Prevalence and Association of Sarcopenia with Mortality in Patients with Head and Neck Cancer: A Systematic Review and Meta-Analysis.

BACKGROUND: The objective of this meta-analysis was to assess the association of sarcopenia defined on computed tomography (CT) head and neck with survival in head and neck cancer patients. METHODS: Following a PROSPERO-registered protocol, two blinded reviewers extracted data and evaluated the quality of the included studies using the Quality In Prognostic Studies (QUIPS) tool, in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The quality of evidence was assessed using the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) framework. A meta-analysis was conducted using maximally adjusted hazard ratios (HRs) with the random-effects model. Heterogeneity was measured using the I2 statistic and was investigated using meta-regression and subgroup analyses where appropriate. RESULTS: From 37 studies (11,181 participants), sarcopenia was associated with poorer overall survival (HR 2.11, 95% confidence interval [CI] 1.81-2.45; p < 0.01), disease-free survival (HR 1.76, 95% CI 1.38-2.24; p < 0.01), disease-specific survival (HR 2.65, 95% CI 1.80-3.90; p < 0.01), progression-free survival (HR 2.24, 95% CI 1.21-4.13; p < 0.01) and increased chemotherapy or radiotherapy toxicity (risk ratio 2.28, 95% CI 1.31-3.95; p < 0.01). The observed association between sarcopenia and overall survival remained significant across different locations of cancer, treatment modality, tumor stages and geographical region, and did not differ between univariate and multivariate HRs. Statistically significant correlations were observed between the C3 and L3 cross-sectional area, skeletal muscle mass, and skeletal muscle index. CONCLUSIONS: Among patients with head and neck cancers, CT-defined sarcopenia was consistently associated with poorer survival and greater toxicity.

A deep learning-based technique for the diagnosis of epidural spinal cord compression on thoracolumbar CT.

PURPOSE: To develop a deep learning (DL) model for epidural spinal cord compression (ESCC) on CT, which will aid earlier ESCC diagnosis for less experienced clinicians. METHODS: We retrospectively collected CT and MRI data from adult patients with suspected ESCC at a tertiary referral institute from 2007 till 2020. A total of 183 patients were used for training/validation of the DL model. A separate test set of 40 patients was used for DL model evaluation and comprised 60 staging CT and matched MRI scans performed with an interval of up to 2 months. DL model performance was compared to eight readers: one musculoskeletal radiologist, two body radiologists, one spine surgeon, and four trainee spine surgeons. Diagnostic performance was evaluated using inter-rater agreement, sensitivity, specificity and AUC. RESULTS: Overall, 3115 axial CT slices were assessed. The DL model showed high kappa of 0.872 for normal, low and high-grade ESCC (trichotomous), which was superior compared to a body radiologist (R4, κ = 0.667) and all four trainee spine surgeons (κ range = 0.625-0.838)(all p < 0.001). In addition, for dichotomous normal versus any grade of ESCC detection, the DL model showed high kappa (κ = 0.879), sensitivity (91.82), specificity (92.01) and AUC (0.919), with the latter AUC superior to all readers (AUC range = 0.732-0.859, all p < 0.001). CONCLUSION: A deep learning model for the objective assessment of ESCC on CT had comparable or superior performance to radiologists and spine surgeons. Earlier diagnosis of ESCC on CT could reduce treatment delays, which are associated with poor outcomes, increased costs, and reduced survival.

Improved Productivity Using Deep Learning-assisted Reporting for Lumbar Spine MRI.

Background Lumbar spine MRI studies are widely used for back pain assessment. Interpretation involves grading lumbar spinal stenosis, which is repetitive and time consuming. Deep learning (DL) could provide faster and more consistent interpretation. Purpose To assess the speed and interobserver agreement of radiologists for reporting lumbar spinal stenosis with and without DL assistance. Materials and Methods In this retrospective study, a DL model designed to assist radiologists in the interpretation of spinal canal, lateral recess, and neural foraminal stenoses on lumbar spine MRI scans was used. Randomly selected lumbar spine MRI studies obtained in patients with back pain who were 18 years and older over a 3-year period, from September 2015 to September 2018, were included in an internal test data set. Studies with instrumentation and scoliosis were excluded. Eight radiologists, each with 2-13 years of experience in spine MRI interpretation, reviewed studies with and without DL model assistance with a 1-month washout period. Time to diagnosis (in seconds) and interobserver agreement (using Gwet κ) were assessed for stenosis grading for each radiologist with and without the DL model and compared with test data set labels provided by an external musculoskeletal radiologist (with 32 years of experience) as the reference standard. Results Overall, 444 images in 25 patients (mean age, 51 years ± 20 [SD]; 14 women) were evaluated in a test data set. DL-assisted radiologists had a reduced interpretation time per spine MRI study, from a mean of 124-274 seconds (SD, 25-88 seconds) to 47-71 seconds (SD, 24-29 seconds) (P < .001). DL-assisted radiologists had either superior or equivalent interobserver agreement for all stenosis gradings compared with unassisted radiologists. DL-assisted general and in-training radiologists improved their interobserver agreement for four-class neural foraminal stenosis, with κ values of 0.71 and 0.70 (with DL) versus 0.39 and 0.39 (without DL), respectively (both P < .001). Conclusion Radiologists who were assisted by deep learning for interpretation of lumbar spinal stenosis on MRI scans showed a marked reduction in reporting time and superior or equivalent interobserver agreement for all stenosis gradings compared with radiologists who were unassisted by deep learning. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

Deep Learning Model for Automated Detection and Classification of Central Canal, Lateral Recess, and Neural Foraminal Stenosis at Lumbar Spine MRI.

Background Assessment of lumbar spinal stenosis at MRI is repetitive and time consuming. Deep learning (DL) could improve -productivity and the consistency of reporting. Purpose To develop a DL model for automated detection and classification of lumbar central canal, lateral recess, and neural -foraminal stenosis. Materials and Methods In this retrospective study, lumbar spine MRI scans obtained from September 2015 to September 2018 were included. Studies of patients with spinal instrumentation or studies with suboptimal image quality, as well as postgadolinium studies and studies of patients with scoliosis, were excluded. Axial T2-weighted and sagittal T1-weighted images were used. Studies were split into an internal training set (80%), validation set (9%), and test set (11%). Training data were labeled by four radiologists using predefined gradings (normal, mild, moderate, and severe). A two-component DL model was developed. First, a convolutional neural network (CNN) was trained to detect the region of interest (ROI), with a second CNN for classification. An internal test set was labeled by a musculoskeletal radiologist with 31 years of experience (reference standard) and two subspecialist radiologists (radiologist 1: A.M., 5 years of experience; radiologist 2: J.T.P.D.H., 9 years of experience). DL model performance on an external test set was evaluated. Detection recall (in percentage), interrater agreement (Gwet κ), sensitivity, and specificity were calculated. Results Overall, 446 MRI lumbar spine studies were analyzed (446 patients; mean age ± standard deviation, 52 years ± 19; 240 women), with 396 patients in the training (80%) and validation (9%) sets and 50 (11%) in the internal test set. For internal testing, DL model and radiologist central canal recall were greater than 99%, with reduced neural foramina recall for the DL model (84.5%) and radiologist 1 (83.9%) compared with radiologist 2 (97.1%) (P < .001). For internal testing, dichotomous classification (normal or mild vs moderate or severe) showed almost-perfect agreement for both radiologists and the DL model, with respective κ values of 0.98, 0.98, and 0.96 for the central canal; 0.92, 0.95, and 0.92 for lateral recesses; and 0.94, 0.95, and 0.89 for neural foramina (P < .001). External testing with 100 MRI scans of lumbar spines showed almost perfect agreement for the DL model for dichotomous classification of all ROIs (κ, 0.95-0.96; P < .001). Conclusion A deep learning model showed comparable agreement with subspecialist radiologists for detection and classification of central canal and lateral recess stenosis, with slightly lower agreement for neural foraminal stenosis at lumbar spine MRI. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Hayashi in this issue.

CT volumetry for gastric carcinoma: association with TNM stage.

OBJECTIVES: We evaluated the feasibility of performing CT volumetry of gastric carcinoma (GC) and its correlation with TNM stage. METHODS: This institutional review board-approved retrospective study was performed on 153 patients who underwent a staging CT study for histologically confirmed GC. CT volumetry was performed by drawing regions of interest including abnormal thickening of the stomach wall. Reproducibility of tumour volume (Tvol) between two readers was assessed. Correlation between Tvol and TNM/peritoneal staging derived from histology/surgical findings was evaluated using ROC analysis and compared with CT evaluation of TNM/peritoneal staging. RESULTS: Tvol was successfully performed in all patients. Reproducibility among readers was excellent (r = 0.97; P = 0.0001). The median Tvol of GC showed an incremental trend with T-stage (T1 = 27 ml; T2 = 32 ml; T3 = 53 ml and T4 = 121 ml, P < 0.01). Tvol predicted with good accuracy T-stage (≥T2:0.95; ≥T3:0.89 and T4:0.83, P = 0.0001), M-stage (0.87, P = 0.0001), peritoneal metastases (0.87, P = 0.0001) and final stage (≥stage 2:0.89; ≥stage 3:0.86 and stage 4:0.87, P = 0.0001), with moderate accuracy for N-stage (≥N1:0.75; ≥N2:0.74 and N3:0.75, P = 0.0001). Tvol was significantly (P < 0.05) more accurate than standard CT staging for prediction of T-stage, N3-stage, M-stage and peritoneal metastases. CONCLUSION: CT volumetry may provide useful adjunct information for preoperative staging of GC. KEY POINTS: CT volumetry of gastric carcinoma is feasible and reproducible. Tumour volume <19.4 ml predicts T1-stage gastric cancer with 91% sensitivity and 100% specificity (P = 0.0001). Tumour volume >95.7 ml predicts metastatic gastric cancer with 87% sensitivity and 78.5% specificity (P = 0.0001). CT volumetry may be a useful adjunct for staging gastric carcinoma.

Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs-A Systematic Review.

Osteoporosis is a complex endocrine disease characterized by a decline in bone mass and microstructural integrity. It constitutes a major global health problem. Recent progress in the field of artificial intelligence (AI) has opened new avenues for the effective diagnosis of osteoporosis via radiographs. This review investigates the application of AI classification of osteoporosis in radiographs. A comprehensive exploration of electronic repositories (ClinicalTrials.gov, Web of Science, PubMed, MEDLINE) was carried out in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement (PRISMA). A collection of 31 articles was extracted from these repositories and their significant outcomes were consolidated and outlined. This encompassed insights into anatomical regions, the specific machine learning methods employed, the effectiveness in predicting BMD, and categorizing osteoporosis. Through analyzing the respective studies, we evaluated the effectiveness and limitations of AI osteoporosis classification in radiographs. The pooled reported accuracy, sensitivity, and specificity of osteoporosis classification ranges from 66.1% to 97.9%, 67.4% to 100.0%, and 60.0% to 97.5% respectively. This review underscores the potential of AI osteoporosis classification and offers valuable insights for future research endeavors, which should focus on addressing the challenges in technical and clinical integration to facilitate practical implementation of this technology.

Association of head and neck CT-derived sarcopenia with mortality and adverse outcomes: A systematic review.

BACKGROUND: There is growing interest in the association of CT-assessed sarcopenia with adverse outcomes in non-oncological settings. PURPOSE: The aim of this systematic review is to summarize existing literature on the prognostic implications of CT-assessed sarcopenia in non-oncological patients. MATERIALS AND METHODS: Three independent authors searched Medline/PubMed, Embase and Cochrane Library up to 30 December 2023 for observational studies that reported the presence of sarcopenia defined on CT head and neck in association with mortality estimates and other adverse outcomes, in non-oncological patients. The quality of included studies were assessed using the Quality of Prognostic Studies tool. RESULTS: Overall, 15 studies (3829 participants) were included. Nine studies were at low risk of bias, and six were at moderate risk of bias. Patient populations included those admitted for trauma or treatment of intracranial aneurysms, ischemic stroke, transient ischemic attack, and intracranial stenosis. Sarcopenia was associated with increased 30-day to 2-year mortality in inpatients and patients undergoing carotid endarterectomy or mechanical thrombectomy for acute ischemic stroke. Sarcopenia was also associated with poorer neurological and functional outcomes, increased likelihood of admission to long-term care facilities, and longer duration of hospital stays. The observed associations of sarcopenia with adverse outcomes remained similar across different imaging modalities and methods for quantifying sarcopenia. CONCLUSION: CT-assessed sarcopenia was associated with increased mortality and poorer outcomes across diverse patient populations. Measurement and early identification of sarcopenia in vulnerable patients allows for enhanced prognostication, and focused allocation of resources to mitigate adverse outcomes.

Pre-treatment radiological factors associated with poor functional outcome in an Asian cohort of large vessel occlusion acute ischemic stroke patients undergoing mechanical thrombectomy.

Background and aims: Endovascular thrombectomy (EVT) is the current standard of care for large vessel occlusion (LVO) acute ischemic stroke (AIS); however, up to two-thirds of EVT patients have poor functional outcomes despite successful reperfusion. Many radiological markers have been studied as predictive biomarkers for patient outcomes in AIS. This study seeks to determine which clinico-radiological factors are associated with outcomes of interest to aid selection of patients for EVT for LVO AIS. Methods: A retrospective study of patients who underwent EVT from 2016 to 2020 was performed. Data on various radiological variables, such as anatomical parameters, clot characteristics, collateral status, and infarct size, were collected alongside traditional demographic and clinical variables. Univariate and multivariate analysis was performed for the primary outcomes of functional independence at 3 months post-stroke (modified Rankin Scale 0-2) and secondary outcomes of in-hospital mortality and symptomatic intracranial hemorrhage. Results: The study cohort comprised 325 consecutive patients with anterior circulation LVO AIS (54.5% male) with a median age of 68 years (interquartile range 57-76). The median NIHSS was 19. Age, hypertension, hyperlipidaemia, National Institutes of Health Stroke Scale (NIHSS), Alberta mCTA score, ASPECTS, clot length, thrombus HU and mTICI score and the angle between ICA and CCA were associated with functional outcomes at 3 months on univariate analysis. On multivariate analysis, age, Alberta mCTA collaterals and NIHSS were significantly associated with functional outcomes, while ASPECTS approached significance. Conclusion: Among the many proposed radiological markers for patients in the hyperacute setting undergoing EVT, the existing well-validated clinico-radiological measures remain strongly associated with functional status.

Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA.

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically.

Incidental findings involving the temporomandibular joint on computed tomography and magnetic resonance imaging.

The temporomandibular joint (TMJ) is frequently imaged in head and neck computed tomography (CT) and magnetic resonance imaging (MRI) studies. Depending on the indication for the study, an abnormality of the TMJ may be an incidental finding. These findings encompass both intra- and extra-articular disorders. They may also be related to local, regional or systemic conditions. Familiarity with these findings along with pertinent clinical information helps narrow the list of differential diagnoses. While definitive diagnosis may not be immediately apparent, a systematic approach contributes to improved discussions between clinicians and radiologists and better patient management.

Artificial Intelligence Applications for Osteoporosis Classification Using Computed Tomography.

Osteoporosis, marked by low bone mineral density (BMD) and a high fracture risk, is a major health issue. Recent progress in medical imaging, especially CT scans, offers new ways of diagnosing and assessing osteoporosis. This review examines the use of AI analysis of CT scans to stratify BMD and diagnose osteoporosis. By summarizing the relevant studies, we aimed to assess the effectiveness, constraints, and potential impact of AI-based osteoporosis classification (severity) via CT. A systematic search of electronic databases (PubMed, MEDLINE, Web of Science, ClinicalTrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 39 articles were retrieved from the databases, and the key findings were compiled and summarized, including the regions analyzed, the type of CT imaging, and their efficacy in predicting BMD compared with conventional DXA studies. Important considerations and limitations are also discussed. The overall reported accuracy, sensitivity, and specificity of AI in classifying osteoporosis using CT images ranged from 61.8% to 99.4%, 41.0% to 100.0%, and 31.0% to 100.0% respectively, with areas under the curve (AUCs) ranging from 0.582 to 0.994. While additional research is necessary to validate the clinical efficacy and reproducibility of these AI tools before incorporating them into routine clinical practice, these studies demonstrate the promising potential of using CT to opportunistically predict and classify osteoporosis without the need for DEXA.

Application of Machine Learning for Differentiating Bone Malignancy on Imaging: A Systematic Review.

An accurate diagnosis of bone tumours on imaging is crucial for appropriate and successful treatment. The advent of Artificial intelligence (AI) and machine learning methods to characterize and assess bone tumours on various imaging modalities may assist in the diagnostic workflow. The purpose of this review article is to summarise the most recent evidence for AI techniques using imaging for differentiating benign from malignant lesions, the characterization of various malignant bone lesions, and their potential clinical application. A systematic search through electronic databases (PubMed, MEDLINE, Web of Science, and clinicaltrials.gov) was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 34 articles were retrieved from the databases and the key findings were compiled and summarised. A total of 34 articles reported the use of AI techniques to distinguish between benign vs. malignant bone lesions, of which 12 (35.3%) focused on radiographs, 12 (35.3%) on MRI, 5 (14.7%) on CT and 5 (14.7%) on PET/CT. The overall reported accuracy, sensitivity, and specificity of AI in distinguishing between benign vs. malignant bone lesions ranges from 0.44-0.99, 0.63-1.00, and 0.73-0.96, respectively, with AUCs of 0.73-0.96. In conclusion, the use of AI to discriminate bone lesions on imaging has achieved a relatively good performance in various imaging modalities, with high sensitivity, specificity, and accuracy for distinguishing between benign vs. malignant lesions in several cohort studies. However, further research is necessary to test the clinical performance of these algorithms before they can be facilitated and integrated into routine clinical practice.

Combined balloon guide catheter, aspiration catheter, and stent retriever technique versus balloon guide catheter and stent retriever alone technique: a systematic review and meta-analysis.

BACKGROUND: The use of a combination of balloon guide catheter (BGC), aspiration catheter, and stent retriever in acute ischemic stroke thrombectomy has not been shown to be better than a stent retriever and BGC alone, but this may be due to a lack of power in these studies. We therefore performed a meta-analysis on this subject. METHODS: A systematic literature search was performed on PubMed, Scopus, Embase/Ovid, and the Cochrane Library from inception to October 20, 2021. Our primary outcomes were the rate of successful final reperfusion (Treatment in Cerebral Ischemia (TICI) 2c-3) and first pass effect (FPE, defined as TICI 2c-3 in a single pass). Secondary outcomes were 3 month functional independence (modified Rankin Scale score of 0-2), mortality, procedural complications, embolic complications, and symptomatic intracranial hemorrhage (SICH). A meta-analysis was performed using RevMan 5,4, and heterogeneity was assessed using the I2 test. RESULTS: Of 1629 studies identified, five articles with 2091 patients were included. For the primary outcomes, FPE (44.9% vs 45.4%, OR 1.04 (95% CI 0.90 to 1.22), I2=57%) or final successful reperfusion (64.5% vs 68.6%, OR 0.98 (95% CI 0.81% to 1.20%), I2=85%) was similar between the combination technique and stent retriever only groups. However, the combination technique had significantly less rescue treatment (18.8% vs 26.9%; OR 0.70 (95% CI 0.54 to 0.91), I2=0%). This did not translate into significant differences in secondary outcomes in functional outcomes, mortality, emboli, complications, or SICH. CONCLUSION: There was no significant difference in successful reperfusion and FPE between the combined techniques and the stent retriever and BGC alone groups. Neither was there any difference in functional outcomes, complications, or mortality.

Revolutionizing the Management of Large-Core Ischaemic Strokes: Decoding the Success of Endovascular Therapy in the Recent Stroke Trials.

Endovascular therapy (EVT) has revolutionized the management of acute ischaemic strokes with large vessel occlusion, with emerging evidence suggesting its benefit also in large infarct core volume strokes. In the last two years, four randomised controlled trials have been published on this topic-RESCUE-Japan LIMIT, ANGEL-ASPECT, SELECT2 and TENSION, with overall results showing that EVT improves functional and neurological outcomes compared to medical management alone. This review aims to summarise the recent evidence presented by these four trials and highlight some of the limitations in our current understanding of this topic.

Deep learning assessment compared to radiologist reporting for metastatic spinal cord compression on CT.

Introduction: Metastatic spinal cord compression (MSCC) is a disastrous complication of advanced malignancy. A deep learning (DL) algorithm for MSCC classification on CT could expedite timely diagnosis. In this study, we externally test a DL algorithm for MSCC classification on CT and compare with radiologist assessment. Methods: Retrospective collection of CT and corresponding MRI from patients with suspected MSCC was conducted from September 2007 to September 2020. Exclusion criteria were scans with instrumentation, no intravenous contrast, motion artefacts and non-thoracic coverage. Internal CT dataset split was 84% for training/validation and 16% for testing. An external test set was also utilised. Internal training/validation sets were labelled by radiologists with spine imaging specialization (6 and 11-years post-board certification) and were used to further develop a DL algorithm for MSCC classification. The spine imaging specialist (11-years expertise) labelled the test sets (reference standard). For evaluation of DL algorithm performance, internal and external test data were independently reviewed by four radiologists: two spine specialists (Rad1 and Rad2, 7 and 5-years post-board certification, respectively) and two oncological imaging specialists (Rad3 and Rad4, 3 and 5-years post-board certification, respectively). DL model performance was also compared against the CT report issued by the radiologist in a real clinical setting. Inter-rater agreement (Gwet's kappa) and sensitivity/specificity/AUCs were calculated. Results: Overall, 420 CT scans were evaluated (225 patients, mean age=60 ± 11.9[SD]); 354(84%) CTs for training/validation and 66(16%) CTs for internal testing. The DL algorithm showed high inter-rater agreement for three-class MSCC grading with kappas of 0.872 (p<0.001) and 0.844 (p<0.001) on internal and external testing, respectively. On internal testing DL algorithm inter-rater agreement (κ=0.872) was superior to Rad 2 (κ=0.795) and Rad 3 (κ=0.724) (both p<0.001). DL algorithm kappa of 0.844 on external testing was superior to Rad 3 (κ=0.721) (p<0.001). CT report classification of high-grade MSCC disease was poor with only slight inter-rater agreement (κ=0.027) and low sensitivity (44.0), relative to the DL algorithm with almost-perfect inter-rater agreement (κ=0.813) and high sensitivity (94.0) (p<0.001). Conclusion: Deep learning algorithm for metastatic spinal cord compression on CT showed superior performance to the CT report issued by experienced radiologists and could aid earlier diagnosis.

Clinical and radiological characteristics of spinal epidural lipomatosis: A retrospective review of 90 consecutive patients.

Background: The epidemiology and clinical characteristics of spinal epidural lipomatosis (SEL) have been well-reported in the literature. However, few studies investigated the concomitant spinal pathologies that were present in patients with SEL. Therefore, we aimed to summarize the clinical and radiological characteristics of patients with SEL diagnosed on spinal imaging. Methods: Patients who were diagnosed with SEL on magnetic resonance imaging from January 2018 to October 2020 at our institution were included in the study. Clinical data was collected using a standardized data collection form. SEL was graded using a modified version of the Borré grading system. Factors associated with moderate or severe SEL were determined using multiple logistic regression. Results: A total of 90 patients were included in the analysis. The mean (±SD) age was 59.3 (±17.1) years, and 62 patients (68.9%) were male. 61 patients (67.8%) had moderate or severe SEL. Most patients were overweight or obese (57 patients, 63.3%). The most common presenting symptoms was back pain (57 patients, 63.3%). SEL was diagnosed incidentally in 42 patients (46.7%). The lumbar spine was the most common site of SEL (35 patients, 38.9%). The most common concomitant spinal pathologies were disc bulge (83 patients, 92.2%) and flavum hypertrophy (60 patients, 66.7%). Moderate or severe SEL was associated with WHO Obesity Class, back pain or radicular leg pain at first presentation, and SEL that was worst at the lumbar or lumbosacral spinal level. Conclusions: Moderate or severe SEL were independently associated with WHO Obesity Class, back pain, radicular leg pain, and SEL that was worst at the lumbar or lumbosacral spinal level. Future studies should prospectively evaluate whether weight loss therapy is warranted in patients with SEL.

Detection of Pneumothorax with Deep Learning Models: Learning From Radiologist Labels vs Natural Language Processing Model Generated Labels.

RATIONALE AND OBJECTIVES: To compare the performance of pneumothorax deep learning detection models trained with radiologist versus natural language processing (NLP) labels on the NIH ChestX-ray14 dataset. MATERIALS AND METHODS: The ChestX-ray14 dataset consisted of 112,120 frontal chest radiographs with 5302 positive and 106, 818 negative labels for pneumothorax using NLP (dataset A). All 112,120 radiographs were also inspected by 4 radiologists leaving a visually confirmed set of 5,138 positive and 104,751 negative for pneumothorax (dataset B). Datasets A and B were used independently to train 3 convolutional neural network (CNN) architectures (ResNet-50, DenseNet-121 and EfficientNetB3). All models' area under the receiver operating characteristic curve (AUC) were evaluated with the official NIH test set and an external test set of 525 chest radiographs from our emergency department. RESULTS: There were significantly higher AUCs on the NIH internal test set for CNN models trained with radiologist vs NLP labels across all architectures. AUCs for the NLP/radiologist-label models were 0.838 (95%CI:0.830, 0.846)/0.881 (95%CI:0.873,0.887) for ResNet-50 (p = 0.034), 0.839 (95%CI:0.831,0.847)/0.880 (95%CI:0.873,0.887) for DenseNet-121, and 0.869 (95%CI: 0.863,0.876)/0.943 (95%CI: 0.939,0.946) for EfficientNetB3 (p ≤0.001). Evaluation with the external test set also showed higher AUCs (p <0.001) for the CNN models trained with radiologist versus NLP labels across all architectures. The AUCs for the NLP/radiologist-label models were 0.686 (95%CI:0.632,0.740)/0.806 (95%CI:0.758,0.854) for ResNet-50, 0.736 (95%CI:0.686, 0.787)/0.871 (95%CI:0.830,0.912) for DenseNet-121, and 0.822 (95%CI: 0.775,0.868)/0.915 (95%CI: 0.882,0.948) for EfficientNetB3. CONCLUSION: We demonstrated improved performance and generalizability of pneumothorax detection deep learning models trained with radiologist labels compared to models trained with NLP labels.