Background: Osteoporosis is underdiagnosed and undertreated. Traditional screening methods like dual-energy X-ray absorptiometry have limitations, prompting the exploration of opportunistic screening using CT and artificial intelligence (AI). Purpose: To develop a reproducible and robust AI-based method to automatically assess spine trabecular attenuation on noncontrast CTs, irrespective of protocol or scanner model used during imaging acquisition, and to establish normative values in a large diverse population. Methods: An AI-based method was developed to automatically quantify trabecular attenuation using a 3D region of interest (ROI) of the thoracic and lumbar spine on chest, abdomen, or spine CTs, adjusted for different tube voltage and scanner models. Normative values, thresholds for osteoporosis of trabecular attenuation of the thoracic and lumbar spine were established across a diverse population, stratified by age, sex, race, and ethnicity. Differences in trabecular attenuation were assessed using the Mann-Whitney U or the Chi-Square Test. Results: 538,946 CT examinations from 283,499 patients (mean age 65 years +/- 15, 51.2% women and 55.5% White), performed on 50 scanner models using six different tube voltages were analyzed. Hounsfield Units at 80 kVp versus 120 kVp differed by 23%, and different scanner models resulted in differences of values by < 10%. Automated ROI placement was validated by manual radiologist review, demonstrating 99% agreement. Mean trabecular attenuation was higher in young women (<50 years) than young men (p<.001) and decreased with age, with a steeper decline in postmenopausal women. In patients older than 50 years, trabecular attention was higher in male than female patients (p<.001). Trabecular attenuation was highest in Blacks, followed by Asians and lowest in Whites (p<.001). The threshold for L1 in diagnosing osteoporosis was 68 HU. Conclusion: AI-based automated opportunistic osteoporosis screening can identify patients with low bone mineral density that undergo CT scans for clinical purposes on different scanners and protocols. ### Competing Interest Statement MW, NL, FH, KB are employees of Visage Imaging. ### Funding Statement This study did not receive any funding ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: This study was approved by the NYU Langone Health institutional review board and was Health Insurance Portability and Accountability Act compliant. The requirement for informed consent was waived. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present work are contained in the manuscript

Despite continuous advancements in cancer treatment, brain metastatic disease remains a significant complication of primary cancer and is associated with an unfavorable prognosis. One approach for improving diagnosis, management, and outcomes is to implement algorithms based on artificial intelligence for the automated segmentation of both pre- and post-treatment MRI brain images. Such algorithms rely on volumetric criteria for lesion identification and treatment response assessment, which are still not available in clinical practice. Therefore, it is critical to establish tools for rapid volumetric segmentations methods that can be translated to clinical practice and that are trained on high quality annotated data. The BraTS-METS 2025 Lighthouse Challenge aims to address this critical need by establishing inter-rater and intra-rater variability in dataset annotation by generating high quality annotated datasets from four individual instances of segmentation by neuroradiologists while being recorded on video (two instances doing "from scratch" and two instances after AI pre-segmentation). This high-quality annotated dataset will be used for testing phase in 2025 Lighthouse challenge and will be publicly released at the completion of the challenge. The 2025 Lighthouse challenge will also release the 2023 and 2024 segmented datasets that were annotated using an established pipeline of pre-segmentation, student annotation, two neuroradiologists checking, and one neuroradiologist finalizing the process. It builds upon its previous edition by including post-treatment cases in the dataset. Using these high-quality annotated datasets, the 2025 Lighthouse challenge plans to test benchmark algorithms for automated segmentation of pre-and post-treatment brain metastases (BM), trained on diverse and multi-institutional datasets of MRI images obtained from patients with brain metastases.

Although digital breast tomosynthesis (DBT) improves diagnostic performance over full-field digital mammography (FFDM), false-positive recalls remain a concern in breast cancer screening. We developed a multi-modal artificial intelligence system integrating FFDM, synthetic mammography, and DBT to provide breast-level predictions and bounding-box localizations of suspicious findings. Our AI system, trained on approximately 500,000 mammography exams, achieved 0.945 AUROC on an internal test set. It demonstrated capacity to reduce recalls by 31.7 underscoring its potential to improve clinical workflows. External validation confirmed strong generalizability, reducing the gap to a perfect AUROC by 35.31 sites, the system reduced recall rates for low-risk cases. An improved version, trained on over 750,000 exams with additional labels, further reduced the gap by 18.86 underscore the importance of utilizing all available imaging modalities, demonstrate the potential for clinical impact, and indicate feasibility of further reduction of the test error with increased training set when using large-capacity neural networks.

Background Abdominal computed tomography (CT) is commonly performed in adults. Abdominal aortic calcification (AAC) can be visualized and quantified using artificial intelligence (AI) on CTs performed for other clinical purposes (opportunistic CT). We sought to investigate the value of AI-enabled AAC quantification as a predictor of coronary artery disease and its association with cardiovascular events. Methods A fully automated AI algorithm to quantify AAC from the diaphragm to aortic bifurcation using the Agatston score was retrospectively applied to a cohort of patient that underwent both noncontrast abdominal CT for routine clinical care and cardiac CT for coronary artery calcification (CAC) assessment. Subjects were followed for a median of 36 months for major adverse cardiovascular events (MACE, composite of death, myocardial infarction [MI], ischemic stroke, coronary revascularization) and major coronary events (MCE, MI or coronary revascularization). The 10-year Predicting Risk of cardiovascular disease EVENTs (PREVENT) cardiovascular risk score was calculated. Results Our cohort included 3599 patients (median age 61 years, 49% female, 73% white) with an evaluable abdominal and cardiac CT. There was a positive correlation between presence and severity of AAC and CAC (r = 0.56, P < .001). AAC showed excellent discriminatory power for detecting or ruling out any CAC (AUC for PREVENT risk score 0.701 [0.683-0.718]; AUC for PREVENT plus AAC 0.782 [0.767-0.797]; P < .001). There were 324 MACE, of which 246 were MCE. Following adjustment for the PREVENT score, the presence of AAC was associated with a significant risk of MACE (adjHR 2.26, 95% CI 1.67-3.07, P < .001) and MCE (adjHR 2.58, 95% CI 1.80-3.71, P < .001). A doubling of the AAC score resulted in an 11% increase in the risk of MACE and a 13% increase in the risk of MCE. Conclusions Using opportunistic abdominal CTs, assessment of AAC using a fully automated AI algorithm, predicted CAC and was independently associated with cardiovascular events. These data support the use of opportunistic imaging for cardiovascular risk assessment. Future studies should investigate whether opportunistic imaging can help guide appropriate cardiovascular prevention strategies.

To assess whether accelerated knee MRI protocols using simultaneous multi-slice (SMS) and deep learning reconstruction (DLR) are non-inferior to a conventional parallel imaging protocol for detecting internal derangement injuries. This retrospective cohort study included 1055 patients who underwent knee MRI followed by arthroscopy within 180 days. Patients were scanned using either a conventional protocol (n = 226), an accelerated SMS protocol (n = 406), or a SMS with DLR protocol (n = 423). Each group included consecutive exams. Imaging was performed on 3 T MRI using five standardized two-dimensional turbo spin echo sequences. Radiology interpretations were compared with arthroscopy (reference standard) for anterior cruciate ligament (ACL), medial meniscus (MM), and lateral meniscus (LM) tears. Sensitivity and specificity were calculated with 95

Brain metastases are a common complication of systemic cancer, affecting over 20 imaging (MRI) is essential for diagnosing patients, tracking disease progression, assessing therapeutic response, and guiding treatment selection. However, the manual review of longitudinal imaging is time-intensive, especially for patients with multifocal disease. Artificial intelligence (AI) offers opportunities to streamline image evaluation, but developing robust AI models requires comprehensive training data representative of real-world imaging studies. Thus, there is an urgent necessity for a large dataset with heterogeneity in imaging protocols and disease presentation. To address this, we present an open-access dataset of 11,884 longitudinal brain MRI studies from 1,430 patients with clinically confirmed brain metastases, paired with clinical and image metadata. The provided dataset will facilitate the development of AI models to assist in the long-term management of patients with brain metastasis.

To develop a tool for the clinical hybrid imaging workflow which combines morphologic and functional measurements. And to quantify the number of clicks saved per positron emission tomography/computed tomography (PET/CT) interpretation. A tool was developed where a volume of interest (VOI) is automatically created around line distance measurements. VOI statistics for both PET and CT component, and line distances are generated and displayed. Usage data for the first two months after introduction of the tool was analyzed. Eleven radiologists and nuclear medicine physicians used the tool in 364 PET/CTs. In 19

Background Osteoporosis is underdiagnosed and undertreated, prompting the exploration of opportunistic screening using CT and artificial intelligence. Purpose To develop a reproducible convolutional neural network to automatically identify a three-dimensional (3D) region of interest (ROI) in trabecular bone, develop a correction method to normalize attenuation values across different CT protocols and scanner models, and establish thresholds for diagnosing osteoporosis in a large diverse population. Materials and Methods In this retrospective study, a deep learning-based method was developed to automatically quantify trabecular attenuation of the thoracic and lumbar spine on CT images with use of a 3D ROI. A statistical method was developed to adjust for different tube voltages and scanner models. Normative values and diagnostic thresholds for trabecular attenuation of the spine for osteoporosis were established based on the reported prevalence of osteoporosis by the World Health Organization. Differences between groups were assessed using the Student t test. Results A total of 538 946 CT examinations from 283 499 patients (mean age, 65 years ± 15 [SD]; 145 021 [51.2%] female; 157 457 [55.5%] White patients) were analyzed, representing 43 scanner models and six different tube voltages. The attenuation values at 80 kVp and 120 kVp differed by 23%, and different scanner models resulted in differences in values of less than 10%. The automated ROI placement of 1496 vertebrae was validated by manual radiologist review and demonstrated greater than 99% agreement. Trabecular attenuation was greater in young women (age <50 years) than in young men (P < .001) and decreased with age, with a steeper decline in postmenopausal women. In patients older than 50 years, trabecular attenuation was greater in male than in female patients (P < .001). Trabecular attenuation was highest in Black patients, followed by Asian patients, and lowest in White patients (P < .001). Conclusion Deep learning-based automated opportunistic osteoporosis screening can identify patients with low bone mineral density using CT scans obtained for clinical purposes with use of different scanners and protocols. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Feuerriegel and Sutter in this issue.

Resection and whole brain radiotherapy (WBRT) are the standards of care for the treatment of patients with brain metastases (BM) but are often associated with cognitive side effects. Stereotactic radiosurgery (SRS) involves a more targeted treatment approach and has been shown to avoid the side effects associated with WBRT. However, SRS requires precise identification and delineation of BM. While many AI algorithms have been developed for this purpose, their clinical adoption has been limited due to poor model performance in the clinical setting. Major reasons for non-generalizable algorithms are the limitations in the datasets used for training the AI network. The purpose of this study was to create a large, heterogenous, annotated BM dataset for training and validation of AI models to improve generalizability. We present a BM dataset of 200 patients with pretreatment T1, T1 post-contrast, T2, and FLAIR MR images. The dataset includes contrast-enhancing and necrotic 3D segmentations on T1 post-contrast and whole tumor (including peritumoral edema) 3D segmentations on FLAIR. Our dataset contains 975 contrast-enhancing lesions, many of which are sub centimeter, along with clinical and imaging feature information. We used a streamlined approach to database-building leveraging a PACS-integrated segmentation workflow.

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well- annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied environments and providing the tools for future development of personalized volumetric reports to patients undergoing BM treatment.

Purpose Retrospectively compare image quality, radiologist diagnostic confidence, and time for images to reach PACS for contrast enhanced abdominopelvic CT examinations created on the scanner console by technologists versus those generated automatically by thin-client artificial intelligence (AI) mechanisms. Methods A retrospective PACS search identified adults who underwent an emergency department contrast-enhanced abdominopelvic CT in 07/2022 (Console Cohort) and 07/2023 (Server Cohort). Coronal and sagittal multiplanar reformatted images (MPR) were created by AI software in the Server cohort. Time to completion of MPR images was compared using 2-sample t-tests for all patients in both cohorts. Two radiologists qualitatively assessed image quality and diagnostic confidence on 5-point Likert scales for 50 consecutive examinations from each cohort. Additionally, they assessed for acute abdominopelvic findings. Continuous variables and qualitative scores were compared with the Mann-Whitney U test. A p < .05 indicated statistical significance. Results Mean[SD] time to exam completion in PACS was 8.7[11.1] minutes in the Console cohort (n = 728) and 4.6[6.6] minutes in the Server cohort (n = 892), p < .001. 50 examinations in the Console Cohort (28 women 22 men, 51[19] years) and Server cohort (27 women 23 men, 57[19] years) were included for radiologist review. Age, sex, CTDlvol, and DLP were not statistically different between the cohorts (all p > .05). There was no significant difference in image quality or diagnostic confidence for either reader when comparing the Console and Server cohorts (all p > .05). Conclusion Examinations utilizing AI generated MPRs on a thin-client architecture were completed approximately 50% faster than those utilizing reconstructions generated at the console with no statistical difference in diagnostic confidence or image quality.

Clinical monitoring of metastatic disease to the brain can be a laborious and timeconsuming process, especially in cases involving multiple metastases when the assessment is performed manually. The Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) guideline, which utilizes the unidimensional longest diameter, is commonly used in clinical and research settings to evaluate response to therapy in patients with brain metastases. However, accurate volumetric assessment of the lesion and surrounding peri-lesional edema holds significant importance in clinical decision-making and can greatly enhance outcome prediction. The unique challenge in performing segmentations of brain metastases lies in their common occurrence as small lesions. Detection and segmentation of lesions that are smaller than 10 mm in size has not demonstrated high accuracy in prior publications. The brain metastases challenge sets itself apart from previously conducted MICCAI challenges on glioma segmentation due to the significant variability in lesion size. Unlike gliomas, which tend to be larger on presentation scans, brain metastases exhibit a wide range of sizes and tend to include small lesions. We hope that the BraTS-METS dataset and challenge will advance the field of automated brain metastasis detection and segmentation.

Objective: To test the performance of a novel machine learning-based breast density tool. The tool utilizes a convolutional neural network to predict the BI-RADS based density assessment of a study. The clinical density assessments of 33,000 mammographic examinations (164,000 images) from one academic medical center (Site A) were used for training. Materials and methods: This was an IRB approved HIPAA compliant study performed at two academic medical centers. The validation data set was composed of 500 studies from one site (Site A) and 700 from another (Site B). At Site A, each study was assessed by three breast radiologists and the majority (consensus) assessment was used as truth. At Site B, if the tool agreed with the clinical reading, then it was considered to have correctly predicted the clinical reading. In cases where the tool and the clinical reading disagreed, then the study was evaluated by three radiologists and the consensus reading was used as the clinical reading. Results: For the classification into the four categories of the Breast Imaging Reporting and Data System (BIRADS & REG;), the AI classifier had an accuracy of 84.6% at Site A and 89.7% at Site B. For binary classification (dense vs. non-dense), the AI classifier had an accuracy of 94.4% at Site A and 97.4% at Site B. In no case did the classifier disagree with the consensus reading by more than one category. Conclusions: The automated breast density tool showed high agreement with radiologists' assessments of breast density.

Purpose:Personalized interpretation of medical images is critical for optimum patient care, but current tools available to physicians to perform quantitative analysis of patient's medical images in real time are significantly limited. In this work, we describe a novel platform within PACS for volumetric analysis of images and thus development of large expert annotated datasets in parallel with radiologist performing the reading that are critically needed for development of clinically meaningful AI algorithms. Specifically, we implemented a deep learning-based algorithm for automated brain tumor segmentation and radiomics extraction, and embedded it into PACS to accelerate a supervised, end-to- end workflow for image annotation and radiomic feature extraction.Materials and methods:An algorithm was trained to segment whole primary brain tumors on FLAIR images from multi-institutional glioma BraTS 2021 dataset. Algorithm was validated using internal dataset from Yale New Haven Health (YHHH) and compared (by Dice similarity coefficient [DSC]) to radiologist manual segmentation. A UNETR deep-learning was embedded into Visage 7 (Visage Imaging, Inc., San Diego, CA, United States) diagnostic workstation. The automatically segmented brain tumor was pliable for manual modification. PyRadiomics (Harvard Medical School, Boston, MA) was natively embedded into Visage 7 for feature extraction from the brain tumor segmentations.Results:UNETR brain tumor segmentation took on average 4 s and the median DSC was 86%, which is similar to published literature but lower than the RSNA ASNR MICCAI BRATS challenge 2021. Finally, extraction of 106 radiomic features within PACS took on average 5.8 ± 0.01 s. The extracted radiomic features did not vary over time of extraction or whether they were extracted within PACS or outside of PACS. The ability to perform segmentation and feature extraction before radiologist opens the study was made available in the workflow. Opening the study in PACS, allows the radiologists to verify the segmentation and thus annotate the study.Conclusion:Integration of image processing algorithms for tumor auto-segmentation and feature extraction into PACS allows curation of large datasets of annotated medical images and can accelerate translation of research into development of personalized medicine applications in the clinic. The ability to use familiar clinical tools to revise the AI segmentations and natively embedding the segmentation and radiomic feature extraction tools on the diagnostic workstation accelerates the process to generate ground-truth data.

To design a clinically applicable workflow for application of AI tools in Neuro-oncology.

BACKGROUND. Improved communication between radiologists and patients is a key component of patient-centered radiology. OBJECTIVE. The purpose of this study was to create patient- centered video radiology reports using simple-to-understand language and annotated images and to assess the effect of these reports on patients' experience and understanding of their imaging results. METHODS. During a 4-month study period, faculty radiologists created video radiology reports using a tool integrated within the diagnostic viewer that allows both image and voice capture. To aid patients' understanding of cross-sectional images, cinematically rendered images were automatically created and made immediately available to radiologists at the workstation, allowing their incorporation into video radiology reports. Video radiology reports were made available to patients via the institutional health portal along with the written radiology report and the examination images. Patient views of the video report were recorded, and descriptive analyses were performed on radiologist and examination characteristics as well as patient demographics. A survey was sent to patients to obtain feedback on their experience. RESULTS. During the study period, 105 of 227 faculty radiologists created 3763 video radiology reports (mean number of reports per radiologist, 36 +/- 27 [SD] reports). Mean time to create a video report was 238 +/- 141 seconds. Patients viewed 864 unique video reports. The mean overall video radiology report experience rating based on 101 patient surveys was 4.7 of 5. The mean rating for how well the video report helped patients understand their findings was also 4.7 of 5. Of the patients who responded to the survey, 91% preferred having both written and video reports together over having written reports alone. CONCLUSION. Patient-centered video radiology reports are a useful tool to help improve patient understanding of imaging results. The mechanism of creating the video reports and delivering them to patients can be integrated into existing informatics infrastructure. CLINICAL IMPACT. Video radiology reports can play an important role in patient-centered radiology, increasing patient understanding of imaging results, and they may improve the visibility of radiologists to patients and highlight the radiologist's important role in patient care.

Abstract Background To externally evaluate the first picture archiving communications system (PACS)‐integrated artificial intelligence (AI)‐based workflow, trained to automatically detect a predefined computed tomography (CT) slice at the third lumbar vertebra (L3) and automatically perform complete image segmentation for analysis of CT body composition and to compare its performance with that of an established semi‐automatic segmentation tool regarding speed and accuracy of tissue area calculation. Methods For fully automatic analysis of body composition with L3 recognition, U‐Nets were trained (Visage) and compared with a conventional image segmentation software (TomoVision). Tissue was differentiated into psoas muscle, skeletal muscle, visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT). Mid‐L3 level images from randomly selected DICOM slice files of 20 CT scans acquired with various imaging protocols were segmented with both methods. Results Success rate of AI‐based L3 recognition was 100%. Compared with semi‐automatic, fully automatic AI‐based image segmentation yielded relative differences of 0.22% and 0.16% for skeletal muscle, 0.47% and 0.49% for psoas muscle, 0.42% and 0.42% for VAT and 0.18% and 0.18% for SAT. AI‐based fully automatic segmentation was significantly faster than semi‐automatic segmentation (3 ± 0 s vs. 170 ± 40 s, P < 0.001, for User 1 and 152 ± 40 s, P < 0.001, for User 2). Conclusion Rapid fully automatic AI‐based, PACS‐integrated assessment of body composition yields identical results without transfer of critical patient data. Additional metabolic information can be inserted into the patient's image report and offered to the referring clinicians.