneously more valuable and less ex- pensive to society. Business drudgery in every indus- try and function—overseeing routine transactions, repeatedly answering the same questions, and ex- tracting data from endless documents—could become the province of machines, freeing up human workers to be more productive and creative. Cognitive tech- nologies are also a catalyst for making other data-in- tensive technologies succeed, including autonomous vehicles, the Internet of Things, and mobile and multi- channel consumer technologies.
    • Cognitive insight.
      The second most common type of project in our study (38% of the total) used algorithms to detect patterns in vast volumes of data and interpret their meaning. Think of it as “analytics on steroids.” These machine-learning applications are being used to:
      - predict what a particular customer is likely to buy;
      - identify credit fraud in real time and detect insur- ance claims fraud
      - analyze warranty data to identify safety or quality problems in automobiles and other manufactured products
      - automate personalized targeting of digital ads; and
      - provide insurers with more-accurate and detailed actuarial modeling.
    • AI in Radiology: The Bottom Line
      - AI will put Radiologists out of business
      - AI is all hype and will soon fade like many fads
      - The reality is that AI will change all aspects of Radiology but may be our savior rather the grim reaper?
    • Reality: AI is already in our patients homes (and in yours)
      - Voice-enabled assistants that use AI have entered the homes of many patients (Amazon Alexa, Google Home)
      -- Connectivity to our patients with pre-study or post-study information
      -- Can help reduce readmissions or un-necessary ER visits by answering patients questions
    • Reality: AI can eliminate needless costs
      - Eliminate positions in customer service, billing and administration
      - Eliminate significant numbers of staff in scheduling or call centers while improving the patient experience. Think Uber and Diner Reservations or even Airline reservations
    • Reality: Machine Learning can decrease medical error
      - Can AI be the ultimate second reader?
      - Clinical applications
      -- CT
      -- MR
      -- Plain Radiographs
      -- Ultrasound
      -- Pathology

    • Harvard Business Review Jan-Feb 2018
    • In 2013 the MD Anderson Cancer Center launched a “moon shot” project: diagnose and recommend treatment plans for certain forms of cancer using IBM’s Watson cognitive system. But in 2017, the project was put on hold after costs topped $62 million—and the system had yet to be used on patients.
    • Determining the use cases
      The second area of assessment evaluates the use cases in which cognitive applications would generate substantial value and contribute to business success. Start by asking key questions such as: How critical to your overall strategy is addressing the targeted problem? How difficult would it be to implement the proposed AI solution—both technically and organizationally? Would the benefits from launching the application be worth the effort? Next, prioritize the use cases according to which offer the most short- and long-term value, and which might ultimately be integrated into a broader platform or suite of cognitive capabilities to create competitive advantage.
    • Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers.
      Materials and Methods: Prospective 18F-FDG PET brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding.
      Results: The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P , .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain.
      Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9 
      https://doi.org/10.1148/radiol.2018180958
    • In this study, we aimed to evaluate whether a deep learning algorithm could be trained to predict the final clinical diagnoses in patients who underwent 18F-FDG PET of the brain and, once trained, how the deep learning algorithm compares with the cur- rent standard clinical reading methods in differentiation of patients with final diagnoses of AD, MCI, or no evidence of dementia. We hypothesized that the deep learning algorithm could detect features or patterns that are not evident on standard clinical review of images and thereby improve the final diagnostic classification of individuals.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/radiol.2018180958

    • A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.2018180958
    • Our study had several limitations. First, our independent test data were relatively small (n = 40) and were not collected as part of a clinical trial. Most notably, this was a highly selected cohort in that all patients must have been referred to the memory clinic and neurologist must have decided that a PET study of the brain would be useful in clinical management. This effectively excluded most non-AD neurodegenerative cases and other neurologic disorders such as stroke that could affect memory function. Arguably, such cohort of patients would be the most relevant group to test the deep learning algorithm, but the algorithm’s performance on a more general patient population remains untested and un- proven, hence the pilot nature of this study.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers.
      Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/radiol.2018180958
    • Second, the deep learning algorithm’s robustness is inherently limited by the clinical distribution of the training set from ADNI. The algorithm achieved strong performance on a small independent test set, where the population substantially differed from the ADNI test set; however, its performance and robustness cannot yet be guaranteed on prospective, unselected, and real-life scenario patient cohorts. Further validation with larger and prospective external test set must be performed before actual clinical use. Further- more, this training set from ADNI did not include non-AD neurodegenerative cases, limiting the utility of the algorithm in such patient population.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Third, the deep learning algorithm did not yield a human interpretable imaging biomarker despite visualization with saliency map, which highlights the inherent black-box limitation of deep learning algorithms. The algorithm instead made predictions based on holistic features of the imaging study, distinct from the human expert approaches. Fourth, MCI and non-AD/MCI were inherently unstable diagnoses in that their accuracy is dependent on the length of follow-up. For example, some of the MCI patients, if followed up for long enough time, may have eventually progressed to AD.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Overall, our study demonstrates that a deep learning algorithm can predict the final diagnosis of AD from 18F- FDG PET imaging studies of the brain with high accuracy and robustness across external test data. Furthermore, this study proposes a working deep learning approaches and a set of convolutional neural network hyperparameters, validated on a public dataset, that can be the groundwork for further model improvement. With further large-scale external validation on multi-institutional data and model calibration, the algorithm may be integrated into clinical workflow and serve as an important decision support tool to aid radiology readers and clinicians with early prediction of AD from 18F- FDG PET imaging studies.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Overall, our study demonstrates that a deep learning algorithm can predict the final diagnosis of AD from 18F- FDG PET imaging studies of the brain with high accuracy and robustness across external test data. Furthermore, this study proposes a working deep learning approaches and a set of convolutional neural network hyperparameters, validated on a public dataset, that can be the groundwork for further model improvement.”
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • “To address these two issues, the authors made use of a large data set of 103489 chest radiographs obtained between 2007 and 2016 in 46712 patients. Only 5232 patients with 7390 radiographs had a BNP test value avail- able. This data set with BNP data was termed “labeled,” and the other data set without BNP data was termed “unlabeled.” In the labeled data set, BNP level was dichotomized at 100 ng/L, above which CHF was defined as present. The labeled data set was divided into a training data set (80% of the data) and a test data set (20% of the data).”
      Using a Deep Learning Network to Diagnose Congestive Heart Failure
      Ngo LH
      Radiology 2019; 00:1–2 •
      https://doi.org/10.1148/radiol.2018182341
    • Nevertheless, clearly the work of Seah et al is highly innovative and has wide applications in many different areas in medical imaging. The concept of GVR is in fact similar to the idea of counterfactuals used in causal inference studies. A GVR-generated deep learning neural network system (as nicely implemented in this study) would definitely improve over time as more labeled images, finer-resolution images, and improved machine learning algorithms become available. One can easily imagine having this system as an additional tool to assist radiologists in delivering better diagnostic information to their patients.
      Using a Deep Learning Network to Diagnose Congestive Heart Failure
      Ngo LH
      Radiology 2019; 00:1–2 •
      https://doi.org/10.1148/radiol.2018182341
    • “Consider Amara’s law: “We tend to overestimate the effect of a technology in the short run and underestimate the effect in the long run.” At the present, we overestimate the degree to which imaging diagnosis will be affected by machine learn- ing in the present moment and we underestimate the role that radiologists have to play in the development and deployment of these technologies. However, given the inevitable, it is essential for radiologists to stay abreast of developments in the machine learning field.”
      Machine Learning in Radiology: Resistance Is Futile
      Larvie M et al.
      Radiology 2019; 00:1-2
      https://doi.org/10.1148/radiol.2018182312
    • "Machine learning technologies are now deeply embedded in our medical information systems. These methods will ultimately be pervasive in the digital realm of radiology. Resistance really is futile. But that’s okay: The best applications will address pressing clinical needs and improve radiology care. Radiologists are well situated both to contribute to this technological progress, as well as to benefit from machine learning applications in their work. Done well, this will lead to improved patient outcomes and large advances for radiology practice”.
      Machine Learning in Radiology: Resistance Is Futile
      Larvie M et al.
      Radiology 2019; 00:1-2
      https://doi.org/10.1148/radiol.2018182312
    • Artificial Intelligence in Practice (AI): Applications
      - Congestive heart failure
      - Alzheimer's disease
      - Pneumonia
      - Lung nodule evaluation
      - Wrist fractures
      - Pancreatic cancer
    • Artificial Intelligence in Practice (AI): Applications
      - Plain x-ray
      - Ultrasound
      - CT
      - MRI
      - PET/CT
    • “Although elegant, Lakhani and Sundaram have a software result, not a hardware result. In most software research, the only individuals with the algorithm are the researchers. Without the AI algorithm, the results cannot be reproduced. Many AI publications are transient—they are proof-of-concept; they cannot be validated. As a radiologist, you cannot implement the AI research in your clinical practice without the algorithm, and the algorithms are largely discarded. In this setting, there is near zero chance that practice guidelines will be changed.”
      Editor’s Note: Publication of AI Research in Radiology
      Bluemke DA
      Radiology 2018 (in press)
      https://doi.org/10.1148/radiol.2018184021
    • New AI research in radiology is amazing. Our dis- cipline has tried for 30 or more years for computers to help us analyze our images. Prior non-AI approaches have mostly not succeeded. In my research lab, technologists and pre- and postdoctoral students analyzed thousands of cardiac MRI cases by drawing circles at the borders of the heart for the last 20 years. Yet in 6 months or less, AI neural networks are now trained to draw those circles better and more consistently than any of our prior efforts. My reaction to seeing new AI developments is equivalent to “shock and awe.”
      Editor’s Note: Publication of AI Research in Radiology
      Bluemke DA
      Radiology 2018 (in press)
      https://doi.org/10.1148/radiol.2018184021
    • “Our first policy affecting AI research is regarding pre-print servers, such as arXiv.org. AI researchers frequently put their latest algorithms on arXiv to claim "I’m first" supremacy. arXiv publications are not peer reviewed. They do however look like normal publications—especially to laypersons. Preprint servers are used by AI researchers to rapidly share software, algorithms, and ideas.”
      Editor’s Note: Publication of AI Research in Radiology
      Bluemke DA
      Radiology 2018 (in press)
      https://doi.org/10.1148/radiol.2018184021
    • The policy of Radiology is to discourage authors from placing their results on preprint servers. There are two reasons for this. First, if the results are already avail- able, the incremental benefit of publication in Radiology is low. Second, the vast majority of submissions for publication undergo substantial changes due to peer review and editorial processes.
      Editor’s Note: Publication of AI Research in Radiology
      Bluemke DA
      Radiology 2018 (in press)
      https://doi.org/10.1148/radiol.2018184021 
    • “Our second policy affecting AI research is to strongly encourage making the computer algorithms available to other researchers. Authors of AI research should make a git archive of their source code or make it available on the author’s web page. Git archive providers such as GitHub, Bitbucket, or Source Forge are already available and in use by some research- ers. Authors should place a link to the web page for their code in their Materials and Methods section. They should also provide a unique identifier for the revision of the code used in the publication.”
      Editor’s Note: Publication of AI Research in Radiology
      Bluemke DA
      Radiology 2018 (in press)
      https://doi.org/10.1148/radiol.2018184021
    • When AI truly succeeds in medical imaging, we will stop calling it AI. The AI portions will simply be integrated tools in our PACS, scanner, or workstation—not separate features.
      Editor’s Note: Publication of AI Research in Radiology
      Bluemke DA
      Radiology 2018 (in press)
      https://doi.org/10.1148/radiol.2018184021
Kidney

    • “Renal cell carcinoma (RCC) is a significant malignancy; 63 000 individuals in the United States were newly diagnosed with RCC in 2017. Approximately 90% of all renal tumors are RCCs, and 76% of RCCs are the clear cell subtype, 17% are papillary, and 6% are the chromophobe subtype. In the United States, the incidence of RCC continues to increase, in part because of high rates of obesity, hypertension, smoking, and exposure to other risk factors and also because of improved tumor detection due to increased use of imaging and advances in imaging technology. Collectively, these factors have led to a progressive decrease in the size of renal masses at initial detection such that localized kidney cancers now represent more than 60% of the detected cases of renal cancer. “
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
    • The AUA guideline for performing RN stipulates that physicians should consider RN in cases in which tumor size, RMB results, and/or imaging characteristics suggest increased oncologic potential. In this setting, RN is preferred when all of the following criteria are met: (a) there is high tumor complexity and PN would be challenging, even in experienced hands; (b) there is no preexisting CKD or proteinuria; and (c) the contralateral kidney is normal and the new baseline estimated glomerular filtration rate will likely be greater than 45 mL/min/1.73 m2.
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
    • The AUA guidelines for performing PN include the following: (a) PN should be a priority for management of cT1a renal masses when intervention is indicated. (b) Nephron-sparing approaches should be a priority for patients with an anatomic or functionally solitary kidney, bilateral tumors, known familial RCC, preexisting CKD, or proteinuria. (c) Nephron-sparing approaches should be considered for patients who are young, have multifocal masses, or have comorbidities that are likely to affect renal function in the future.
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
    • The AUA guidelines for performing thermal ablation are as follows: (a) Consider thermal ablation as an alternative approach for management of cT1a renal masses smaller than 3 cm. A percutaneous approach is preferred. (b) Radiofrequency ablation and cryoablation are options. (c) RMB should be performed before thermal ablation. (d) Counseling regard- ing thermal ablation should include information about the increased likelihood of tumor persistence or recurrence after the primary thermal ablation.
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
    • AUA guidelines for active surveillance include the following recommendations: (a) Active surveillance is an option for initial management in patients with renal masses suspicious for cancer, especially those smaller than 2 cm. (b) Active surveillance or expectant management should be a priority when the anticipated risk of intervention or competing risks of death outweigh the potential oncologic benefits of active treatment.
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
    • “For preoperative evaluation, arterial phase CT scans obtained with a 30-second delay can help to detect renal arterial branches and their relationship to the tumor. In addition, excretory phase images can be used to identify the position of the collecting system in relation to the mass.”
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
    • For evaluation of cystic lesions, the Bosniak system should be applied. Relatively recent study results suggest that 54%–65% of Bosniak III cysts and approximately 85%–86% of Bosniak IV cysts are malignant. For enhancing solid lesions, the main differential considerations for benign tumors are lipid-poor angiomyolipoma and oncocytoma.
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
    • The management of RCC is evolving and becoming less aggressive, in part because of the recognition that many renal tumors, especially small ones, are indolent. In light of these findings, the roles of RMB and management techniques such as thermal ablation and active surveillance are becoming increasingly important. Additional data suggest that postprocedural kidney function may be an important factor in long-term survival, shifting the preference from RN to nephron- sparing techniques such as PN and thermal ablation. The radiologist has an essential role in the evaluation, counseling, and selective treatment of patients with localized kidney cancer.
      2017 AUA Renal Mass and Localized Renal Cancer Guidelines: Imaging Implications
      Ward RD et al.
      RadioGraphics 2018 (in press)
Musculoskeletal

    • “With emerging virtual reality technologies, application of new tools in forensic medicine and anthropology will require adjustments, technical optimization, and validation. This study serves as an example of the anticipated level of efficacy and some of the limitations of virtual skeletons using current technology. Technical improvements should focus on searching for appropriate 3D-rendering parameters and minimization of stair-step artifacts. When virtual pelvic bones are used in an assessment, the cinematic volume rendering 3D CT has a high level of efficacy in revealing relevant details on the pubic bone, but remains unsuitable for evaluation of the auricular surface because of the poor demonstration of transverse organization and porosity.”
      Technical note: Efficacy of three-dimensional cinematic rendering computed tomography images in visualizing features related to age estimation in pelvic bones
      Nuttaya Pattamapaspong et al.
      Forensic Science International (in press)
    • - Virtual skeletons created from 3D CT images have the potential to be used as a substitute for real bones. 
      - For age estimation, 3D CT can reveal relevant details on the pubic symphyses. 
      - 3D CT cannot effectively display the transverse organization or the porosity of the auricular surface. 
      - Appropriate rendering parameters and reduction of artifacts in 3D CT are required.
      Technical note: Efficacy of three-dimensional cinematic rendering computed tomography images in visualizing features related to age estimation in pelvic bones
      Nuttaya Pattamapaspong et al.
      Forensic Science International (in press)
    • “Cinematic volume rendering is a newly introduced technique inspired by the photorealistic appearance of some animation movies. Owing to advances in computer technology, cinematic volume rendering resembles casting billons light rays from all possible directions to create an image. This technique integrates natural light effects which improves the rendering of shape, depth, and shading on the surface of 3D images.”
      Technical note: Efficacy of three-dimensional cinematic rendering computed tomography images in visualizing features related to age estimation in pelvic bones
      Nuttaya Pattamapaspong et al.
      Forensic Science International (in press)
Neuroradiology

    • Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers.
      Materials and Methods: Prospective 18F-FDG PET brain images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2109 imaging studies from 2005 to 2017, 1002 patients) and retrospective independent test set (40 imaging studies from 2006 to 2016, 40 patients) were collected. Final clinical diagnosis at follow-up was recorded. Convolutional neural network of InceptionV3 architecture was trained on 90% of ADNI data set and tested on the remaining 10%, as well as the independent test set, with performance compared to radiologic readers. Model was analyzed with sensitivity, specificity, receiver operating characteristic (ROC), saliency map, and t-distributed stochastic neighbor embedding.
      Results: The algorithm achieved area under the ROC curve of 0.98 (95% confidence interval: 0.94, 1.00) when evaluated on predicting the final clinical diagnosis of AD in the independent test set (82% specificity at 100% sensitivity), an average of 75.8 months prior to the final diagnosis, which in ROC space outperformed reader performance (57% [four of seven] sensitivity, 91% [30 of 33] specificity; P , .05). Saliency map demonstrated attention to known areas of interest but with focus on the entire brain.
      Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9 
      https://doi.org/10.1148/radiol.2018180958
    • Purpose: To develop and validate a deep learning algorithm that predicts the final diagnosis of Alzheimer disease (AD), mild cognitive impairment, or neither at fluorine 18 (18F) fluorodeoxyglucose (FDG) PET of the brain and compare its performance to that of radiologic readers.
      Conclusion: By using fluorine 18 fluorodeoxyglucose PET of the brain, a deep learning algorithm developed for early prediction of Alzheimer disease achieved 82% specificity at 100% sensitivity, an average of 75.8 months prior to the final diagnosis.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/radiol.2018180958
    • In this study, we aimed to evaluate whether a deep learning algorithm could be trained to predict the final clinical diagnoses in patients who underwent 18F-FDG PET of the brain and, once trained, how the deep learning algorithm compares with the cur- rent standard clinical reading methods in differentiation of patients with final diagnoses of AD, MCI, or no evidence of dementia. We hypothesized that the deep learning algorithm could detect features or patterns that are not evident on standard clinical review of images and thereby improve the final diagnostic classification of individuals.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/radiol.2018180958

    • A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.2018180958
    • Our study had several limitations. First, our independent test data were relatively small (n = 40) and were not collected as part of a clinical trial. Most notably, this was a highly selected cohort in that all patients must have been referred to the memory clinic and neurologist must have decided that a PET study of the brain would be useful in clinical management. This effectively excluded most non-AD neurodegenerative cases and other neurologic disorders such as stroke that could affect memory function. Arguably, such cohort of patients would be the most relevant group to test the deep learning algorithm, but the algorithm’s performance on a more general patient population remains untested and un- proven, hence the pilot nature of this study.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Second, the deep learning algorithm’s robustness is inherently limited by the clinical distribution of the training set from ADNI. The algorithm achieved strong performance on a small independent test set, where the population substantially differed from the ADNI test set; however, its performance and robustness cannot yet be guaranteed on prospective, unselected, and real-life scenario patient cohorts. Further validation with larger and prospective external test set must be performed before actual clinical use. Further- more, this training set from ADNI did not include non-AD neurodegenerative cases, limiting the utility of the algorithm in such patient population.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Third, the deep learning algorithm did not yield a human interpretable imaging biomarker despite visualization with saliency map, which highlights the inherent black-box limitation of deep learning algorithms. The algorithm instead made predictions based on holistic features of the imaging study, distinct from the human expert approaches. Fourth, MCI and non-AD/MCI were inherently unstable diagnoses in that their accuracy is dependent on the length of follow-up. For example, some of the MCI patients, if followed up for long enough time, may have eventually progressed to AD.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Overall, our study demonstrates that a deep learning algorithm can predict the final diagnosis of AD from 18F- FDG PET imaging studies of the brain with high accuracy and robustness across external test data. Furthermore, this study proposes a working deep learning approaches and a set of convolutional neural network hyperparameters, validated on a public dataset, that can be the groundwork for further model improvement. With further large-scale external validation on multi-institutional data and model calibration, the algorithm may be integrated into clinical workflow and serve as an important decision support tool to aid radiology readers and clinicians with early prediction of AD from 18F- FDG PET imaging studies.
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • “Overall, our study demonstrates that a deep learning algorithm can predict the final diagnosis of AD from 18F- FDG PET imaging studies of the brain with high accuracy and robustness across external test data. Furthermore, this study proposes a working deep learning approaches and a set of convolutional neural network hyperparameters, validated on a public dataset, that can be the groundwork for further model improvement.”
      A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain
      Yiming Ding et al.
      Radiology 2018; 00:1–9
      https://doi.org/10.1148/iol.201818095
    • Brain Tumors: Pathology
      We here demonstrate that DNA methylation-based CNS tumour classification using a comprehensive machine-learning approach is a valuable asset for clinical decision-making. In particular, the high level of standardization has great promise to reduce the substantial inter-observer variability observed in current CNS tumour diagnostics.
    • “We here demonstrate that DNA methylation-based CNS tumour classification using a comprehensive machine-learning approach is a valuable asset for clinical decision-making. In particular, the high level of standardization has great promise to reduce the substantial inter-observer variability observed in current CNS tumour diagnostics.”
      DNA methylation-based classification of central nervous system tumours
      Pfister SM et al.
      Nature 2018 (in press)
    • “We here demonstrate that DNA methylation-based CNS tumour classification using a comprehensive machine-learning approach is a valuable asset for clinical decision-making. In particular, the high level of standardization has great promise to reduce the substantial inter-observer variability observed in current CNS tumour diagnostics. Furthermore, in contrast to traditional pathology, where there is a pressure to assign all tumours to a described entity even for atypical or challenging cases, the objective measure that we provide here allows for ‘no match’ to a defined class.”
      DNA methylation-based classification of central nervous system tumours
      Nature 2018 (in press)
    • “We have shown that radiological scores can be predicted to an excellent standard using only the disc-specific assessments as a reference set. The proposed method is quite general, and although we have implemented it here for sagittal T2 scans, it could easily be applied to T1 scans or axial scans, and for radiological features not studied here or indeed to any medical task where label/grading might be available only for a small region or a specific anatomy of an image. One benefit of automated reading is to produce a numerical signal score that would provide a scale of degeneration and so avoid an arbitrary categorization into artificial grades.”
      Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist
      Jamaludin A et al.
      Eur Spine J 2018; DOI 10.1007/s00586-017-4956-3
    • “Automation of radiological grading is now on par with human performance. The system can be beneficial in aiding clinical diagnoses in terms of objectivity of gradings and the speed of analysis. It can also draw the attention of a radiologist to regions of degradation. This objectivity and speed is an important stepping stone in the investigation of the relationship between MRIs and clinical diagnoses of back pain in large cohorts.”
      Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist
      Jamaludin A et al.
      Eur Spine J 2018; DOI 10.1007/s00586-017-4956-3
    • The process in a flow chart
    • Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning. Building a highly accurate prediction model for these tasks usually requires a large number of images manually annotated with labels and finding sites of abnormalities. In reality, however, such annotated data are expensive to acquire, especially the ones with location annotations. We need methods that can work well with only a small amount of location annotations. To address this challenge, we present a unified approach that simultaneously performs disease identification and localization through the same underlying model for all images. We demonstrate that our approach can effectively leverage both class information as well as limited location annotation, and significantly outperforms the comparative reference baseline in both classification and localization tasks.
      Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al
      arVIX March 2018 (in press)
    • “We propose a unified model that jointly models disease identification and localization with limited localization annotation data. This is achieved through the same underlying prediction model for both tasks. Quantitative and qualitative results demonstrate that our method significantly outperforms the state-of-the-art algorithm”
      Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al
      arVIX March 2018 (in press)

    • Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al
      arVIX March 2018 (in press)c

    • Thoracic Disease Identification and Localization with Limited Supervision
      Zhe Li et al
      arVIX March 2018 (in press)c
Pancreas

    • “Neoplastic lesions such as high-grade NETs, small SPTs, and metastases and inflammatory lesions including focal AIP and groove pancreatitis can mimic PDAC. Abrupt narrow- ing of a dilated pancreatic duct is a usual imaging finding of PDAC. Although some mimics occasionally accompany pancreatic duct dilatation, they have points of differential diagnosis: presence of tumor thrombus and hypervascular liver metastases, absence of adjacent vascular invasion, and delayed enhancement pattern.”
      Pancreas Ductal Adenocarcinoma and its Mimics: Review of Cross- sectional Imaging Findings for Differential Diagnosis.
      Kim, SS, et al.
      Journal of the Belgian Society of Radiology. 2018; 102(1): 71, 1–8.
    • Background: The incidence of occult metastatic disease (OMD) in pancreatic ductal adenocarcinoma (PDAC) and associated risk factors are largely unknown.
      Conclusions: Occurrence of OMD in PDAC accounts for 8% of cases. Preoperative CA 19‐9 > 192 U/mL, primary tumor size > 30 mm, and identification of indeterminate lesions in preoperative CT may indicate the need for diagnostic laparoscopy.
      Incidence and risk factors for abdominal occult metastatic disease in patients with pancreatic adenocarcinoma
      Georgios Gemenetzis MD1 | Vincent P. Groot MD1 | Alex B. Blair MD1 |Ding Ding MD, MS1 | Sameer S. Thakker1 | Elliot K. Fishman MD2 | John L. Cameron MD1 | Martin A. Makary MD1 | Matthew J. Weiss MD1 | Christopher L. Wolfgang MD, PhD1 | Jin He MD, PhD1 J Surg Oncol. 2018;1-8.
    • “As expected, OMD patients had unfavorable outcomes. The median postoperative survival for this cohort was 6 months, similar to patients with metastatic disease at diagnosis.44 A more specific difference on survival based on the site of occult metastases was not identified, probably due to the small cohort size. When compared with historic postoperative survival rates in resectable PDAC,20 survival rates were significantly lower.”
      Incidence and risk factors for abdominal occult metastatic disease in patients with pancreatic adenocarcinoma
      Georgios Gemenetzis MD1 | Vincent P. Groot MD1 | Alex B. Blair MD1 |Ding Ding MD, MS1 | Sameer S. Thakker1 | Elliot K. Fishman MD2 | John L. Cameron MD1 | Martin A. Makary MD1 | Matthew J. Weiss MD1 | Christopher L. Wolfgang MD, PhD1 | Jin He MD, PhD1 J Surg Oncol. 2018;1-8.
    • The occurrence of OMD accounts for approximately 8% of patients with PDAC. Preoperative increased CA 19‐9 values, abdominal pain at presentation, and identification of indeterminate lesions and primary tumor size larger than 30 mm in preoperative MDCT suggest increased risk for OMD and may indicate the need for diagnostic laparoscopy. Patient assessment in a multidisciplinary setting within high‐volume centers can increase the yield of accurate preoperative identification of patients with OMD and direct appropriate treatment accordingly.
      Incidence and risk factors for abdominal occult metastatic disease in patients with pancreatic adenocarcinoma
      Georgios Gemenetzis MD1 | Vincent P. Groot MD1 | Alex B. Blair MD1 |Ding Ding MD, MS1 | Sameer S. Thakker1 | Elliot K. Fishman MD2 | John L. Cameron MD1 | Martin A. Makary MD1 | Matthew J. Weiss MD1 | Christopher L. Wolfgang MD, PhD1 | Jin He MD, PhD1 J Surg Oncol. 2018;1-8.
    • “Autoimmune pancreatitis (AIP) is an uncommon form of chronic pancreatitis caused by an autoimmune mechanism. It is a challenge to distinguish focal AIP from PDAC because the two diseases show similar imaging features, but several reports have offered suggestions for discriminating between them. According to those studies, slightly lower or similar signal intensity compared with the spleen on unenhanced T1-weighted images, relatively homogeneous enhancement, signs of pancreatic duct penetration, smooth tapered narrowing of the pancreatic duct (icicle sign) or bile duct, multifocal stricture of the pancreatic duct, and a delayed enhancement pattern on dynamic enhanced images are features favoring AIP over PDAC.”
      Pancreas Ductal Adenocarcinoma and its Mimics: Review of Cross- sectional Imaging Findings for Differential Diagnosis.
      Kim, SS, et al.
      Journal of the Belgian Society of Radiology. 2018; 102(1): 71, 1–8.
    • “Pancreatic NETs originate from the islet cells of Langerhans and are divided into low-, intermediate-, and high-grade according to the World Health Organization classification. High-grade NETs more frequently show vascular invasion, lymph node metastasis, and diffusion restriction compared with low-grade; therefore, high- grade NETs can mimic PDAC on images. However, high-grade NETs usually do not show pancreatic duct dilatation. In addition, they occasionally accompany tumor thrombus, which can be helpful in the differential diagnosis of high-grade NETs from PDAC. Liver metastases from NETs frequently reveal findings of hypervascularity and intralesional hemorrhage, in contrast to those from PDAC, which reveal hypovascularity.”
      Pancreas Ductal Adenocarcinoma and its Mimics: Review of Cross- sectional Imaging Findings for Differential Diagnosis.
      Kim, SS, et al.
      Journal of the Belgian Society of Radiology. 2018; 102(1): 71, 1–8.
    • “SPTs are uncommon neoplasms with low malignancy potential, occurring predominantly in young women. Calcification, cystic change, and internal hemorrhage due to weak vascular channels are characteristic features of SPT. However, small (≤3 cm) SPTs show different imaging findings from larger ones, primarily a homogeneous nature. Small SPTs show a pure solid consistency, well-defined margin, and diffusion restriction on magnetic resonance (MR) imaging. After contrast infusion, small SPTs reveal an early heterogenous nature, followed by a progressive enhancement pattern.”
      Pancreas Ductal Adenocarcinoma and its Mimics: Review of Cross- sectional Imaging Findings for Differential Diagnosis.
      Kim, SS, et al.
      Journal of the Belgian Society of Radiology. 2018; 102(1): 71, 1–8.
Practice Management

    • All too often, people ignore my advice by saying that “our industry is different, and what you have to teach me doesn’t hold true for us.” Let me assure you, however, that our industries are not so very different, and that we both share a primary goal of serving the customer. Your department may be composed of some of the best physicians in the world, and you may know more about medicine than some of your competitors, but that doesn’t necessarily matter.
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “If you don’t understand how to optimize service for your customers, all the medical knowledge in the world will not be sufficient for your business to succeed.”
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “In my experience, there are 3 things customers expect from any business: (1) timely service, (2) a good product, and (3) people who treat me well and are nice to me (ie, caring service).”
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “Let’s assume for a moment that your department and institution have a good product—you are great physicians and nurses, and patients can expect good outcomes if they choose your hospital. Unfortunately, the general public may not always have enough medical knowledge to recognize that you’re doing a good job—it is timely service and the way in which people interact with them that come to define their perceptions of you and their care.”
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • We’ve found that a wait any longer than a couple of minutes is enough to create a negative perception of your organization in the customer’s mind. Unfortunately, long wait times seem to be common at many hospitals. Why? The last people who should be kept waiting are sick patients, who are scared and anxious.
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “How do you create an environ- ment in which our customers are given timely, satisfactory, and courteous service? You have to hire the right people and give them a chance to work in an environment of belonging and purpose.”
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “I hire my employees as human beings to join us and be apart of us. I want them to be a part of the vision and dream of our company, and I want them to gain happiness from being part of a team that creates excellence.”
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “Just as important, I have discovered over the years that the success of the team and individual employees is highly contingent on having your organization filled with leaders rather than managers. Leaders give no excuses—they exude positivity, optimism, and drive, and that filters down to every member of the organization. Managers, on the other hand, are concerned with covering up their own lack of drive and ambition with excuses.”
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “Finding leaders is not that easy, but I have managed to gradually fill up my organization with leaders, rather than managers, and that has contributed toward my employees’ being happy and being placed in positions where they can succeed. Hiring the right people is the key to success and should be a top priority.”
      The pursuit of excellence: from hotels to hospitals.
      Schulze HH, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Jan;12(1):17-8
    • “Another important lesson I have learned is that there is always something “stupid” or “dumb” happening all the time in any organization—we just don’t recognize it unless it becomes a big enough problem. As you get higher in the organization, you see fewer and fewer of the problems, and frankly, the interconnections and relationships in a big company are so numerous and complex that no leader can completely understand or grasp them in any real way.”
      From Toy Story to CT Scans: Lessons From Pixar for Radiology
      Catmull E, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Sep;12(9):978-9.
    • “Finally, having an organization in which everyone feels empowered to suggest ideas and make contributions is critical if you hope to innovate”.
      From Toy Story to CT Scans: Lessons From Pixar for Radiology
      Catmull E, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Sep;12(9):978-9.
    • “Even worse, although I had established an open-door policy, I was told that the production staff had felt hesitant to voice their concerns because they didn’t want to be seen as “going over the head” of their coworkers. From that time on, my policy at Pixar has been that anyone can voice an opinion to anyone else without worrying about consequences or reprimand.”
      From Toy Story to CT Scans: Lessons From Pixar for Radiology
      Catmull E, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Sep;12(9):978-9.
    • Dr Catmull’s admonition about “hidden” aspects of an organization is very important. Radiologists may have a good sense of what is happening in departmental reading rooms, as the majority of radiologists in a department perform at least some clinical work. However, “other” facets of the department, including many patient-centric aspects of radiology, such as scheduling an appointment, patient parking, checking in with the receptionist in the waiting room, having an intravenous line placed by a nurse, or requesting one’s scan results, are all somewhat obscure in the minds of most radiologists but are critical in the “patient experience”.
      From Toy Story to CT Scans: Lessons From Pixar for Radiology
      Catmull E, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Sep;12(9):978-9.
    • “Dr Catmull stressed that candor is essential in an organization. It is dangerous when everyone in a meeting is afraid to speak up or voice their concerns, but once the meeting is over, they talk to one another in private about the real issues. Real concerns need to be addressed and corrected early, before they become huge and costly. As a leader, it is essential that you surround yourself with people who are honest and unafraid to disagree with you. As Dr Catmull nicely stated, “if there is more truth in the hallways than in meetings, you have a problem.”
      From Toy Story to CT Scans: Lessons From Pixar for Radiology
      Catmull E, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Sep;12(9):978-9.
    • “In all of the organizations I have worked, the best leaders and executives have been able to create work cultures that inspire both clients and their companies’ employees, and they have had the strength as leaders to drive the difficult changes needed to create those positive work cultures. Over the years, having seen both successful and un- successful businesses, I have become a strong believer that in order for your company to be successful, your employees must be happy, they must truly believe in their company and products, and they must be willing to put their clients first.”
      Improving Patient Care Through Inspiring Happiness.
      Kaplowitz M, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Nov;12(11):1227-8
    • The success of any company starts with caring about your people, products, and clients, and of these three, I would argue that focusing on the happiness of your own employees may actually be most important for the long-term sustainability of your business. Without happy employees, it is difficult to maintain happy clients, no matter how good your product may be.
      Improving Patient Care Through Inspiring Happiness.
      Kaplowitz M, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Nov;12(11):1227-8
    • At the core of a successful company lies a happy, motivated work-force that does not feel unduly stressed or burdened. Although many companies put a lot of emphasis on attracting the best talent to their workforces, it is my view that this alone is not sufficient, as a company must put equal emphasis on creating a high- performance workplace that allows those employees to maximize their potential.
      Improving Patient Care Through Inspiring Happiness.
      Kaplowitz M, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Nov;12(11):1227-8
    • Over the course of our experience with the happiness training program, we have come away with five key lessons:
      * Happiness is a choice rather than something one is born with, and it can be taught to individuals who otherwise consider themselves unhappy.
      * Happiness requires the ability to balance one’s personal and public lives.
      Improving Patient Care Through Inspiring Happiness.
      Kaplowitz M, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Nov;12(11):1227-8
    • * Feeling gratitude for the good things in one’s life can help suppress many of the negative emotions that can hinder happiness and success.
      *Nurturing positive relationships, and taking the time to acknowledge and express gratitude for the efforts of others, can help one feel better about oneself.
      * Learning optimism can help make people and businesses more successful.
      Improving Patient Care Through Inspiring Happiness.
      Kaplowitz M, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Nov;12(11):1227-8
    • “We must not forget that the happiness of all our employees is critical to a practice’s success, not simply the happiness of its physicians alone. Support staff members, including nurses, receptionists, and technologists, are much more likely to directly interact with our patients (ie, customers), and if we have not taken the effort to create a positive, happy work culture for these employees, it is unlikely that they will be positive and engaging around our patients. and businesses more successful”.
      Improving Patient Care Through Inspiring Happiness.
      Kaplowitz M, Fishman EK, Horton KM, Raman SP.
      J Am Coll Radiol. 2015 Nov;12(11):1227-8
Spleen

    • “Primary splenic angiosarcomas are rare, aggressive malignant neoplasms arising from splenic sinusoidal vascular endothelium. First described by Langhans in 1879,it is among the rarest types of neoplasm, with an estimated annual incidence of 0.14 to 0.25 cases per million persons.”
      Primary Splenic Angiosarcoma
      Kamran S. Hamid et al.
      JSLS. 2010 Jul-Sep; 14(3): 431–435.
    • “ Primary angiosarcoma of the spleen is a rare and aggressive malignant neoplasm arising from splenic vascular endothelium and mesenchymal-derived elongated endothelial cells lining the spleen's spongy network of sinusoids. In general, angiosarcomas are rapidly proliferating, highly infiltrating anaplastic cells that tend to recur locally, spread widely, and have an increased rate of lymph node and systemic metastases.”
      Primary Splenic Angiosarcoma
      Kamran S. Hamid et al.
      JSLS. 2010 Jul-Sep; 14(3): 431–435.
    • Thorium dioxide, vinyl chloride, and arsenic have been implicated in the formation of hepatic angiosarcomas, but no etiologic association between these substances and splenic angiosarcomas has been substantiated.”
      Primary Splenic Angiosarcoma
      Kamran S. Hamid et al.
      JSLS. 2010 Jul-Sep; 14(3): 431–435.
    • "Macroscopically, there may be diffuse involvement of the spleen and replacement of the entire splenic parenchyma with tumor. Solitary masses are uncommon, and most tumors have usually undergone hemorrhage and necrosis. The histologic appearance of splenic angiosarcomas is quite heterogeneous. Immunohistochemical investigations have suggested that primary splenic angiosarcomas may arise from splenic sinus endothelial cells.”
      Primary Splenic Angiosarcoma
      Kamran S. Hamid et al.
      JSLS. 2010 Jul-Sep; 14(3): 431–435.
    • "Metastases occur in 69% to 100% of cases of splenic angiosarcoma.Neuhauser et al reported the rates of metastases as 89% to the liver, 78% to the lungs, 56% to lymph nodes, and 44% to bone. Falk et al found rates of metastases as 41% to the liver, 22% to bone or its marrow, and 3% to lymph nodes..”
      Primary Splenic Angiosarcoma
      Kamran S. Hamid et al.
      JSLS. 2010 Jul-Sep; 14(3): 431–435.
    • "On CT scans, the most common finding is an ill-defined heterogeneously enhancing splenic mass with areas of necrosis. In the event of acute rupture, hemorrhage will appear hyperattenuated on unenhanced images. There is no particular pattern of calcification associated with splenic angiosarcoma, but areas of hypervascular metastases to the liver, lungs, bones, and lymphatic system are well demonstrated on CT.”
      Primary Splenic Angiosarcoma
      Kamran S. Hamid et al.
      JSLS. 2010 Jul-Sep; 14(3): 431–435.
    • “Splenic angiosarcoma is exceedingly rare, but it is the most common primary nonhematolymphoid malignant neoplasm of the spleen. It is a highly aggressive malignancy with a poor prognosis. The majority of patients present with abdominal pain or a palpable abdominal mass. Occasionally, widespread metastases or splenic rupture will be the presenting manifestation.”
      Angiosarcoma of the Spleen: Imaging Characteristics in 12 Patients
      Thompson WM et al.
      Radiology 2005; 235:106-115
    • “The most common CT finding, found in six (60%) patients, was an enlarged spleen that contained a large heterogeneous complex mass or masses that almost completely replaced the spleen. In two of these patients, there was substantial contrast enhancement, and in the other four patients, there was only minimal con- trast enhancement, with areas of decreased attenuation suggesting necrosis.”
      Angiosarcoma of the Spleen: Imaging Characteristics in 12 Patients
      Thompson WM et al.
      Radiology 2005; 235:106-115
© 1999-2018 Elliot K. Fishman, MD, FACR. All rights reserved.