OBJECTIVE:To assess the utility of AI-driven quantification of abdominal aortic calcification (AAC) extracted from contrast-enhanced CT (CECT) scans using a fully automated AI tool for predicting all-cause mortality and cardiovascular events (CVEs). MATERIALS AND METHODS:In this retrospective cohort study, a fully automated deep learning tool for quantifying AAC from the aortic hiatus to iliac bifurcation was applied to abdominal CT scans in a large, adult population undergoing CT between January 2001 and February 2021. The aortic tool was applied to noncontrast CT (NCCT) and CECT scans. Validated linear adjustments were applied to CECT scans to derive NCCT-equivalent (NCE) measures. Death and cardiovascular events following CT were documented from the electronic health record. ROC curve and time-to-event analyses were performed to generate 5 and 10-year AUCs, HRs comparing the highest and lowest risk quartiles, and Kaplan-Meier survival curves. RESULTS:A total of 123,500 adults (mean age, 51; M:F, 58,442: 65,058) underwent abdominal CT over the study interval (43,455 NCCT; 79,885 CECT). 21,937 patients died, and 16,599 patients had a documented CVE over the study interval (median follow-up: 59 mo). Similar 10-year AUCs were observed for mortality [0.744 (NCCT), 0.732 (CECT), 0.732 (NCE)] and CVE[0.716 (NCCT), 0.718 (CECT), and 0.718 (NCE)] prediction. Comparing the highest and lowest risk quartiles, higher AAC was associated with increased mortality risk: HR of 2.08 (CI: 1.94, 2.24) for NCCT, HR of 1.8 (CI: 1.70, 1.91) for CECT ( P <0.001 for all). Higher AAC was also associated with increased CVE risk: HR of 1.73 (CI: 1.61,1.86) for NCCT, HR of 1.45 (CI: 1.35,1.55) for CECT ( P <0.001 for all). No differences were observed after applying adjustments for IV contrast. CONCLUSIONS:AAC extracted from clinical CECT scans is predictive of mortality and CVD risk, with similar performance to NCCT. AI-driven quantification of AAC from CECT is feasible and can expand the scope and impact of population-level "opportunistic screening."

Quantifying the utilization of clinical MRI exams is challenging. Using analytics tools to characterize MR exam utilization, improvement opportunities can be identified, and such tools are essential to improve the value of MRI. The purpose of this work is to develop and validate an analytics methodology that quantifies MRI exam utilization. An analytics methodology that quantifies MRI exam utilization was developed. To demonstrate the utility of this methodology, we quantified the impact of three types of interventions: 1. comparing similar protocols with the comprehensive protocol and focused surveillance protocol, 2. evaluating workflow changes with rectal cancer staging, and 3. targeted individual protocol modification with MR enterography. We successfully developed an analytics methodology to quantify MRI exam utilization. The three protocol interventions resulted in a reduction in exam time. The surveillance protocol reduced average exam time both when compared with screening protocols in the same year and when compared to patients’ prior screening exam. For rectal cancer staging, the change in methodology of communication led to a 4:33 min decrease in average exam time. MR enterography protocol modification led to a 9:55 min exam time reduction. All interventions were shown to improve MRI workflow and significantly reduce exam time (P < 0.05). We successfully developed an analytics methodology for quantifying MRI utilization and demonstrated its value with three example use cases. We conclude that the application of analytics tools for assessment of MRI utilization provides an objective strategy that permits data-driven decisions to modify protocols and improve value.

The growing volume of clinical imaging and the emergence of artificial intelligence technologies present a unique opportunity to extract additional value from existing imaging data that would otherwise go unused, providing patients with health benefits beyond the original imaging purpose through value-added opportunistic screening. By targeting clinically significant diseases and major public health concerns, opportunistic screening can enhance existing risk assessment, prevention, and treatment paradigms, expanding radiology's reach and impact for individual patients and at the population level.

There is a growing awareness that body CT scans contain rich cardiometabolic information that can be leveraged for additional patient benefits. However, the clinical implementation of opportunistic CT screening in routine practice has been hindered by valuable yet onerous manual measurements and subjective assessments. Explainable artificial intelligence (AI) algorithms are now poised to change this. The potential impact of opportunistic screening is further enhanced by the large volume of CT scans being obtained. In this "How I Do It" installment, the authors briefly outline some current approaches that can be obtained "on the fly," while focusing more on emerging automated solutions. Detecting unsuspected or presymptomatic conditions, such as osteoporosis, cardiovascular disease, sarcopenia, and hepatic steatosis, could lead to preventive interventions, regardless of the original indication for imaging. Composite models that combine multiple cardiometabolic CT biomarkers can be applied to survival prediction and assessment of biologic aging, frailty, cancer cachexia, metabolic syndrome, and fracture risk, among other factors. For clinical reporting, a range of logistical, actuarial, and ethical issues must be carefully considered. However, if executed properly, we believe that opportunistic CT screening can add substantial value, be cost saving, and provide a new level of personalized precision medicine befitting the dawning AI information era.

Abstract Understanding how patients lose body mass during cachexia is critical for improving diagnosis and developing meaningful clinical endpoints. Yet, which body compartments drive the wasting phenotype remains unknown. We hypothesized that distinct patterns of changes to body composition might stratify patients into clinically relevant subtypes of cachexia. To test this hypothesis, we computed changes in body composition across periods of weight loss in a cohort of over 6000 pan-cancer patients from MSKCC and identified that loss of subcutaneous fat, loss of skeletal muscle, and unexpectedly, gain of liver volume, were the principal alterations during cachexia. Although all patients underwent periods of weight loss, unsupervised clustering of all body composition changes identified two broad subtypes of wasted and non-wasted patients. Wasted patients had significantly inferior overall survival, increased C-reactive protein, decreased albumin, and lower rates of weight recovery. Bulk RNA-sequencing analysis from a subset of BLCA, RCC, and PDAC patients identified a unique transcriptional phenotype of wasted patients, with marked upregulation in inflammatory response, interferon gamma response, and IL6-JAK-STAT3 signalling pathways. A subset of wasted patients exhibited pronounced hepatomegaly accompanied by markers of steatosis such as decreased radiographic liver density and increased alkaline phosphatase. This wasted-hepatomegaly subgroup, characterized by pronounced systemic inflammation, showed the poorest overall survival, suggesting a potential liver-driven axis of cachexia severity. Together, our data leverages opportunistic screening of computed-tomography scans to classify weight loss episodes using a radiographic biomarker that identifies bona fide wasting cachexia in a human patient cohort. Citation Format: Sonia Boscenco, Venise Jan Castillon, Perry J. Pickhardt, John W. Garrett, Nathaniel C. Swinburne, Ed Reznik. Subtyping cancer cachexia through automated body composition [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 2676.

ABSTRACT Background Abdominal CT‐based assessments of skeletal muscle may provide important prognostic information for all‐cause mortality in aging adults. We aimed to evaluate whether AI‐segmented muscle area and muscle density predict long‐term survival in a large, retrospective adult population. Methods This retrospective study included 151 141 adult patients who underwent an abdominal CT examination for any indication between 2000 and 2021. A validated automated AI‐based algorithm measured L3‐level muscle area (cm2) and muscle density in Hounsfield units (HU). Demographic and clinical data (age, sex, BMI and date of death) were extracted from electronic health records. Survival analyses included Kaplan–Meier curves and multivariable hazard ratio (HR) models to determine the relationship between these muscle metrics and mortality. Results Among the 138 535 adults (66 468 men and 72 067 women) included, 28 489 died over the 20‐year period post‐CT, yielding an overall 20‐year survival rate of 0.620 (95% CI: 0.611–0.629). Of these, 9343 deaths occurred within the first year [survival rate: 0.933 (95% CI: 0.932–0.934)]. Mean and median follow‐up time was 6.4 and 4.9 years, respectively. Lower muscle density significantly predicted higher mortality when each patient's measurement was expressed by its percentile within the age and sex‐matched population (HR up to 3.5 in women and 4.0 in men), with decreasing mortality throughout the higher percentiles. Lower muscle area showed a more modest effect on mortality in both sexes when expressed in percentiles. Individuals with high muscle density demonstrated the most favourable survival and those with low density demonstrated the worst survival. Low muscle density significantly predicted mortality across all age groups and both sexes. Conversely, muscle area predicted mortality in all age groups in men, albeit to a lesser degree and did not predict mortality in any age group among women. Conclusions Automated CT‐based measurements of muscle density are superior to muscle area in predicting all‐cause mortality in a large, heterogeneous adult population. Incorporating AI‐driven muscle density assessments into routine clinical practice could substantially improve patient risk stratification and management, of particular relevance for aging and sarcopenic patients.

OBJECTIVES:We evaluated whether automated CT-based adiposity tools can predict all-cause mortality in a large retrospective adult population. METHODS:This study included 151 177 patients who underwent abdominal CT between 2000 and 2021. An AI-based algorithm measured abdominal visceral adipose tissue (VAT) cross-sectional area and density at the L3. Kaplan-Meier survival curves and hazard ratios assessed VAT and mortality. RESULTS:Among 136 895 patients included, 9059 died within 1 year and 18 829 died within 2 to 20 years post-CT. Higher VAT density predicted 1-year mortality (hazard ratio [HR] up to 3.8) and over 2-20 years (HR up to 2.1). In contrast, VAT area did not significantly predict mortality. High VAT density was associated with the poorest survival, regardless of area. Low VAT density predicted better survival, regardless of area. VAT density consistently predicted mortality across age groups and sexes, whereas BMI did not differentiate risk. CONCLUSIONS:AI-enabled CT measures of VAT density are superior to VAT area for predicting all-cause mortality. Furthermore, we analysed VAT density vs. BMI in our largest age group (40-59) and found BMI was unable to adequately predict risk of mortality. Automated assessment of VAT density may enhance patient risk assessment and management. ADVANCES IN KNOWLEDGE:Assessing visceral fat density using fully automated AI-based CT tools offers a significant advancement in predicting health risk, leading to targeted interventions and improved management strategies. This study is novel due to its large patient population, offering evidence that prognostication with VAT density is broadly generalizable across varying patient populations.

This study assessed variation of automated CT-based L1 trabecular attenuation for opportunistic CT screening across multiple U.S.-based healthcare systems. L1 HU measurements demonstrated similar behavior among the five sites, including relative relationships according to age, sex, race, and CT scanner, and < 100 HU was generalizable for practical opportunistic CT screening and diagnosis. To assess variability of automated population-based L1 trabecular attenuation (HU) measurement at abdominal CT among five US-based medical systems and consider a practical 100 HU threshold for opportunistic CT-based osteoporosis screening and diagnosis. Heterogeneous adult patient cohorts undergoing abdominal CT evaluation for any indication at five US medical systems were included for L1 vertebral body trabecular attenuation (L1 HU) assessment using a validated AI pipeline that places a fully automated ROI. Exclusion criteria included IV contrast, non-120 kVp setting, and non-physiologic outliers. All results were normalized to White patient ranges after age and sex matching. Thresholds of 100 HU and 120 HU were considered. The final multi-center cohort included 123,001 adults (51.1

To report longitudinal intra-patient changes in CT-based body composition using fully automated AI tools in an adult patient sample. This retrospective longitudinal study included 15,616 adult patients (mean age at first CT, 53.0 ± 14.7 years; 7096 male, 8520 female) who underwent at least two abdominal CT examinations at least five years apart (mean study interval, 9.1 ± 3.3 years, range, 5.0-20.4 years) at a single academic institution between January 1, 2000 and February 28, 2021. CT examinations were not restricted based on patient setting, clinical indication, or IV contrast media use. Seven fully automated AI body composition tools quantifying vertebral trabecular attenuation, skeletal muscle area and attenuation, visceral adipose tissue (VAT) area and attenuation, subcutaneous adipose tissue (SAT) area, and VAT/SAT ratio (VSR) were applied to each patient’s first and last available abdominal CT. Change in body composition per year were determined using the first and last available CT scans. T-test and linear regression were used to assess sex and age as predictors of longitudinal body composition change, respectively. Significant differences in sex-specific mean rates of change were observed for all measures (p < 0.05) except muscle attenuation. Certain CT biomarkers showed varying rates of change among younger, middle-age, and older adults. Age significantly predicted body composition measures except VSR in female patients, although effect size was small (R2 values 0.002–0.040). There are significant age and sex-specific differences in longitudinal, intra-patient body composition changes over time.

BACKGROUND:Proton density fat fraction (PDFF) measured using magnetic resonance imaging (MRI) is considered a noninvasive reference measure of fat deposition in various tissues and has been proposed as a quantitative indicator of tissue quality. Although the contraindications of MRI limit PDFF as a routine clinical tool, computed tomography (CT) scans are often available clinically. Currently, there are no standard methods to compare CT and MRI tissue density measures. OBJECTIVES:The objective of this study was to determine the relationship between CT and MRI tissue density values in skeletal muscle and subcutaneous adipose tissue (SAT). METHODS:Tissue density (using same-day CT and MRI) was assessed for both muscle and SAT in a healthy prospective clinical cohort [n = 50, 23 males, 27 females; mean age: 57 ± 5 y; BMI (kg/m2): 27 ± 5]. Comparisons using small regions of interest and entire cross-sectional areas (CSAs) were made at both L1 and L3 vertebral levels. CT CSA was measured using automated artificial intelligence-based segmentation software. All other measurements were demarcated manually. Regressions with 95% confidence intervals were fitted separately for each comparison. RESULTS:A strong negative linear correlation was found for all CT Hounsfield unit (HU)-PDFF tissue density pairings. The strongest association for skeletal muscle tissue density was measured at L3 using CSA [PDFF (%) = -0.352 × mean CT attenuation (HU) + 26.4; r2 = 0.791]. The strongest linear correlation for SAT density was identified at L1 using CSA [PDFF (%) = -0.604 × mean CT attenuation (HU) + 31.2; r2 = 0.885]. CONCLUSIONS:It is feasible to convert density values from CT scans to accurate estimates of PDFF in skeletal muscle and SAT. Conversion of tissue density values from CT HU to estimated PDFF expands clinical measures of muscle quality and improves body composition assessment.

Background:The early detection of clinical deterioration and timely intervention for hospitalized patients can improve patient outcomes. The currently existing early warning systems rely on variables from structured data, such as vital signs and laboratory values, and do not incorporate other potentially predictive data modalities. Because respiratory failure is a common cause of deterioration, chest radiographs are often acquired in patients with clinical deterioration, which may be informative for predicting their risk of intensive care unit (ICU) transfer. Objective:This study aimed to compare and validate different computer vision models and data augmentation approaches with chest radiographs for predicting clinical deterioration. Methods:This retrospective observational study included adult patients hospitalized at the University of Wisconsin Health System between 2009 and 2020 with an elevated electronic cardiac arrest risk triage (eCART) score, a validated clinical deterioration early warning score, on the medical-surgical wards. Patients with a chest radiograph obtained within 48 hours prior to the elevated score were included in this study. Five computer vision model architectures (VGG16, DenseNet121, Vision Transformer, ResNet50, and Inception V3) and four data augmentation methods (histogram normalization, random flip, random Gaussian noise, and random rotate) were compared using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC) for predicting clinical deterioration (ie, ICU transfer or ward death in the following 24 hours). Results:The study included 21,817 patient admissions, of which 1655 (7.6%) experienced clinical deterioration. The DenseNet121 model pretrained on chest radiograph datasets with histogram normalization and random Gaussian noise augmentation had the highest discrimination (AUROC 0.734 and AUPRC 0.414), while the vision transformer having 24 transformer blocks with random rotate augmentation had the lowest discrimination (AUROC 0.598). Conclusions:The study shows the potential of chest radiographs in deep learning models for predicting clinical deterioration. The DenseNet121 architecture pretrained with chest radiographs performed better than other architectures in most experiments, and the addition of histogram normalization with random Gaussian noise data augmentation may enhance the performance of DenseNet121 and pretrained VGG16 architectures.

Aging is a complex phenomenon reflecting the time-dependent accumulation of damage that results in progressive structural and functional decline, disease risk, and death. Chronological age (CA) is an imperfect measure of health but remains an important driver of health care decisions. Biological age (BA) is a construct that attempts to provide a more holistic evaluation of the cumulative effects of aging and aging-related disease. The emergence of "omics"-based aging clocks (eg, epigenomics) has improved BA estimation, but imaging remains underutilized. CT biomarkers of muscle, fat, aortic calcification, and bone are examples of biomarkers of aging that can be used to construct a BA model (ie, CT-based biological age). As opposed to cellular and subcellular "frailomics" used in existing BA models, CT biomarkers are accessible and reproducible and reflect big-picture net phenotypic effects of aging at the tissue level (eg, using tissue segmentation). Recent technological advancements and improvements in artificial intelligence (AI) technologies have transformed our understanding of aging, and rapid automated AI tools enable scaling of image-based approaches for population-level impact. The understandable nature of explainable AI imaging tools instills trust in a model's prediction compared with opaque black box methodologies. Automated imaging-based body composition tools also can be applied opportunistically in either a retrospective or prospective fashion without the need for additional imaging, specialized testing, or patient time. Using a CT-based phenotypic approach to BA estimation is a practical example of opportunistic imaging that could be used to improve existing medical decision making and risk prediction for individual patient and societal benefit in ways that existing frailomics have failed. ©RSNA, 2025 See the invited commentary by Pyrros and Siddiqui in this issue.

Foundation models, pre-trained on extensive datasets, have significantly advanced machine learning by providing robust and transferable embeddings applicable to various domains, including medical imaging diagnostics. This study evaluates the utility of embeddings derived from both general-purpose and medical domain-specific foundation models for training lightweight adapter models in multi-class radiography classification, focusing specifically on tube placement assessment and related findings, with comparison to the end-to-end training of an established convolutional neural network. A dataset comprising 8842 radiographs classified into seven distinct categories was employed to extract embeddings using seven foundation models: DenseNet121, BiomedCLIP, Med-Flamingo, MedImageInsight, MedSigLIP, Rad-DINO, and CXR-Foundation. Adapter models were subsequently trained using classical machine learning algorithms, including K-nearest neighbors (KNN), logistic regression (LR), support vector machines (SVM), random forest (RF), and multi-layer perceptron (MLP). Among these combinations, MedImageInsight embeddings paired with an SVM or MLP adapter yielded the highest mean area under the curve (mAUC) at 93.1%, followed closely by MedSigLIP with MLP (91.0%), Rad-DINO with SVM (90.7%), and CXR-Foundation with LR (88.6%), achieving a higher mAUC score than a fully finetuned convolutional neural network, DenseNet121 (87.2%). In comparison, BiomedCLIP and DenseNet121 exhibited moderate performance with SVM, obtaining mAUC scores of 82.8% and 81.1%, respectively, whereas Med-Flamingo delivered the lowest performance at 78.5% when combined with RF. Significant differences were found between each embedding model and MedImageInsight using the Wilcoxon signed-rank test at the significance level 0.05 (before Bonferroni correction). Notably, most adapter models demonstrated computational efficiency, achieving training within minutes and inference within seconds on CPU, underscoring their practicality for clinical applications. Furthermore, fairness analysis on adapters trained on MedImageInsight-derived embeddings indicated minimal disparities, with gender differences in performance within 1.8% and standard deviations across age groups not exceeding 1.4%. Further analysis indicated there is no significant difference across gender and age at a significance level of 0.05. These findings confirm that foundation model embeddings-especially those from MedImageInsight-facilitate accurate, computationally efficient, and equitable diagnostic classification using lightweight adapters for radiographic image analysis.

We derive and test a CT-based biological age model for predicting longevity, using an automated pipeline of explainable AI algorithms that quantifies skeletal muscle, abdominal fat, aortic calcification, bone density, and solid abdominal organs. We apply these AI tools to abdominal CT scans from 123,281 adults (mean age, 53.6 years; 47% women; median follow-up, 5.3 years). The final weighted CT biomarker selection was based on the index of prediction accuracy. The CT model significantly outperforms standard demographic data for predicting longevity (IPA = 29.2 vs. 21.7; 10-year AUC = 0.880 vs. 0.779; p < 0.001). Age- and sex-corrected survival hazard ratio for the highest-vs-lowest risk quartile was 8.73 (95% CI,8.14-9.36) for the CT biological age model, and increased to 24.79 after excluding cancer diagnoses within 5 years of CT. Muscle density, aortic plaque burden, visceral fat density, and bone density contributed the most. Here we show a personalized phenotypic CT biological age model that can be opportunistically-derived, regardless of clinical indication, to better inform risk assessment.

BACKGROUND:Prekidney transplant evaluation routinely includes abdominal CT for presurgical vascular assessment. A wealth of body composition data are available from these CT examinations, but they remain an underused source of data, often missing from prognostication models, as these measurements require organ segmentation not routinely performed clinically by radiologists. We hypothesize that artificial intelligence facilitates accurate extraction of abdominal CT body composition data, allowing better prediction of outcomes. METHODS:We conducted a retrospective, single-center observational study of kidney transplant candidates wait-listed between January 1, 2007, and December 31, 2017, with available CT data. Validated deep learning models quantified body composition including fat, aortic calcification, bone density, and muscle mass. Logistic regression was used to compare body composition data to Expected Post-Transplant Survival Score (EPTS) as a predictor of 5-year wait-list mortality. RESULTS:In all, 899 patients were followed for a median 943 days (interquartile range 320-1,697). Of 899, 589 (65.5%) were men and 680 of 899 (75.6%) were White, non-Hispanic. Of 899, 167 patients (18.6%) died while on the waiting list. Myosteatosis (defined as the lowest tertile of muscle attenuation) and increased total aortic and abdominal calcification were associated with increased 5-year wait-list mortality. Logistic regression showed that imaging parameters performed similarly to EPTS at predicting 5-year wait-list mortality (area under receiver operating characteristic curve 0.70 [0.64-0.75] versus 0.67 [0.62-0.72], respectively), and combining body composition parameters with EPTS led to a slight improved survival prediction (area under receiver operating characteristic curve = 0.72, 95% confidence interval 0.66-0.76). CONCLUSIONS:Fully automated quantification of body composition in kidney transplant candidates is feasible. Myosteatosis and atherosclerosis are associated with 5-year wait-list mortality.

Fully automated AI-based algorithms can quantify adipose tissue on abdominal CT images. The aim of this study was to investigate the clinical value of these biomarkers by determining the association between adipose tissue measures and all-cause mortality. This retrospective study included 151,141 patients who underwent abdominal CT for any reason between 2000 and 2021. A validated AI-based algorithm quantified subcutaneous (SAT) and visceral (VAT) adipose tissue cross-sectional area. A visceral-to-subcutaneous adipose tissue area ratio (VSR) was calculated. Clinical data (age at the time of CT, sex, date of death, date of last contact) was obtained from a database search of the electronic health record. Hazard ratios (HR) and Kaplan–Meier curves assessed the relationship between adipose tissue measures and mortality. The endpoint of interest was all-cause mortality, with additional subgroup analysis including age and gender. 138,169 patients were included in the final analysis. Higher VSR was associated with increased mortality; this association was strongest in younger women (highest compared to lowest risk quartile HR 3.32 in 18-39y). Lower SAT was associated with increased mortality regardless of sex or age group (HR up to 1.63 in 18-39y). Higher VAT was associated with increased mortality in younger age groups, with the trend weakening and reversing with age; this association was stronger in women. AI-based CT measures of SAT, VAT, and VSR are predictive of mortality, with VSR being the highest performing fat area biomarker overall. These metrics tended to perform better for women and younger patients. Incorporating AI tools can augment patient assessment and management, improving outcome.

Purpose: Surveys to assess views about artificial intelligence (AI) of various diagnostic radiology constituencies have revealed interesting combinations of enthusiasm, caution, and implementation priorities. We surveyed academic radiology leaders about their views on AI and how they intend to approach AI implementation in their departments. Materials and methods: We conducted a web survey of Society of Chairs of Academic Radiology Departments members between October 5 and October 31, 2023, to solicit optimism or pessimism about AI, target use cases, planned implementation, and perceptions of their workforce. P values are provided only for descriptive purposes and have not been adjusted for multiple testing in this exploratory research. Results: The survey was sent to the 112 Society of Chairs of Academic Radiology Departments members and 43 responded (38%). Chairs were optimistic, with no statistical difference between views of AI in general versus generative AI. Chairs plan to implement AI to improve quality and efficiency (43 of 43, 100%), burnout (41 of 43, 95%), health care costs (22 of 43, 51%), and equity (27 of 43, 63%) and most likely will target the postprocessing (26 of 43, 60%), interpretation workflow (26 of 43, 60%), and image acquisition (18 of 43, 42%) steps in the imaging value chain. Chairs perceived that radiologists (36 of 43, 84%) and technologists (38 of 43, 88%) were not particularly worried about being displaced but saw trainees as slightly less confident (31 of 43, 72%). Free text responses revealed concerns about the cost of AI and emphasized trade-offs that needed to be balanced. Conclusion: Radiology chairs are optimistic about AI and poised to tackle departmental challenges. Concerns about generative AI and workforce replacement are minimal.

To correlate fully-automated PMCT-based body composition measures with causes of death and comorbidities. Retrospective study of New Mexico Decedent Image Database (NMDID) with non-contrast PMCT scans between 2010 and 2017. Automated pipeline of AI-driven algorithms for quantifying skeletal muscle, subcutaneous/visceral fat, and aortic calcification from the abdominal component of PMCT scans was used. Scans with more than minimal decomposition were excluded. Cause of death was categorized as “acute” or “chronic.” A predetermined model derived CT-based “biological age.” 6638 decedents (mean age, 50±18 [SD]; 74

To quantify the potential of fully automated CT-based body composition metrics and clinical frailty data in predicting liver transplant recipient postoperative outcomes. AI-enabled body composition tools were applied to pre-transplant abdominal CT scans in a retrospective cohort of first-time deceased-donor liver transplant recipients. Clinical frailty data (Fried frailty score) was obtained from an established transplant database. Age- and sex-corrected hazard ratios (HRs) were analyzed according to highest-risk quartiles compared with the other three quartiles combined. Area under the receiver operating characteristic curve (ROC AUC) analysis in univariate and multivariate scenarios was also performed. 598 liver transplant recipients (median age, 56 years [IQR, 49–61]; 383 men/215 women) were included from 2005 to 2021. Mean clinical follow-up interval after transplant was 8.6 ± 4.5 years, with 224 deaths (mean interval, 5.3 ± 3.9 years post-transplant) and 246 graft failures (mean interval, 4.7 ± 4.0 years post-transplant) observed. Univariate HRs for post-transplant survival included 1.53 (95

Accurate, reproducible body composition analysis from abdominal computed tomography (CT) images is critical for both clinical research and patient care. We present a fully automated, artificial intelligence (AI)-based pipeline that streamlines the entire process-from data normalization and anatomical landmarking to automated tissue segmentation and quantitative biomarker extraction. Our methodology ensures standardized inputs and robust segmentation models to compute volumetric, density, and cross-sectional area metrics for a range of organs and tissues. Additionally, we capture selected DICOM header fields to enable downstream analysis of scan parameters and facilitate correction for acquisition-related variability. By emphasizing portability and compatibility across different scanner types, image protocols, and computational environments, we ensure broad applicability of our framework. This toolkit is the basis for the Opportunistic Screening Consortium in Abdominal Radiology (OSCAR) and has been shown to be robust and versatile, critical for large multi-center studies.