In vivo neuropil density from anatomical MRI and machine learning.

Brain energy budgets specify metabolic costs emerging from underlying mechanisms of cellular and synaptic activities. While current bottom-up energy budgets use prototypical values of cellular density and synaptic density, predicting metabolism from a person's individualized neuropil density would be ideal. We hypothesize that in vivo neuropil density can be derived from magnetic resonance imaging (MRI) data, consisting of longitudinal relaxation (T1) MRI for gray/white matter distinction and diffusion MRI for tissue cellularity (apparent diffusion coefficient, ADC) and axon directionality (fractional anisotropy, FA). We present a machine learning algorithm that predicts neuropil density from in vivo MRI scans, where ex vivo Merker staining and in vivo synaptic vesicle glycoprotein 2A Positron Emission Tomography (SV2A-PET) images were reference standards for cellular and synaptic density, respectively. We used Gaussian-smoothed T1/ADC/FA data from 10 healthy subjects to train an artificial neural network, subsequently used to predict cellular and synaptic density for 54 test subjects. While excellent histogram overlaps were observed both for synaptic density (0.93) and cellular density (0.85) maps across all subjects, the lower spatial correlations both for synaptic density (0.89) and cellular density (0.58) maps are suggestive of individualized predictions. This proof-of-concept artificial neural network may pave the way for individualized energy atlas prediction, enabling microscopic interpretations of functional neuroimaging data.

Multicenter Quantification of Radiation Exposure and Associated Risks for Prostatic Artery Embolization in 1476 Patients.

Background Prostatic artery embolization (PAE) is a safe, minimally invasive angiographic procedure that effectively treats benign prostatic hyperplasia; however, PAE-related patient radiation exposure and associated risks are not completely understood. Purpose To quantify radiation dose and assess radiation-related adverse events in patients who underwent PAE at multiple centers. Materials and Methods This retrospective study included patients undergoing PAE for any indication performed by experienced operators at 10 high-volume international centers from January 2014 to May 2021. Patient characteristics, procedural and radiation dose data, and radiation-related adverse events were collected. Procedural radiation effective doses were calculated by multiplying kerma-area product values by an established conversion factor for abdominopelvic fluoroscopy-guided procedures. Relationships between cumulative air kerma (CAK) or effective dose and patient body mass index (BMI), fluoroscopy time, or radiation field area were assessed with linear regression. Differences in radiation dose stemming from radiopaque prostheses or fluoroscopy unit type were assessed using two-sample t tests and Wilcoxon rank sum tests. Results A total of 1476 patients (mean age, 69.9 years ± 9.0 [SD]) were included, of whom 1345 (91.1%) and 131 (8.9%) underwent the procedure with fixed interventional or mobile fluoroscopy units, respectively. Median procedure effective dose was 17.8 mSv for fixed interventional units and 12.3 mSv for mobile units. CAK and effective dose both correlated positively with BMI (R2 = 0.15 and 0.17; P < .001) and fluoroscopy time (R2 = 0.16 and 0.08; P < .001). No radiation-related 90-day adverse events were reported. Patients with radiopaque implants versus those without implants had higher median CAK (1452 mGy [range, 900-2685 mGy] vs 1177 mGy [range, 700-1959 mGy], respectively; P = .01). Median effective dose was lower for mobile than for fixed interventional systems (12.3 mSv [range, 8.5-22.0 mSv] vs 20.4 mSv [range, 13.8-30.6 mSv], respectively; P < .001). Conclusion Patients who underwent PAE performed with fixed interventional or mobile fluoroscopy units were exposed to a median effective radiation dose of 17.8 mSv or 12.3 mSv, respectively. No radiation-related adverse events at 90 days were reported. © RSNA, 2024 See also the editorial by Mahesh in this issue.

Multi-Task Learning for Motion Analysis and Segmentation in 3D Echocardiography.

Characterizing left ventricular deformation and strain using 3D+time echocardiography provides useful insights into cardiac function and can be used to detect and localize myocardial injury. To achieve this, it is imperative to obtain accurate motion estimates of the left ventricle. In many strain analysis pipelines, this step is often accompanied by a separate segmentation step; however, recent works have shown both tasks to be highly related and can be complementary when optimized jointly. In this work, we present a multi-task learning network that can simultaneously segment the left ventricle and track its motion between multiple time frames. Two task-specific networks are trained using a composite loss function. Cross-stitch units combine the activations of these networks by learning shared representations between the tasks at different levels. We also propose a novel shape-consistency unit that encourages motion propagated segmentations to match directly predicted segmentations. Using a combined synthetic and in-vivo 3D echocardiography dataset, we demonstrate that our proposed model can achieve excellent estimates of left ventricular motion displacement and myocardial segmentation. Additionally, we observe strong correlation of our image-based strain measurements with crystal-based strain measurements as well as good correspondence with SPECT perfusion mappings. Finally, we demonstrate the clinical utility of the segmentation masks in estimating ejection fraction and sphericity indices that correspond well with benchmark measurements.

Deferral of Estimated Glomerular Filtration Rate Testing Before Contrast-Enhanced CT in Low-Risk Emergency Department Patients: Assessment of Safety and Impact on Throughput.

OBJECTIVE: To assess the safety and utility of deferring estimated glomerular filtration rate (eGFR) testing before contrast-enhanced CT (CECT) in low-risk emergency department (ED) patients. METHODS: A new question was added to CECT order screens, allowing ordering ED providers to defer eGFR testing in patients deemed low risk for contrast-induced acute kidney injury (AKI). Low risk was defined as no known chronic kidney disease (CKD) or risk factors for AKI or CKD. Patients on chronic dialysis were deemed low risk. The project included three phases: baseline, pilot (optional order question), and full implementation (required order question). Outcomes were operational throughput metrics of CECT order to protocol (O to P) and order to begin (O to B) times. As a balancing safety measure, the proportion of patients deemed to be "low risk" and subsequently found to have eGFR value less than 30 mL/min/1.73 m2 was reported. RESULTS: A total of 16,446 CECT studies were included from four EDs. In the pilot phase, provider engagement rates with the question were low (5%-14%). After full implementation, median O to P time improved from 23.93 min at baseline to 13.02 (P < .0001) and median O to B time improved from 80.34 min to 76.48 (P = .0002). In 0.3% (2 of 646) studies, CECT was completed in patients categorized as low risk by the ED provider with subsequently resulted eGFR <30 mL/min/1.73 m2. DISCUSSION: Upfront clinical risk assessment for AKI and CKD by ED providers can be used to safely defer eGFR testing and improve operational performance for patients requiring CECT.

Performance and reliability assessment of a lower dose, task-based scoliosis radiography protocol in pediatric patients.

BACKGROUND: Follow-up scoliosis radiographs are performed to assess the degree of spinal curvature and skeletal maturity, which can be done at lower radiation exposures than those in standard-dose radiography. OBJECTIVE: Describe and evaluate a protocol that reduced the radiation in follow-up frontal-view scoliosis radiographs. MATERIALS AND METHODS: We implemented a postero-anterior lower dose modified-technique for scoliosis radiography with task-based definition of adequate image quality and use of technique charts based on target exposure index and patient's height and weight. We subsequently retrospectively evaluated 40 consecutive patients who underwent a follow-up radiograph using the modified-technique after an initial standard-technique radiograph. We evaluated comparisons of proportions for subjective assessment with chi-squared tests, and agreements of reader's scores with intraclass correlation coefficients and Bland-Altman plots. We determined incident air kerma, exposure index, deviation index/standard deviation, dose-area product (DAP), and effective dose for each radiograph. We set statistical significance at P<0.05. RESULTS: Forty patients (65% female), aged 4-17 years. Median effective dose was reduced from 39 to 10 µSv (P<0.001), incident air kerma from 139 to 29 µSv (P<0.001), and DAP from 266 to 55 mGy*cm2 (P<0.001). All modified-technique parameters were rated with a mean score of acceptable or above. All modified-technique measurements obtained inter- and intra-observer correlation coefficient agreements of 0.86 ("Good") or greater. CONCLUSION: Substantial dose reduction on follow-up scoliosis imaging with existing radiography units is achievable through task-based definition of adequate image quality and tailoring of radiation to each patient's height and weight, while still allowing for reliable assessment and reproducible measurements.

Reliable Prostate Cancer Risk Mapping From MRI Using Targeted and Systematic Core Needle Biopsy Histopathology.

OBJECTIVE: To compute a dense prostate cancer risk map for the individual patient post-biopsy from magnetic resonance imaging (MRI) and to provide a more reliable evaluation of its fitness in prostate regions that were not identified as suspicious for cancer by a human-reader in pre- and intra-biopsy imaging analysis. METHODS: Low-level pre-biopsy MRI biomarkers from targeted and non-targeted biopsy locations were extracted and statistically tested for representativeness against biomarkers from non-biopsied prostate regions. A probabilistic machine learning classifier was optimized to map biomarkers to their core-level pathology, followed by extrapolation of pathology scores to non-biopsied prostate regions. Goodness-of-fit was assessed at targeted and non-targeted biopsy locations for the post-biopsy individual patient. RESULTS: Our experiments showed high predictability of imaging biomarkers in differentiating histopathology scores in thousands of non-targeted core-biopsy locations (ROC-AUCs: 0.85-0.88), but also high variability between patients (Median ROC-AUC [IQR]: 0.81-0.89 [0.29-0.40]). CONCLUSION: The sparseness of prostate biopsy data makes the validation of a whole gland risk mapping a non-trivial task. Previous studies i) focused on targeted-biopsy locations although biopsy-specimens drawn from systematically scattered locations across the prostate constitute a more representative sample to non-biopsied regions, and ii) estimated prediction-power across predicted instances (e.g., biopsy specimens) with no patient distinction, which may lead to unreliable estimation of model fitness to the individual patient due to variation between patients in instance count, imaging characteristics, and pathologies. SIGNIFICANCE: This study proposes a personalized whole-gland prostate cancer risk mapping post-biopsy to allow clinicians to better stage and personalize focal therapy treatment plans.

INTEGRATING PROSTATE SPECIFIC ANTIGEN DENSITY BIOMARKER INTO DEEP LEARNING PROSTATE MRI LESION SEGMENTATION MODELS.

Prostate cancer lesion segmentation in multi-parametric magnetic resonance imaging (mpMRI) is crucial for pre-biopsy diagnosis and targeted biopsy guidance. Deep convolution neural networks have been widely utilized for lesion segmentation. However, these methods fail to achieve a high Dice coefficient because of the large variations in lesion size and location within the gland. To address this problem, we integrate the clinically-meaningful prostate specific antigen density (PSAD) biomarker into the deep learning model using feature-wise transformations to condition the features in latent space, and thus control the size of lesion prediction. We tested our models on a public dataset with 214 annotated mpMRI scans and compared the segmentation performance to a baseline 3D U-Net model. Results demonstrate that integrating the PSAD biomarker significantly improves segmentation performance in both Dice coefficient and centroid distance metric.

Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-Aware Contrastive Distillation.

Contrastive learning has shown great promise over annotation scarcity problems in the context of medical image segmentation. Existing approaches typically assume a balanced class distribution for both labeled and unlabeled medical images. However, medical image data in reality is commonly imbalanced (i.e., multi-class label imbalance), which naturally yields blurry contours and usually incorrectly labels rare objects. Moreover, it remains unclear whether all negative samples are equally negative. In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation. Specifically, we first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs. We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data. Second, we raise a more important question: Can we really handle imbalanced samples to yield better performance? Hence, the key innovation in ACTION is to learn global semantic relationship across the entire dataset and local anatomical features among the neighbouring pixels with minimal additional memory footprint. During the training, we introduce anatomical contrast by actively sampling a sparse set of hard negative pixels, which can generate smoother segmentation boundaries and more accurate predictions. Extensive experiments across two benchmark datasets and different unlabeled settings show that ACTION significantly outperforms the current state-of-the-art semi-supervised methods.

A Multiclass Radiomics Method-Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans.

OBJECTIVES: The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans. MATERIALS AND METHODS: The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion. RESULTS: AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95. CONCLUSIONS: A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.

Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning.

Tumor recurrence affects up to 70% of early-stage hepatocellular carcinoma (HCC) patients, depending on treatment option. Deep learning algorithms allow in-depth exploration of imaging data to discover imaging features that may be predictive of recurrence. This study explored the use of convolutional neural networks (CNN) to predict HCC recurrence in patients with early-stage HCC from pre-treatment magnetic resonance (MR) images. This retrospective study included 120 patients with early-stage HCC. Pre-treatment MR images were fed into a machine learning pipeline (VGG16 and XGBoost) to predict recurrence within six different time frames (range 1-6 years). Model performance was evaluated with the area under the receiver operating characteristic curves (AUC-ROC). After prediction, the model's clinical relevance was evaluated using Kaplan-Meier analysis with recurrence-free survival (RFS) as the endpoint. Of 120 patients, 44 had disease recurrence after therapy. Six different models performed with AUC values between 0.71 to 0.85. In Kaplan-Meier analysis, five of six models obtained statistical significance when predicting RFS (log-rank p < 0.05). Our proof-of-concept study indicates that deep learning algorithms can be utilized to predict early-stage HCC recurrence. Successful identification of high-risk recurrence candidates may help optimize follow-up imaging and improve long-term outcomes post-treatment.

Operator Learning Curve for Prostatic Artery Embolization and Its Impact on Outcomes in 296 Patients.

PURPOSE: To define operator learning curve inflection points for prostatic artery embolization (PAE) and their impact on technical efficiency, clinical outcomes, and adverse events. MATERIALS AND METHODS: Between May 2013 and May 2021, 296 consecutive patients with moderate-to-severe lower urinary tract symptoms, urinary retention, or gross hematuria from benign prostatic hyperplasia underwent PAE by an interventional radiologist without prior PAE-specific experience. Operator learning curves plotted procedure time, fluoroscopy time, contrast volume, and embolic endpoint data against sequential procedure number. Multiple regression analysis evaluated for improvements in these parameters, with segmented linear regression to detect learning curve inflection points. Linear and logistic regression evaluated for learning curve impacts on 6-month clinical outcomes and 90-day adverse events. RESULTS: No baseline patient characteristic varied over the series apart from decreasing pre-procedural gland volume (P < 0.01). Multiple regression analysis demonstrated experience-dependent improvements in procedure time, fluoroscopy time, and contrast volume (P < 0.01), with corresponding learning curve inflection points at 76 (P < 0.01), 78 (P < 0.01), and 73 (P = 0.10) procedures. Embolic endpoints did not vary with experience (P > 0.05). Post-procedure reductions in International Prostate Symptom Score (21.5 ± 6.2 to 6.7 ± 4.7), Quality of Life score (4.5 ± 1.2 to 1.3 ± 1.2), post-void residual (190 ± 203 to 97 ± 148 mL), and gland volume (142 ± 97 to 76 ± 47 mL) were substantial (P < 0.01) but did not vary with experience (P > 0.05), nor did adverse event frequency/severity (P > 0.05). CONCLUSION: Operator technical efficiency plateaued after 73-78 PAE procedures. Clinical improvements were substantial and adverse event frequency/severity low, and neither varied with experience. Operators without prior PAE-specific experience may perform PAE safely and effectively from the outset. LEVEL OF EVIDENCE: Level 2b, Cohort Study.

Machine Learning Models for Prediction of Posttreatment Recurrence in Early-Stage Hepatocellular Carcinoma Using Pretreatment Clinical and MRI Features: A Proof-of-Concept Study.

BACKGROUND. Posttreatment recurrence is an unpredictable complication after liver transplant for hepatocellular carcinoma (HCC) that is associated with poor survival. Biomarkers are needed to estimate recurrence risk before organ allocation. OBJECTIVE. This proof-of-concept study evaluated the use of machine learning (ML) to predict recurrence from pretreatment laboratory, clinical, and MRI data in patients with early-stage HCC initially eligible for liver transplant. METHODS. This retrospective study included 120 patients (88 men, 32 women; median age, 60.0 years) with early-stage HCC diagnosed who were initially eligible for liver transplant and underwent treatment by transplant, resection, or thermal ablation between June 2005 and March 2018. Patients underwent pretreatment MRI and posttreatment imaging surveillance. Imaging features were extracted from postcontrast phases of pretreatment MRI examinations using a pretrained convolutional neural network. Pretreatment clinical characteristics (including laboratory data) and extracted imaging features were integrated to develop three ML models (clinical model, imaging model, combined model) for predicting recurrence within six time frames ranging from 1 through 6 years after treatment. Kaplan-Meier analysis with time to recurrence as the endpoint was used to assess the clinical relevance of model predictions. RESULTS. Tumor recurred in 44 of 120 (36.7%) patients during follow-up. The three models predicted recurrence with AUCs across the six time frames of 0.60-0.78 (clinical model), 0.71-0.85 (imaging model), and 0.62-0.86 (combined model). The mean AUC was higher for the imaging model than the clinical model (0.76 vs 0.68, respectively; p = .03), but the mean AUC was not significantly different between the clinical and combined models or between the imaging and combined models (p > .05). Kaplan-Meier curves were significantly different between patients predicted to be at low risk and those predicted to be at high risk by all three models for the 2-, 3-, 4-, 5-, and 6-year time frames (p < .05). CONCLUSION. The findings suggest that ML-based models can predict recurrence before therapy allocation in patients with early-stage HCC initially eligible for liver transplant. Adding MRI data as model input improved predictive performance over clinical parameters alone. The combined model did not surpass the imaging model's performance. CLINICAL IMPACT. ML-based models applied to currently underutilized imaging features may help design more reliable criteria for organ allocation and liver transplant eligibility.

Identifying clinically applicable machine learning algorithms for glioma segmentation: recent advances and discoveries.

Background: While there are innumerable machine learning (ML) research algorithms used for segmentation of gliomas, there is yet to be a US FDA cleared product. The aim of this study is to explore the systemic limitations of research algorithms that have prevented translation from concept to product by a review of the current research literature. Methods: We performed a systematic literature review on 4 databases. Of 11 727 articles, 58 articles met the inclusion criteria and were used for data extraction and screening using TRIPOD. Results: We found that while many articles were published on ML-based glioma segmentation and report high accuracy results, there were substantial limitations in the methods and results portions of the papers that result in difficulty reproducing the methods and translation into clinical practice. Conclusions: In addition, we identified that more than a third of the articles used the same publicly available BRaTS and TCIA datasets and are responsible for the majority of patient data on which ML algorithms were trained, which leads to limited generalizability and potential for overfitting and bias.

Prediction of Adverse Pathology at Radical Prostatectomy in Grade Group 2 and 3 Prostate Biopsies Using Machine Learning.

PURPOSE: There is ongoing clinical need to improve estimates of disease outcome in prostate cancer. Machine learning (ML) approaches to pathologic diagnosis and prognosis are a promising and increasingly used strategy. In this study, we use an ML algorithm for prediction of adverse outcomes at radical prostatectomy (RP) using whole-slide images (WSIs) of prostate biopsies with Grade Group (GG) 2 or 3 disease. METHODS: We performed a retrospective review of prostate biopsies collected at our institution which had corresponding RP, GG 2 or 3 disease one or more cores, and no biopsies with higher than GG 3 disease. A hematoxylin and eosin-stained core needle biopsy from each site with GG 2 or 3 disease was scanned and used as the sole input for the algorithm. The ML pipeline had three phases: image preprocessing, feature extraction, and adverse outcome prediction. First, patches were extracted from each biopsy scan. Subsequently, the pre-trained Visual Geometry Group-16 convolutional neural network was used for feature extraction. A representative feature vector was then used as input to an Extreme Gradient Boosting classifier for predicting the binary adverse outcome. We subsequently assessed patient clinical risk using CAPRA score for comparison with the ML pipeline results. RESULTS: The data set included 361 WSIs from 107 patients (56 with adverse pathology at RP). The area under the receiver operating characteristic curves for the ML classification were 0.72 (95% CI, 0.62 to 0.81), 0.65 (95% CI, 0.53 to 0.79) and 0.89 (95% CI, 0.79 to 1.00) for the entire cohort, and GG 2 and GG 3 patients, respectively, similar to the performance of the CAPRA clinical risk assessment. CONCLUSION: We provide evidence for the potential of ML algorithms to use WSIs of needle core prostate biopsies to estimate clinically relevant prostate cancer outcomes.

Machine Learning Tools for Image-Based Glioma Grading and the Quality of Their Reporting: Challenges and Opportunities.

Technological innovation has enabled the development of machine learning (ML) tools that aim to improve the practice of radiologists. In the last decade, ML applications to neuro-oncology have expanded significantly, with the pre-operative prediction of glioma grade using medical imaging as a specific area of interest. We introduce the subject of ML models for glioma grade prediction by remarking upon the models reported in the literature as well as by describing their characteristic developmental workflow and widely used classifier algorithms. The challenges facing these models-including data sources, external validation, and glioma grade classification methods -are highlighted. We also discuss the quality of how these models are reported, explore the present and future of reporting guidelines and risk of bias tools, and provide suggestions for the reporting of prospective works. Finally, this review offers insights into next steps that the field of ML glioma grade prediction can take to facilitate clinical implementation.

Machine Learning Models for Classifying High- and Low-Grade Gliomas: A Systematic Review and Quality of Reporting Analysis.

Objectives: To systematically review, assess the reporting quality of, and discuss improvement opportunities for studies describing machine learning (ML) models for glioma grade prediction. Methods: This study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy (PRISMA-DTA) statement. A systematic search was performed in September 2020, and repeated in January 2021, on four databases: Embase, Medline, CENTRAL, and Web of Science Core Collection. Publications were screened in Covidence, and reporting quality was measured against the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) Statement. Descriptive statistics were calculated using GraphPad Prism 9. Results: The search identified 11,727 candidate articles with 1,135 articles undergoing full text review and 85 included in analysis. 67 (79%) articles were published between 2018-2021. The mean prediction accuracy of the best performing model in each study was 0.89 ± 0.09. The most common algorithm for conventional machine learning studies was Support Vector Machine (mean accuracy: 0.90 ± 0.07) and for deep learning studies was Convolutional Neural Network (mean accuracy: 0.91 ± 0.10). Only one study used both a large training dataset (n>200) and external validation (accuracy: 0.72) for their model. The mean adherence rate to TRIPOD was 44.5% ± 11.1%, with poor reporting adherence for model performance (0%), abstracts (0%), and titles (0%). Conclusions: The application of ML to glioma grade prediction has grown substantially, with ML model studies reporting high predictive accuracies but lacking essential metrics and characteristics for assessing model performance. Several domains, including generalizability and reproducibility, warrant further attention to enable translation into clinical practice. Systematic Review Registration: PROSPERO, identifier CRD42020209938.

MR Imaging Biomarkers for the Prediction of Outcome after Radiofrequency Ablation of Hepatocellular Carcinoma: Qualitative and Quantitative Assessments of the Liver Imaging Reporting and Data System and Radiomic Features.

PURPOSE: To assess the Liver Imaging Reporting and Data System (LI-RADS) and radiomic features in pretreatment magnetic resonance (MR) imaging for predicting progression-free survival (PFS) in patients with nodular hepatocellular carcinoma (HCC) treated with radiofrequency (RF) ablation. MATERIAL AND METHODS: Sixty-five therapy-naïve patients with 85 nodular HCC tumors <5 cm in size were included in this Health Insurance Portability and Accountability Act-compliant, institutional review board-approved, retrospective study. All patients underwent RF ablation as first-line treatment and demonstrated complete response on the first follow-up imaging. Gadolinium-enhanced MR imaging biomarkers were analyzed for LI-RADS features by 2 board-certified radiologists or by analysis of nodular and perinodular radiomic features from 3-dimensional segmentations. A radiomic signature was calculated with the most informative features of a least absolute shrinkage and selection operator Cox regression model using leave-one-out cross-validation. The association between both LI-RADS features and radiomic signatures with PFS was assessed via the Kaplan-Meier analysis and a weighted log-rank test. RESULTS: The median PFS was 19 months (95% confidence interval, 16.1-19.4) for a follow-up period of 24 months. Multifocality (P = .033); the appearance of capsular continuity, compared with an absent or discontinuous capsule (P = .012); and a higher radiomic signature based on nodular and perinodular features (P = .030) were associated with poorer PFS in early-stage HCC. The observation size, presence of arterial hyperenhancement, nonperipheral washout, and appearance of an enhancing "capsule" were not associated with PFS (P > .05). CONCLUSIONS: Although multifocal HCC clearly indicates a more aggressive phenotype even in early-stage disease, the continuity of an enhancing capsule and a higher radiomic signature may add value as MR imaging biomarkers for poor PFS in HCC treated with RF ablation.

Cryoablation of Venous Malformations: A Systematic Review.

This study aimed to review systematically the efficacy, safety, and technical aspects of cryoablation in the treatment of venous malformations (VMs) and to provide the groundwork for future studies. A literature search for clinical studies utilizing percutaneous cryoablation of VMs was performed. All clinical studies related to primary or secondary treatment of VMs with percutaneous cryoablation were included in this review. These selected studies were evaluated for patient characteristics, cryoablation technique, technical success, lesion size and pain scores before and after cryoablation, and adverse outcomes. Random effects analysis of postprocedural changes in lesion volume and pain scores was performed. There were 54 patients with 55 cases of cryoablation of VMs. Of these cases, 27 recorded changes in lesion volume and 31 recorded changes in pain scores. The weighted mean postprocedural decrease in lesion size was 92.0% (raw average, 71.7%). The weighted mean reduction in pain score was 77% (raw average, 78.2%). Considering all treated cases (55), complete resolution of symptoms was seen in 35 cases (63.6%) and overall (complete or partial) improvement in 52 cases (94.5%). Common postprocedural symptoms included pain, bruising, swelling and numbness lasting less than 2 weeks. There were two major adverse events (3.7%), with both cases due to persistent dysesthesia. Patients with a history of prior sclerotherapy demonstrated lower preprocedural and postprocedural pain scores (4.7 and 1.3) than patients without prior treatments (5.8 and 2.8). Cryoablation of VMs appears to be potentially safe and effective on limited short-interval follow-up.

Machine Learning Applications for Differentiation of Glioma from Brain Metastasis-A Systematic Review.

Glioma and brain metastasis can be difficult to distinguish on conventional magnetic resonance imaging (MRI) due to the similarity of imaging features in specific clinical circumstances. Multiple studies have investigated the use of machine learning (ML) models for non-invasive differentiation of glioma from brain metastasis. Many of the studies report promising classification results, however, to date, none have been implemented into clinical practice. After a screening of 12,470 studies, we included 29 eligible studies in our systematic review. From each study, we aggregated data on model design, development, and best classifiers, as well as quality of reporting according to the TRIPOD statement. In a subset of eligible studies, we conducted a meta-analysis of the reported AUC. It was found that data predominantly originated from single-center institutions (n = 25/29) and only two studies performed external validation. The median TRIPOD adherence was 0.48, indicating insufficient quality of reporting among surveyed studies. Our findings illustrate that despite promising classification results, reliable model assessment is limited by poor reporting of study design and lack of algorithm validation and generalizability. Therefore, adherence to quality guidelines and validation on outside datasets is critical for the clinical translation of ML for the differentiation of glioma and brain metastasis.

SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation.

Automated segmentation in medical image analysis is a challenging task that requires a large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited manually annotated medical data, which poses a major practical problem for accurate and robust medical image segmentation. In addition, most existing semi-supervised approaches are usually not robust compared with the supervised counterparts, and also lack explicit modeling of geometric structure and semantic information, both of which limit the segmentation accuracy. In this work, we present SimCVD, a simple contrastive distillation framework that significantly advances state-of-the-art voxel-wise representation learning. We first describe an unsupervised training strategy, which takes two views of an input volume and predicts their signed distance maps of object boundaries in a contrastive objective, with only two independent dropout as mask. This simple approach works surprisingly well, performing on the same level as previous fully supervised methods with much less labeled data. We hypothesize that dropout can be viewed as a minimal form of data augmentation and makes the network robust to representation collapse. Then, we propose to perform structural distillation by distilling pair-wise similarities. We evaluate SimCVD on two popular datasets: the Left Atrial Segmentation Challenge (LA) and the NIH pancreas CT dataset. The results on the LA dataset demonstrate that, in two types of labeled ratios (i.e., 20% and 10%), SimCVD achieves an average Dice score of 90.85% and 89.03% respectively, a 0.91% and 2.22% improvement compared to previous best results. Our method can be trained in an end-to-end fashion, showing the promise of utilizing SimCVD as a general framework for downstream tasks, such as medical image synthesis, enhancement, and registration.