Purpose To develop a deep learning model that integrates longitudinal mammograms and static clinical data for predicting the recurrence risk and recurrence subtype of breast cancer. Materials and Methods In this retrospective study, the data of patients examined via imaging from January 2004 to December 2020 were included. A multimodal deep learning model incorporating pretreatment mammographic features and clinical data were developed. A multitask framework was implemented to jointly predict recurrence occurrence (binary classification) and recurrence subtype (local/regional/distant). The model was trained and evaluated within a single institutional cohort. Results A total of 3,923 patients and 19,684 examinations (mean age ± SD, 52.98 years ± 10.98; 3923 female) were included. In the test cohort, the model achieved an area under the receiver operating characteristic curve (AUC) of 0.80 (95% CI: 0.74, 0.85) and an area under the precision-recall curve (AUPRC) of 0.537 (95% CI: 0.432, 0.638) for overall recurrence, outperforming unimodal approaches. For recurrence subtype prediction among recurrencepositive patients, the model achieved a balanced accuracy of 65.1% (95% CI: 60.2%, 71.1%) and an AUC of 0.72 (95% CI: 0.68, 0.78). Conclusion The proposed multimodal deep learning framework improves both recurrence prediction and recurrence subtype discrimination over existing models. ©RSNA, 2026.
Purpose To investigate whether selective removal of vascular structures can improve lesion visibility and interpretability in maximum intensity projection (MIP) images derived from dynamic contrast-enhanced MRI. Materials and Methods A retrospective analysis was conducted using breast MRI scans from the Duke-Breast-Cancer-MRI (Duke) dataset for model development. DeepVEST, a deep learning method for automatic vessel segmentation and removal, was developed. A reader study with five breast radiologists was conducted to evaluate the impact of vessel-removed MIPs on lesion assessment, using images from the Duke and Advanced-MRI-Breast-Lesions (AMBL) datasets. Segmentation performance was evaluated against manually annotated vessel segmentations using the Dice similarity coefficient (DSC), and perceived usefulness and quality were measured through reader study metrics. Interreader agreement on vessel removal quality and artifact impact was calculated using the Gwet agreement coefficient (AC1). Results DeepVEST achieved a DSC of 0.611 for vessel segmentation. In the reader study (150 assessments, 600 responses), vessels partially or fully obscured lesion margins in 91 of 150 assessments (60.7%). Vessel removal effectiveness was rated 3.820 ± 0.749 on a 5-point Likert scale. Artifacts were reported in 45 of 150 assessments (30.0%), with a low average severity score of 0.493 ± 0.900 (scale 0-5), indicating minimal image quality impact. Substantial interreader agreement was observed for vessel removal quality (AC1 = 0.703) and artifact evaluation (AC1 = 0.736). Conclusion DeepVEST enabled automatic vessel segmentation and removal in breast MRI MIP images, showing high effectiveness with minimal artifacts. Most readers found it helpful for lesion assessment in challenging cases. ©RSNA, 2026.
Research on AI in diagnostic radiology has focused on algorithm development and standalone performance, yet the human-AI interactions that ultimately determine the clinical value of AI are poorly understood. A narrative synthesis of the human-AI interaction and radiology AI literature highlighted three underrecognized determinants of successful human-AI collaboration in radiology. First, cognitive psychology dictates how automation bias, the framing of AI uncertainty, and AI-induced skill decay distort diagnostic reasoning. Second, the user interface (UI) and user experience (UX) of AI tools determine how the timing, salience, and documentation of AI findings shape radiologists' attention and reporting behavior; the influence of UI/UX is becoming even more critical as generative AI introduces novel applications and interaction paradigms. Third, algorithmic conformity leads radiologists to override their own judgment under medicolegal, transparency, and organizational pressures. For each domain, concrete research directions are proposed to bridge the gap between algorithmic capabilities and clinical utility.
Artificial intelligence (AI) is being deployed in radiology for image reconstruction and postprocessing to produce images that appear sharper, smoother, and more detailed. However, incorporating AI also introduces new failure modes and can exacerbate the disconnect between the perceived quality of an image and its diagnostic information content. Understanding the limitations of AI-enabled image reconstruction and postprocessing is essential for the safe and effective use of this technology. Therefore, the purpose of this report is to raise awareness of the limitations of AI-based image reconstruction and postprocessing to help users realize the benefits of the technology while minimizing risks. Accordingly, this report reviews approaches to image quality assessment, discusses the regulatory framework relevant to AI-enabled imaging devices, describes AI-specific failure modes, and outlines strategies to mitigate associated risks.
