Mapping the Anatomy of the Human Lymphatic System.

BACKGROUND: While substantial anatomical study has been pursued throughout the human body, anatomical study of the human lymphatic system remains in its infancy. For microsurgeons specializing in lymphatic surgery, a better command of lymphatic anatomy is needed to further our ability to offer surgical interventions with precision. In an effort to facilitate the dissemination and advancement of human lymphatic anatomy knowledge, our teams worked together to create a map. The aim of this paper is to present our experience in mapping the anatomy of the human lymphatic system. METHODS: Three steps were followed to develop a modern map of the human lymphatic system: (1) identifying our source material, which was "Anatomy of the human lymphatic system," published by Rouvière and Tobias (1938), (2) choosing a modern platform, the Miro Mind Map software, to integrate the source material, and (3) transitioning our modern platform into The Human BioMolecular Atlas Program (HuBMAP). RESULTS: The map of lymphatic anatomy based on the Rouvière textbook contained over 900 data points. Specifically, the map contained 404 channels, pathways, or trunks and 309 lymph node groups. Additionally, lymphatic drainage from 165 distinct anatomical regions were identified and integrated into the map. The map is being integrated into HuBMAP by creating a standard data format called an Anatomical Structures, Cell Types, plus Biomarkers table for the lymphatic vasculature, which is currently in the process of construction. CONCLUSION: Through a collaborative effort, we have developed a unified and centralized source for lymphatic anatomy knowledge available to the entire scientific community. We believe this resource will ultimately advance our knowledge of human lymphatic anatomy while simultaneously highlighting gaps for future research. Advancements in lymphatic anatomy knowledge will be critical for lymphatic surgeons to further refine surgical indications and operative approaches.

Synchronous and asynchronous teledermatology: A narrative review of strengths and limitations.

The policy changes prompted by the COVID-19 pandemic caused synchronous models (primarily video visits) to supplant asynchronous models (store-and-forward or shared digital photographs) as the default and predominant modality of teledermatology care. Here, we call attention to the unique strengths and limitations of these models in terms of clinical utility, accessibility, and cost-effectiveness. Strengths of synchronous visits include direct physician-patient interaction and current reimbursement parity; limitations include variable video image quality, technological difficulties, and accessibility barriers. Strengths of asynchronous visits include greater convenience, especially for clinicians, and potential for image quality superior to video; limitations include less direct physician-patient communication, barriers to follow-up, and limited reimbursement. Both synchronous and asynchronous models have been shown to be cost-effective. Teledermatology is positioned to play a prominent role in patient care post-pandemic. Moving forward, dermatologists are challenged to optimize teledermatology use in order to improve outcomes, efficiency, and workflows to meet diverse patient needs. Future directions will depend on sustainable reimbursement of both teledermatology formats by government and private payers.

An automated COVID-19 triage pipeline using artificial intelligence based on chest radiographs and clinical data.

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital's image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform.

Artificial intelligence for prediction of COVID-19 progression using CT imaging and clinical data.

OBJECTIVES: Early recognition of coronavirus disease 2019 (COVID-19) severity can guide patient management. However, it is challenging to predict when COVID-19 patients will progress to critical illness. This study aimed to develop an artificial intelligence system to predict future deterioration to critical illness in COVID-19 patients. METHODS: An artificial intelligence (AI) system in a time-to-event analysis framework was developed to integrate chest CT and clinical data for risk prediction of future deterioration to critical illness in patients with COVID-19. RESULTS: A multi-institutional international cohort of 1,051 patients with RT-PCR confirmed COVID-19 and chest CT was included in this study. Of them, 282 patients developed critical illness, which was defined as requiring ICU admission and/or mechanical ventilation and/or reaching death during their hospital stay. The AI system achieved a C-index of 0.80 for predicting individual COVID-19 patients' to critical illness. The AI system successfully stratified the patients into high-risk and low-risk groups with distinct progression risks (p < 0.0001). CONCLUSIONS: Using CT imaging and clinical data, the AI system successfully predicted time to critical illness for individual patients and identified patients with high risk. AI has the potential to accurately triage patients and facilitate personalized treatment. KEY POINT: • AI system can predict time to critical illness for patients with COVID-19 by using CT imaging and clinical data.

Aiding clinical assessment of neonatal sepsis using hematological analyzer data with machine learning techniques.

INTRODUCTION: Early diagnosis and antibiotic administration are essential for reducing sepsis morbidity and mortality; however, diagnosis remains difficult due to complex pathogenesis and presentation. We created a machine learning model for bacterial sepsis identification in the neonatal intensive care unit (NICU) using hematological analyzer data. METHODS: Hematological analyzer data were gathered from NICU patients up to 48 hours prior to clinical evaluation for bacterial sepsis. Five models, Support Vector Machine, K-nearest-neighbors, Logistic Regression, Random Forest (RF), and Extreme Gradient boosting (XGBoost), were trained on 60 hematological and nine clinical variables for 2357 cases (1692 control, 665 septic). Clinical feature only models (nine variables) were additionally trained and compared with models including hematological variables. Feature importance was used to assess relative contributions of parameters to performance. RESULTS: The three best performing models were RF, Logistic Regression, and XGBoost. RF achieved an average accuracy of 0.74, AUC-ROC of 0.73, Sensitivity of 0.38, and Specificity of 0.88. Logistic Regression achieved an average accuracy of 0.70, AUC-ROC of 0.74, Sensitivity of 0.62, and Specificity of 0.73. XGBoost achieved an average accuracy of 0.72, AUC-ROC of 0.71, Sensitivity of 0.40, and Specificity of 0.85. All models with hematological variables had significantly stronger performance than models trained on only clinical features. Neutrophil parameters had the highest average feature importance. CONCLUSIONS: Machine learning models using hematological analyzer data can classify NICU patients as sepsis positive or negative with stronger performance compared to clinical feature only models. Hematological analyzer variables could augment current sepsis classification machine learning algorithms.

Machine Learning-Based Prediction of COVID-19 Severity and Progression to Critical Illness Using CT Imaging and Clinical Data.

OBJECTIVE: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. MATERIALS AND METHODS: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. RESULTS: Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. CONCLUSION: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

Prognostication of patients with COVID-19 using artificial intelligence based on chest x-rays and clinical data: a retrospective study.

BACKGROUND: Chest x-ray is a relatively accessible, inexpensive, fast imaging modality that might be valuable in the prognostication of patients with COVID-19. We aimed to develop and evaluate an artificial intelligence system using chest x-rays and clinical data to predict disease severity and progression in patients with COVID-19. METHODS: We did a retrospective study in multiple hospitals in the University of Pennsylvania Health System in Philadelphia, PA, USA, and Brown University affiliated hospitals in Providence, RI, USA. Patients who presented to a hospital in the University of Pennsylvania Health System via the emergency department, with a diagnosis of COVID-19 confirmed by RT-PCR and with an available chest x-ray from their initial presentation or admission, were retrospectively identified and randomly divided into training, validation, and test sets (7:1:2). Using the chest x-rays as input to an EfficientNet deep neural network and clinical data, models were trained to predict the binary outcome of disease severity (ie, critical or non-critical). The deep-learning features extracted from the model and clinical data were used to build time-to-event models to predict the risk of disease progression. The models were externally tested on patients who presented to an independent multicentre institution, Brown University affiliated hospitals, and compared with severity scores provided by radiologists. FINDINGS: 1834 patients who presented via the University of Pennsylvania Health System between March 9 and July 20, 2020, were identified and assigned to the model training (n=1285), validation (n=183), or testing (n=366) sets. 475 patients who presented via the Brown University affiliated hospitals between March 1 and July 18, 2020, were identified for external testing of the models. When chest x-rays were added to clinical data for severity prediction, area under the receiver operating characteristic curve (ROC-AUC) increased from 0·821 (95% CI 0·796-0·828) to 0·846 (0·815-0·852; p<0·0001) on internal testing and 0·731 (0·712-0·738) to 0·792 (0·780-0 ·803; p<0·0001) on external testing. When deep-learning features were added to clinical data for progression prediction, the concordance index (C-index) increased from 0·769 (0·755-0·786) to 0·805 (0·800-0·820; p<0·0001) on internal testing and 0·707 (0·695-0·729) to 0·752 (0·739-0·764; p<0·0001) on external testing. The image and clinical data combined model had significantly better prognostic performance than combined severity scores and clinical data on internal testing (C-index 0·805 vs 0·781; p=0·0002) and external testing (C-index 0·752 vs 0·715; p<0·0001). INTERPRETATION: In patients with COVID-19, artificial intelligence based on chest x-rays had better prognostic performance than clinical data or radiologist-derived severity scores. Using artificial intelligence, chest x-rays can augment clinical data in predicting the risk of progression to critical illness in patients with COVID-19. FUNDING: Brown University, Amazon Web Services Diagnostic Development Initiative, Radiological Society of North America, National Cancer Institute and National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health.

Evaluation of a convolutional neural network for ovarian tumor differentiation based on magnetic resonance imaging.

OBJECTIVES: There currently lacks a noninvasive and accurate method to distinguish benign and malignant ovarian lesion prior to treatment. This study developed a deep learning algorithm that distinguishes benign from malignant ovarian lesion by applying a convolutional neural network on routine MR imaging. METHODS: Five hundred forty-five lesions (379 benign and 166 malignant) from 451 patients from a single institution were divided into training, validation, and testing set in a 7:2:1 ratio. Model performance was compared with four junior and three senior radiologists on the test set. RESULTS: Compared with junior radiologists averaged, the final ensemble model combining MR imaging and clinical variables had a higher test accuracy (0.87 vs 0.64, p < 0.001) and specificity (0.92 vs 0.64, p < 0.001) with comparable sensitivity (0.75 vs 0.63, p = 0.407). Against the senior radiologists averaged, the final ensemble model also had a higher test accuracy (0.87 vs 0.74, p = 0.033) and specificity (0.92 vs 0.70, p < 0.001) with comparable sensitivity (0.75 vs 0.83, p = 0.557). Assisted by the model's probabilities, the junior radiologists achieved a higher average test accuracy (0.77 vs 0.64, Δ = 0.13, p < 0.001) and specificity (0.81 vs 0.64, Δ = 0.17, p < 0.001) with unchanged sensitivity (0.69 vs 0.63, Δ = 0.06, p = 0.302). With the AI probabilities, the junior radiologists had higher specificity (0.81 vs 0.70, Δ = 0.11, p = 0.005) but similar accuracy (0.77 vs 0.74, Δ = 0.03, p = 0.409) and sensitivity (0.69 vs 0.83, Δ = -0.146, p = 0.097) when compared with the senior radiologists. CONCLUSIONS: These results demonstrate that artificial intelligence based on deep learning can assist radiologists in assessing the nature of ovarian lesions and improve their performance. KEY POINTS: • Artificial Intelligence based on deep learning can assess the nature of ovarian lesions on routine MRI with higher accuracy and specificity than radiologists. • Assisted by the deep learning model's probabilities, junior radiologists achieved better performance that matched those of senior radiologists.

Spillover Effects of Medicare's Voluntary Bundled Payments for Joint Replacement Surgery to Patients Insured by Commercial Health Plans.

BACKGROUND: Under the Bundled Payments for Care Improvement (BPCI) program, bundled paymtents for lower-extremity joint replacement (LEJR) are associated with 2% to 4% cost savings with stable quality among Medicare fee-for-service beneficiaries. However, BPCI may prompt practice changes that benefit all patients, not just fee-for-service beneficiaries. OBJECTIVE: To examine the association between hospital participation in BPCI and LEJR outcomes for patients with commercial insurance or Medicare Advantage (MA). DESIGN: Quasi-experimental study using Health Care Cost Institute claims from 2011 to 2016. SETTING: LEJR at 281 BPCI hospitals and 562 non-BPCI hospitals. PATIENTS: 184 922 patients with MA or commercial insurance. MEASUREMENTS: Differential changes in LEJR outcomes at BPCI hospitals versus at non-BPCI hospitals matched on propensity score were evaluated using a difference-in-differences (DID) method. Secondary analyses evaluated associations by patient MA status and hospital characteristics. Primary outcomes were changes in 90-day total spending on LEJR episodes and 90-day readmissions; secondary outcomes were postacute spending and discharge to postacute care providers. RESULTS: Average episode spending decreased more at BPCI versus non-BPCI hospitals (change, -2.2% [95% CI, -3.6% to -0.71%]; P = 0.004), but differences in changes in 90-day readmissions were not significant (adjusted DID, -0.47 percentage point [CI, -1.0 to 0.06 percentage point]; P = 0.084). Participation in BPCI was also associated with differences in decreases in postacute spending and discharge to institutional postacute care providers. Decreases in episode spending were larger for hospitals with high baseline spending but did not vary by MA status. LIMITATION: Nonrandomized studies are subject to residual confounding and selection. CONCLUSION: Participation in BPCI was associated with modest spillovers in episode savings. Bundled payments may prompt hospitals to implement broad care redesign that produces benefits regardless of insurance coverage. PRIMARY FUNDING SOURCE: Leonard Davis Institute of Health Economics at the University of Pennsylvania.

Spillover effects of mandatory hip and knee replacement surgery bundles in medicare.

BACKGROUND: Medicare used the Comprehensive Care for Joint Replacement (CJR) Model to mandate that hospitals in certain health care markets accept bundled payments for lower extremity joint replacement surgery. CJR has reduced spending with stable quality as intended among Medicare fee-for-service patients, but benefits could "spill over" to individuals insured through private health plans. Definitive evidence of spillovers remains lacking. OBJECTIVE: To evaluate the association between CJR participation and changes in outcomes among privately insured individuals. DESIGN, SETTING, PARTICIPANTS: We used 2013-2017 Health Care Cost Institute claims for 418,016 privately insured individuals undergoing joint replacement in 75 CJR and 121 Non-CJR markets. Multivariable generalized linear models with hospital and market random effects and time fixed effects were used to analyze the association between CJR participation and changes in outcomes. MAIN OUTCOMES AND MEASURES: Total episode spending, discharge to institutional post-acute care, and quality (e.g., surgical complications, readmissions). RESULTS: Patients in CJR and Non-CJR markets did not differ in total episode spending (difference of -$157, 95% CI -$1043 to $728, p = 0.73) or discharge to institutional post-acute care (difference of -1.1%, 95% CI -3.2%-1.0%, p = 0.31). Similarly, patients in the two groups did not differ in quality or other utilization outcomes. Findings were generally similar in stratified and sensitivity analyses. CONCLUSIONS: There was a lack of evidence of cost or utilization spillovers from CJR to privately insured individuals. There may be limits in the ability of certain value-based payment reforms to drive broad changes in care delivery and patient outcomes.

Deep Learning Based on MR Imaging for Predicting Outcome of Uterine Fibroid Embolization.

PURPOSE: To develop and validate a deep learning model based on routine magnetic resonance (MR) imaging obtained before uterine fibroid embolization to predict procedure outcome. MATERIALS AND METHODS: Clinical data were collected on patients treated with uterine fibroid embolization at the Hospital of the University of Pennsylvania from 2007 to 2018. Fibroids for each patient were manually segmented by an abdominal radiologist on a T1-weighted contrast-enhanced (T1C) sequence and a T2-weighted sequence of MR imaging obtained before and after embolization. A residual convolutional neural network (ResNet) model to predict clinical outcome was trained using MR imaging obtained before the procedure. RESULTS: Inclusion criteria were met by 727 fibroids in 409 patients. At clinical follow-up, 85.6% (n = 350) of 409 patients (590 of 727 fibroids; 81.1%) experienced symptom resolution or improvement, and 14.4% (n = 59) of 409 patients (137 of 727 fibroids; 18.9%) had no improvement or worsening symptoms. The T1C trained model achieved a test accuracy of 0.847 (95% confidence interval [CI], 0.745-0.914), sensitivity of 0.932 (95% CI, 0.833-0.978), and specificity of 0.462 (95% CI, 0.232-0.709). In comparison, the average of 4 radiologists achieved a test accuracy of 0.722 (95% CI, 0.609-0.813), sensitivity of 0.852 (95% CI, 0.737-0.923), and specificity of 0.135 (95% CI, 0.021-0.415). CONCLUSIONS: This study demonstrates that deep learning based on a ResNet model achieves good accuracy in predicting outcome of uterine fibroid embolization. If further validated, the model may help clinicians better identify patients who can most benefit from this therapy and aid clinical decision making.

Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT.

Background Coronavirus disease 2019 (COVID-19) and pneumonia of other diseases share similar CT characteristics, which contributes to the challenges in differentiating them with high accuracy. Purpose To establish and evaluate an artificial intelligence (AI) system for differentiating COVID-19 and other pneumonia at chest CT and assessing radiologist performance without and with AI assistance. Materials and Methods A total of 521 patients with positive reverse transcription polymerase chain reaction results for COVID-19 and abnormal chest CT findings were retrospectively identified from 10 hospitals from January 2020 to April 2020. A total of 665 patients with non-COVID-19 pneumonia and definite evidence of pneumonia at chest CT were retrospectively selected from three hospitals between 2017 and 2019. To classify COVID-19 versus other pneumonia for each patient, abnormal CT slices were input into the EfficientNet B4 deep neural network architecture after lung segmentation, followed by a two-layer fully connected neural network to pool slices together. The final cohort of 1186 patients (132 583 CT slices) was divided into training, validation, and test sets in a 7:2:1 and equal ratio. Independent testing was performed by evaluating model performance in separate hospitals. Studies were blindly reviewed by six radiologists without and then with AI assistance. Results The final model achieved a test accuracy of 96% (95% confidence interval [CI]: 90%, 98%), a sensitivity of 95% (95% CI: 83%, 100%), and a specificity of 96% (95% CI: 88%, 99%) with area under the receiver operating characteristic curve of 0.95 and area under the precision-recall curve of 0.90. On independent testing, this model achieved an accuracy of 87% (95% CI: 82%, 90%), a sensitivity of 89% (95% CI: 81%, 94%), and a specificity of 86% (95% CI: 80%, 90%) with area under the receiver operating characteristic curve of 0.90 and area under the precision-recall curve of 0.87. Assisted by the probabilities of the model, the radiologists achieved a higher average test accuracy (90% vs 85%, Δ = 5, P < .001), sensitivity (88% vs 79%, Δ = 9, P < .001), and specificity (91% vs 88%, Δ = 3, P = .001). Conclusion Artificial intelligence assistance improved radiologists' performance in distinguishing coronavirus disease 2019 pneumonia from non-coronavirus disease 2019 pneumonia at chest CT. © RSNA, 2020 Online supplemental material is available for this article.

Opportunity Costs of Receiving Palliative Chemotherapy for Metastatic Pancreatic Ductal Adenocarcinoma.

PURPOSE: The median overall survival (OS) for metastatic pancreatic ductal adenocarcinoma (mPDAC) is < 1 year. Factors that contribute to quality of life during treatment are critical to quantify. One factor-time spent obtaining clinical services-is understudied. We quantified total outpatient time among patients with mPDAC receiving palliative systemic chemotherapy. METHODS: We conducted a retrospective analysis using four patient-level time measures calculated from the medical record of patients with mPDAC receiving 5-fluorouracil infusion, leucovorin, oxaliplatin, and irinotecan; gemcitabine/nab-paclitaxel; or gemcitabine within the University of Pennsylvania Health System between January 1, 2011 and January 15, 2019. These included the total number of health care encounter days (any day with at least one visit) and total visit time. Total visit time represented the time spent receiving care (care time) plus time spent commuting and waiting for care (noncare time). We performed descriptive statistics on these outpatient time metrics and compared the number of encounter days to OS. RESULTS: A total of 362 patients were identified (median age, 65 years; 52% male; 78% white; 62% received gemcitabine plus nab-paclitaxel). Median OS was 230.5 days (7.6 months), with 79% of patients deceased at the end of follow-up. On average, patients had 22 health care encounter days, accounting for 10% of their total days survived. Median visit time was 4.6 hours, of which 2.5 hours was spent commuting or waiting for care. CONCLUSION: On average, patients receiving palliative chemotherapy for mPDAC spend 10% of survival time on outpatient health care. More than half of this time is spent commuting and waiting for care. These findings provide an important snapshot of the patient experience during ambulatory care, and efforts to enhance efficiency of care delivery may be warranted.

Deep Learning Based on MRI for Differentiation of Low- and High-Grade in Low-Stage Renal Cell Carcinoma.

Pretreatment determination of renal cell carcinoma aggressiveness may help to guide clinical decision-making. PURPOSE: To evaluate the efficacy of residual convolutional neural network using routine MRI in differentiating low-grade (grade I-II) from high-grade (grade III-IV) in stage I and II renal cell carcinoma. STUDY TYPE: Retrospective. POPULATION: In all, 376 patients with 430 renal cell carcinoma lesions from 2008-2019 in a multicenter cohort were acquired. The 353 Fuhrman-graded renal cell carcinomas were divided into a training, validation, and test set with a 7:2:1 split. The 77 WHO/ISUP graded renal cell carcinomas were used as a separate WHO/ISUP test set. FIELD STRENGTH/SEQUENCE: 1.5T and 3.0T/T2 -weighted and T1 contrast-enhanced sequences. ASSESSMENT: The accuracy, sensitivity, and specificity of the final model were assessed. The receiver operating characteristic (ROC) curve and precision-recall curve were plotted to measure the performance of the binary classifier. A confusion matrix was drawn to show the true positive, true negative, false positive, and false negative of the model. STATISTICAL TESTS: Mann-Whitney U-test for continuous data and the chi-square test or Fisher's exact test for categorical data were used to compare the difference of clinicopathologic characteristics between the low- and high-grade groups. The adjusted Wald method was used to calculate the 95% confidence interval (CI) of accuracy, sensitivity, and specificity. RESULTS: The final deep-learning model achieved a test accuracy of 0.88 (95% CI: 0.73-0.96), sensitivity of 0.89 (95% CI: 0.74-0.96), and specificity of 0.88 (95% CI: 0.73-0.96) in the Fuhrman test set and a test accuracy of 0.83 (95% CI: 0.73-0.90), sensitivity of 0.92 (95% CI: 0.84-0.97), and specificity of 0.78 (95% CI: 0.68-0.86) in the WHO/ISUP test set. DATA CONCLUSION: Deep learning can noninvasively predict the histological grade of stage I and II renal cell carcinoma using conventional MRI in a multiinstitutional dataset with high accuracy. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Clinical effectiveness and cost-effectiveness of teledermatology: Where are we now, and what are the barriers to adoption?

There has been rapid growth in teledermatology over the past decade, and teledermatology services are increasingly being used to support patient care across a variety of care settings. Teledermatology has the potential to increase access to high-quality dermatologic care while maintaining clinical efficacy and cost-effectiveness. Recent expansions in telemedicine reimbursement from the Centers for Medicare & Medicaid Services (CMS) ensure that teledermatology will play an increasingly prominent role in patient care. Therefore, it is important that dermatologists be well informed of both the promises of teledermatology and the potential practice challenges a continuously evolving mode of care delivery brings. In this article, we will review the evidence on the clinical and cost-effectiveness of teledermatology and we will discuss system-level and practice-level barriers to successful teledermatology implementation as well as potential implications for dermatologists.

Deep Learning to Distinguish Benign from Malignant Renal Lesions Based on Routine MR Imaging.

PURPOSE: With increasing incidence of renal mass, it is important to make a pretreatment differentiation between benign renal mass and malignant tumor. We aimed to develop a deep learning model that distinguishes benign renal tumors from renal cell carcinoma (RCC) by applying a residual convolutional neural network (ResNet) on routine MR imaging. EXPERIMENTAL DESIGN: Preoperative MR images (T2-weighted and T1-postcontrast sequences) of 1,162 renal lesions definitely diagnosed on pathology or imaging in a multicenter cohort were divided into training, validation, and test sets (70:20:10 split). An ensemble model based on ResNet was built combining clinical variables and T1C and T2WI MR images using a bagging classifier to predict renal tumor pathology. Final model performance was compared with expert interpretation and the most optimized radiomics model. RESULTS: Among the 1,162 renal lesions, 655 were malignant and 507 were benign. Compared with a baseline zero rule algorithm, the ensemble deep learning model had a statistically significant higher test accuracy (0.70 vs. 0.56, P = 0.004). Compared with all experts averaged, the ensemble deep learning model had higher test accuracy (0.70 vs. 0.60, P = 0.053), sensitivity (0.92 vs. 0.80, P = 0.017), and specificity (0.41 vs. 0.35, P = 0.450). Compared with the radiomics model, the ensemble deep learning model had higher test accuracy (0.70 vs. 0.62, P = 0.081), sensitivity (0.92 vs. 0.79, P = 0.012), and specificity (0.41 vs. 0.39, P = 0.770). CONCLUSIONS: Deep learning can noninvasively distinguish benign renal tumors from RCC using conventional MR imaging in a multi-institutional dataset with good accuracy, sensitivity, and specificity comparable with experts and radiomics.