The high-resolution three-dimensional (3D) images generated with digital breast tomosynthesis (DBT) in the screening of breast cancer offer new possibilities for early disease diagnosis. Early detection is especially important as the incidence of breast cancer increases. However, DBT also presents challenges in terms of poorer results for dense breasts, increased false positive rates, slightly higher radiation doses, and increased reading times. Deep learning (DL) has been shown to effectively increase the processing efficiency and diagnostic accuracy of DBT images. This article reviews the application and outlook of DL in DBT-based breast cancer screening. First, the fundamentals and challenges of DBT technology are introduced. The applications of DL in DBT are then grouped into three categories: diagnostic classification of breast diseases, lesion segmentation and detection, and medical image generation. Additionally, the current public databases for mammography are summarized in detail. Finally, this paper analyzes the main challenges in the application of DL techniques in DBT, such as the lack of public datasets and model training issues, and proposes possible directions for future research, including large language models, multisource domain transfer, and data augmentation, to encourage innovative applications of DL in medical imaging.

To demonstrate that a deep learning (DL) model can be employed as a teaching tool to improve radiologists' ability to perform a subsequent imaging task without additional artificial intelligence (AI) assistance at time of image interpretation. Three human readers were tasked to categorize 50 frontal knee radiographs by male and female sex before and after reviewing data derived from our DL model. The model's high accuracy in performing this task was revealed to the human subjects, who were also supplied the DL model's resultant occlusion interpretation maps ("heat maps") to serve as a teaching tool for study before final testing. Two weeks later, the three human readers performed the same task with a new set of 50 radiographs. The average accuracy of the three human readers was initially 0.59 (95%CI: 0.59-0.65), not statistically different than guessing given our sample skew. The DL model categorized sex with 0.96 accuracy. After study of AI-derived "heat maps" and associated radiographs, the average accuracy of the human readers, without the direct help of AI, on the new set of radiographs increased to 0.80 (95%CI: 0.73-0.86), a significant improvement (p=0.0270). AI-derived data can be used as a teaching tool to improve radiologists' own ability to perform an imaging task. This is an idea that we have not before seen advanced in the radiology literature. AI can be used as a teaching tool to improve the intrinsic accuracy of radiologists, even without the concurrent use of AI.

This study explores a self-learning method as an auxiliary approach in residency training for distinguishing between benign and malignant thyroid nodules. Conducted from March to December 2022, internal medicine residents underwent three repeated learning sessions with a "learning set" comprising 3000 thyroid nodule images. Diagnostic performances for internal medicine residents were assessed before the study, after every learning session, and for radiology residents before and after one-on-one education, using a "test set," comprising 120 thyroid nodule images. Finally, all residents repeated the same test using artificial intelligence computer-assisted diagnosis (AI-CAD). Twenty-one internal medicine and eight radiology residents participated. Initially, internal medicine residents had a lower area under the receiver operating characteristic curve (AUROC) than radiology residents (0.578 vs. 0.701, P < 0.001), improving post-learning (0.578 to 0.709, P < 0.001) to a comparable level with radiology residents (0.709 vs. 0.735, P = 0.17). Further improvement occurred with AI-CAD for both group (0.709 to 0.755, P < 0.001; 0.735 to 0.768, P = 0.03). The proposed iterative self-learning method using a large volume of ultrasonographic images can assist beginners, such as residents, in thyroid imaging to differentiate benign and malignant thyroid nodules. Additionally, AI-CAD can improve the diagnostic performance across varied levels of experience in thyroid imaging.

Breast cancer is a devastating disease that affects women worldwide, and computer-aided algorithms have shown potential in automating cancer diagnosis. Recently Generative Artificial Intelligence (GenAI) opens new possibilities for addressing the challenges of labeled data scarcity and accurate prediction in critical applications. However, a lack of diversity, as well as unrealistic and unreliable data, have a detrimental impact on performance. Therefore, this study proposes an augmentation scheme to address the scarcity of labeled data and data imbalance in medical datasets. This approach integrates the concepts of the Gaussian-Laplacian pyramid and pyramid blending with similarity measures. In order to maintain the structural properties of images and capture inter-variability of patient images of the same category similarity-metric-based intermixing has been introduced. It helps to maintain the overall quality and integrity of the dataset. Subsequently, deep learning approach with significant modification, that leverages transfer learning through the usage of concatenated pre-trained models is applied to classify breast cancer histopathological images. The effectiveness of the proposal, including the impact of data augmentation, is demonstrated through a detailed analysis of three different medical datasets, showing significant performance improvement over baseline models. The proposal has the potential to contribute to the development of more accurate and reliable approach for breast cancer diagnosis.

Cardiovascular disease is a leading global cause of death, requiring accurate heart segmentation for diagnosis and surgical planning. Deep learning methods have been demonstrated to achieve superior performances in cardiac structures segmentation. However, there are still limitations in 3D whole heart segmentation, such as inadequate spatial context modeling, difficulty in capturing long-distance dependencies, high computational complexity, and limited representation of local high-level semantic information. To tackle the above problems, we propose a lightweight Pyramid Pooling Transformer-CNN (P2TC) network for accurate 3D whole heart segmentation. The proposed architecture comprises a dual encoder-decoder structure with a 3D pyramid pooling Transformer for multi-scale information fusion and a lightweight large-kernel Convolutional Neural Network (CNN) for local feature extraction. The decoder has two branches for precise segmentation and contextual residual handling. The first branch is used to generate segmentation masks for pixel-level classification based on the features extracted by the encoder to achieve accurate segmentation of cardiac structures. The second branch highlights contextual residuals across slices, enabling the network to better handle variations and boundaries. Extensive experimental results on the Multi-Modality Whole Heart Segmentation (MM-WHS) 2017 challenge dataset demonstrate that P2TC outperforms the most advanced methods, achieving the Dice scores of 92.6% and 88.1% in Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) modalities respectively, which surpasses the baseline model by 1.5% and 1.7%, and achieves state-of-the-art segmentation results.

Deep learning frameworks utilizing convolutional neural networks (CNNs) have frequently been used for brain age prediction and have achieved outstanding performance. Nevertheless, deep learning remains a black box as it is hard to interpret which brain parts contribute significantly to the predictions. To tackle this challenge, we first trained a lightweight, fully CNN model for brain age estimation on a large sample data set (N = 3054, age range = [8,80 years]) and tested it on an independent data set (N = 555, age range = [8,80 years]). We then developed an interpretable scheme combining network occlusion sensitivity analysis (NOSA) with a fine-grained human brain atlas to uncover the learned invariance of the model. Our findings show that the dorsolateral, dorsomedial frontal cortex, anterior cingulate cortex, and thalamus had the highest contributions to age prediction across the lifespan. More interestingly, we observed that different regions showed divergent patterns in their predictions for specific age groups and that the bilateral hemispheres contributed differently to the predictions. Regions in the frontal lobe were essential predictors in both the developmental and aging stages, with the thalamus remaining relatively stable and saliently correlated with other regional changes throughout the lifespan. The lateral and medial temporal brain regions gradually became involved during the aging phase. At the network level, the frontoparietal and the default mode networks show an inverted U-shape contribution from the developmental to the aging stages. The framework could identify regional contributions to the brain age prediction model, which could help increase the model interpretability when serving as an aging biomarker.

<i>Radiology: Cardiothoracic Imaging</i> publishes research, technical developments, and reviews related to cardiac, vascular, and thoracic imaging. The current review article, led by the <i>Radiology: Cardiothoracic Imaging</i> trainee editorial board, highlights the most impactful articles published in the journal between November 2023 and October 2024. The review encompasses various aspects of cardiac, vascular, and thoracic imaging related to coronary artery disease, cardiac MRI, valvular imaging, congenital and inherited heart diseases, thoracic imaging, lung cancer, artificial intelligence, and health services research. Key highlights include the role of CT fractional flow reserve analysis to guide patient management, the role of MRI elastography in identifying age-related myocardial stiffness associated with increased risk of heart failure, review of MRI in patients with cardiovascular implantable electronic devices and fractured or abandoned leads, imaging of mitral annular disjunction, specificity of the Lung Imaging Reporting and Data System version 2022 for detecting malignant airway nodules, and a radiomics-based reinforcement learning model to analyze serial low-dose CT scans in lung cancer screening. Ongoing research and future directions include artificial intelligence tools for applications such as plaque quantification using coronary CT angiography and growing understanding of the interconnectedness of environmental sustainability and cardiovascular imaging. <b>Keywords:</b> CT, MRI, CT-Coronary Angiography, Cardiac, Pulmonary, Coronary Arteries, Heart, Lung, Mediastinum, Mitral Valve, Aortic Valve, Artificial Intelligence © RSNA, 2025.

Assess the feasibility of using a large language model (LLM) to identify valuable radiology teaching cases through report discrepancy detection. Retrospective study included after-hours head CT and musculoskeletal radiograph exams from January 2017 to December 2021. Discrepancy level between trainee's preliminary interpretation and final attending report was annotated on a 5-point scale. RadBERT, an LLM pretrained on a vast corpus of radiology text, was fine-tuned for discrepancy detection. For comparison and to ensure the robustness of the approach, Mixstral 8×7B, Mistral 7B, and Llama2 were also evaluated. The model's performance in detecting discrepancies was evaluated using a randomly selected hold-out test set. A subset of discrepant cases identified by the LLM was compared to a random case set by recording clinical parameters, discrepant pathology, and evaluating possible educational value. F1 statistic was used for model comparison. Pearson's chi-squared test was employed to assess discrepancy prevalence and score between groups (significance set at p<0.05). The fine-tuned LLM model achieved an overall accuracy of 90.5% with a specificity of 95.5% and a sensitivity of 66.3% for discrepancy detection. The model sensitivity significantly improved with higher discrepancy scores, 49% (34/70) for score 2 versus 67% (47/62) for score 3, and 81% (35/43) for score 4/5 (p<0.05 compared to score 2). LLM-curated set showed a significant increase in the prevalence of all discrepancies and major discrepancies (scores 4 or 5) compared to a random case set (P<0.05 for both). Evaluation of the clinical characteristics from both the random and discrepant case sets demonstrated a broad mix of pathologies and discrepancy types. An LLM can detect trainee report discrepancies, including both higher and lower-scoring discrepancies, and may improve case set curation for resident education as well as serve as a trainee oversight tool.

To evaluate the performance of large language models (LLMs) in generating clinically follow-up recommendations for pulmonary nodules by leveraging radiological report findings and management guidelines. This retrospective study included CT follow-up reports of pulmonary nodules documented by senior radiologists from September 1st, 2023, to April 30th, 2024. Sixty reports were collected for prompting engineering additionally, based on few-shot learning and the Chain of Thought methodology. Radiological findings of pulmonary nodules, along with finally prompt, were input into GPT-4o-mini or ERNIE-4.0-Turbo-8K to generate follow-up recommendations. The AI-generated recommendations were evaluated against radiologist-defined guideline-based standards through binary classification, assessing nodule risk classifications, follow-up intervals, and harmfulness. Performance metrics included sensitivity, specificity, positive/negative predictive values, and F1 score. On 1009 reports from 996 patients (median age, 50.0 years, IQR, 39.0-60.0 years; 511 male patients), ERNIE-4.0-Turbo-8K and GPT-4o-mini demonstrated comparable performance in both accuracy of follow-up recommendations (94.6 % vs 92.8 %, P = 0.07) and harmfulness rates (2.9 % vs 3.5 %, P = 0.48). In nodules classification, ERNIE-4.0-Turbo-8K and GPT-4o-mini performed similarly with accuracy rates of 99.8 % vs 99.9 % sensitivity of 96.9 % vs 100.0 %, specificity of 99.9 % vs 99.9 %, positive predictive value of 96.9 % vs 96.9 %, negative predictive value of 100.0 % vs 99.9 %, f1-score of 96.9 % vs 98.4 %, respectively. LLMs show promise in providing guideline-based follow-up recommendations for pulmonary nodules, but require rigorous validation and supervision to mitigate potential clinical risks. This study offers insights into their potential role in automated radiological decision support.