Prostate MRI has transformed lesion detection and risk stratification in prostate cancer, but its impact is constrained by the high cost of the exam, variability in interpretation, and limited scalability. False negatives, false positives, and moderate inter-reader agreement undermine reliability, while long acquisition times restrict throughput. Artificial intelligence (AI) offers potential solutions to address many of the limitations of prostate MRI in the clinical management pathway. Machine learning-based triage can refine patient selection to optimize resources. Deep learning reconstruction enables accelerated acquisition while preserving diagnostic quality, with multiple FDA-cleared products now in clinical use. Ongoing development of automated quality assessment and artifact correction aims to improve reliability by reducing nondiagnostic exams. In image interpretation, AI models for lesion detection and clinically significant prostate cancer prediction achieve performance comparable to radiologists, and the PI-CAI international reader study has provided the strongest evidence to date of non-inferiority at scale. More recent work extends MRI-derived features into prognostic modeling of recurrence, metastasis, and functional outcomes. This review synthesizes progress across five domains-triage, accelerated acquisition and reconstruction, image quality assurance, diagnosis, and prognosis-highlighting the level of evidence, validation status, and barriers to adoption. While acquisition and reconstruction are furthest along, with FDA-cleared tools and prospective evaluations, triage, quality control, and prognosis remain earlier in development. Ensuring equitable performance across populations, incorporating uncertainty estimation, and conducting prospective workflow trials will be essential to move from promising prototypes to routine practice. Ultimately, AI could accelerate the adoption of prostate MRI toward a scalable platform for earlier detection and population-level prostate cancer management. EVIDENCE LEVEL: N/A TECHNICAL EFFICACY: 3.

Transformers have shown remarkable performance in 3D medical image segmentation, but their high computational requirements and need for large amounts of labeled data limit their applicability. To address these challenges, we consider two crucial aspects: model efficiency and data efficiency. Specifically, we propose Light-UNETR, a lightweight transformer designed to achieve model efficiency. Light-UNETR features a Lightweight Dimension Reductive Attention (LIDR) module, which reduces spatial and channel dimensions while capturing both global and local features via multi-branch attention. Additionally, we introduce a Compact Gated Linear Unit (CGLU) to selectively control channel interaction with minimal parameters. Furthermore, we introduce a Contextual Synergic Enhancement (CSE) learning strategy, which aims to boost the data efficiency of Transformers. It first leverages the extrinsic contextual information to support the learning of unlabeled data with Attention-Guided Replacement, then applies Spatial Masking Consistency that utilizes intrinsic contextual information to enhance the spatial context reasoning for unlabeled data. Extensive experiments on various benchmarks demonstrate the superiority of our approach in both performance and efficiency. For example, with only 10% labeled data on the Left Atrial Segmentation dataset, our method surpasses BCP by 1.43% Jaccard while drastically reducing the FLOPs by 90.8% and parameters by 85.8%. Code is released at https://github.com/CUHK-AIM-Group/Light-UNETR.

Accurate identification of benign and malignant bile duct dilatation (BDD) is needed to determine its management plan. Conventional imaging evaluation is subjective, whereas deep learning (DL) offers potential for automated objective assessment. To construct and evaluate DL models and ensemble strategies based on magnetic resonance cholangiopancreatography (MRCP) images for identifying benign and malignant BDD. Retrospective and prospective. A retrospective cohort (n = 378; median age, 60 years [range: 14, 90]; 194 male) from two institutions and a prospective cohort (n = 60; median age, 62.5 years [range: 15, 86]; 30 male) were included. Retrospective data were randomly stratified split into training, validation, and internal test sets (2:1:1) and an independent external test set. Benign cases were downsampled to balance class distribution. 3 T MRCP (3D turbo spin echo: VISTA and SPACE). The primary retrospective endpoint was area under the curve (AUC) across DL algorithms and ensembles. Prospectively, the accuracy, sensitivity, and specificity of the model was compared with those of three radiologists. Group comparisons used Mann-Whitney U and Chi-square tests (p < 0.05). Model performance was evaluated using the Hosmer-Lemeshow test, DeLong's test with Bonferroni correction (α = 0.005), and McNemar's test. The Xception model achieved AUCs of 0.816 (95% CI, 0.788-0.844) on the internal test set and 0.807 (95% CI, 0.779-0.835) on the external test set. The ensemble model incorporating logistic regression yielded higher patient-level AUCs of 0.890 and 0.885, with good calibration (p = 0.109). No significant differences were observed among the five ensemble strategies (minimum adjusted p = 0.62). In the prospective cohort, the model showed 90.0% accuracy, sensitivity, and specificity, comparable to radiologists (76.7%-86.7%) without a significant difference (p = 0.143, 0.302, and 0.774, respectively). The Xce-LR model shows potential for automating BDD differentiation using MRCP. Stage 2.

Detecting Brain Tumors is essential in medical imaging, as early and accurate diagnosis significantly improves treatment decisions and patient outcomes. Convolutional Neural Networks have demonstrated high efficiency in this domain, but their lack of interpretability remains a significant drawback for clinical adoption. This study explores the integration of Explainability techniques to enhance transparency in CNN-based classification and improve model performance through advanced optimization strategies. The primary research question addressed is how to improve the accuracy, generalization, and interpretability of CNNs for brain tumor Detection. While previous studies have demonstrated the effectiveness of deep learning for tumor detections, challenges such as class imbalance and overfitting of CNNs persist. To bridge this gap, we employ different dynamic learning rate modifiers, perform architectural enhancements, and apply XAI techniques, including Grad-CAM and LIME. Our experiments are conducted on three publicly available multiclass tumor datasets to ensure the generalizability of the proposed approach. Among the tested architectures, the enhanced ResNet model consistently outperformed others across all datasets, achieving the highest test accuracy, ranging from 99.36% to 99.65%. The techniques such as unfreezing layers, integrating various blocks, pooling, and dropout layers enhanced feature refinement and reduced overfitting. By incorporating XAI, we improve model interpretability, ensuring that clinically relevant regions in MRI scans are highlighted. These advancements contribute to highly reliable AI-assisted diagnostics, addressing significant challenges in medical image classification.

Cone-beam computed tomography (CBCT) is a critical imaging modality in various medical fields, yet its repeated use poses radiation risks to patients. Low-dose CBCT image reconstruction aims to mitigate these risks while preserving image quality, which is crucial for clinical diagnosis and treatment. This review paper provides an in-depth analysis of the latest research progress in low-dose CBCT image reconstruction. We explore analytical reconstruction algorithms, iterative reconstruction algorithms, and deep learning approaches, each with distinct characteristics and applications. The paper comprehensively reviews the methods used for dose reduction in CBCT, the evolution of reconstruction algorithms, and their performance evaluations. We also identify challenges and limitations in current techniques, discussing potential future directions for low-dose CBCT reconstruction. Through a systematic literature search and analysis, this review offers a valuable reference for researchers and clinicians alike, aiming to advance the field of CBCT and enhance patient care through reduced radiation exposure and improved imaging outcomes.

A 48-year-old man with a coronary artery calcium (CAC) score of 0 underwent serial artificial intelligence (AI)-assisted coronary computed tomography angiography (CCTA) from 2015 to 2026, which revealed progressive noncalcified plaque. Despite the absence of baseline calcification, serial imaging demonstrated increasing plaque volume before initiation of high-intensity rosuvastatin (20 mg daily). After treatment, low-density lipoprotein fell from 143 to 62 mg/dL, and plaque-volume growth slowed from ∼18.6% to 12.6% per year. A minute calcific focus (0.8 mm³) appeared in 2025, consistent with early stabilization. This longitudinal single-patient study provides imaging-based evidence that intensive statin therapy can decelerate noncalcified plaque progression, even in the absence of baseline calcium, as measured by quantitative AI-CCTA. This is the first human case documenting statin-mediated slowing of noncalcified plaque in a CAC 0 patient with decade-long serial CCTA. AI-quantified CCTA reveals subclinical atherosclerosis invisible to CAC 0 scoring and enables plaque-directed therapy monitoring in individual patients.

Stereotactic radiosurgery (SRS) is a standard treatment for brain metastases; however, it may lead to radiation necrosis (RN). RN can be virtually indistinguishable from tumor progression (TP), which can have significant clinical implications on appropriate, time-sensitive treatment. This study investigated the effectiveness of multimodal chemical exchange saturation transfer magnetic resonance imaging (MRI), combined with T1/T2 mapping and/or conventional structural MRI, in addressing this diagnostic challenge, when analyzed through attention-guided deep learning. MRI data (3-dimensional amide proton transfer magnetization transfer ratio [Amide_MTR], relayed nuclear Overhauser effect magnetization transfer ratio [rNOE_MTR], T1 and T2 parametric maps, and postcontrast T1-weighted [T1c] and T2-weighted fluid-attenuated inversion recovery [T2-FLAIR] images) were acquired from 93 patients (230 brain metastases lesions) treated with SRS a few months prior. Lesion outcomes (TP/RN) were confirmed via histopathology and/or serial clinical imaging, including the use of perfusion imaging, over a follow-up period of at least 6 months. Data were split into training (47 patients; 184 lesions) and independent testing (46 patients; 46 lesions) sets. A 3-dimensional transformer model with 2 new attention mechanisms was developed to classify lesions using various combinations of multimodal MRI inputs. Among dual-channel models, T1c and T2-FLAIR yielded an area under the receiver operating characteristic curve (AUC) of 0.78 ± 0.01, whereas Amide_MTR and rNOE_MTR maps achieved 0.76 ± 0.01. Integrating Amide_MTR and rNOE_MTR with either T1/T2 maps or T1c/T2-FLAIR substantially improved performance (AUC = 0.84 ± 0.02 and 0.85 ± 0.02, respectively). The highest performance (AUC = 0.87 ± 0.01) was achieved using all 6 modalities. Attention-guided deep-learning analysis of chemical exchange saturation transfer MRI shows strong potential for accurately distinguishing RN from TP, underscoring the significance of multimodal MRI inputs for post-SRS lesion evaluation.

Skull base osteomyelitis (SBO) and nasopharyngeal carcinoma (NPca) are challenging to differentiate due to overlapping clinical and radiological features. This study aimed to develop and validate a multi-parametric magnetic resonance imaging (MRI)-based radiomics model with high sensitivity, enabling reliable diagnosis of SBO in adult patients presenting with equivocal imaging findings. This was a retrospective, multicenter study using institutional data. The training cohort, comprising 63 adult patients from two classes (31 SBO, 32 NPca) with MRI data, was used for model development and optimization. An external test set (n = 30; 12 SBO, 18 NPca) obtained from two different clinical centers was used for model performance analysis and generalizability. Lesion segmentation was performed using a manual volumetric technique on three axial MRI sequences (pre-contrast T1-weighted, fat-suppressed T2-weighted, and post-contrast fat-suppressed T1-weighted). Hand-crafted radiomic features (n = 2,553) were extracted using the Pyradiomics library. A multi-step process was used to select the final features, including reproducibility analysis using an interclass correlation coefficient threshold of 0.9, pairwise Spearman correlation analysis with a threshold of 0.8 to reduce redundancy, and least absolute shrinkage and selection operator regression. The final set of five features were used to train six machine learning models. The models were internally validated using 5-fold cross-validation, and performance was confirmed using the unseen external test set. Traditional statistical tests, including the Mann-Whitney U test and chi-squared test, were used to compare baseline characteristics, with a P value of <0.05 considered significant. Among the evaluated classifiers, the random forest model demonstrated the best diagnostic performance, yielding the highest area under the curve (AUC) value in the 5-fold cross-validation analysis. In the external test set, the semantic model demonstrated the best diagnostic performance, achieving an AUC of 0.940 [95% confidence interval (CI): 0.857-1.00], followed by the radiomics model (AUC: 0.903, 95% CI: 0.784-1). The apparent diffusion coefficient (ADC)-based model demonstrated limited discriminative ability (AUC: 0.694, 95% CI: 0.497-0.892). The difference between the semantic and radiomics models did not reach statistical significance (<i>P</i> = 0.644), whereas both significantly outperformed the ADC model (<i>P</i> < 0.05). Radiomics achieved high and consistent performance in distinguishing SBO from advanced NPca. Although expert-based semantic assessment performed slightly better, radiomics provides an objective alternative. ADC-based methods showed limited generalizability due to inter-center variability. Our study confirms the importance of expert radiologist assessment while demonstrating that radiomics offers a comparably effective and objective decision-support tool. Its ability to provide a consistent, quantitative output is particularly valuable for standardizing the diagnostic approach and empowering less experienced radiologists to make more confident assessments.

To evaluate whether deep learning reconstruction (DLR) can reduce the radiation dose in routine clinical computed tomography (CT) scans compared with iterative reconstruction (IR) while maintaining or improving image quality. The study assesses DLR's consistency and effectiveness across four distinct CT protocols-chest, head, chest-abdomen-pelvis (CAP) oncology, and lower limb CT angiography (CTA)-representing a wide range of clinical applications. Our study is retrospective and monocentric. It involves a total population of 13,060 patients who underwent a CT scan using either a DLR algorithm (CT-DLR) or an IR algorithm (CT-IR) in one of four different CT acquisition protocols. Image quality was evaluated qualitatively and quantitatively by measuring standardized signal-to-noise ratio and contrast-to-noise ratio values. Assessment was performed on a subsample of 200 patients (25 per protocol per group). The overall reduction in radiation dose for the CT-DLR group compared with the CT-IR group was approximately 20%. By protocol, dose reductions were 22% for chest CT, 21% for CAP oncology, 20% for lower limb CTA, and 19% for head CT. The CT-DLR group exhibited superior subjective and objective image quality to the CT-IR group. DLR algorithms allow for a significant reduction in radiation dose while achieving higher image quality compared with IR algorithms. This large-scale study confirms that DLR can significantly reduce the radiation dose in routine CT imaging while maintaining or enhancing diagnostic image quality. Its consistent performance across multiple protocols supports broader clinical adoption. Notably, the greatest dose reductions were observed in high-use protocols such as chest and CAP CT, underscoring DLR's potential to improve both individual patient care and long-term population-level radiation safety.

The study aims to develop a deep learning (DL) model based on multiparametric magnetic resonance imaging (MRI) for distinguishing between benign and malignant breast lesions. A total of 556 lesions (307 malignant, 249 benign) in 509 patients were pooled in the training/validation datasets between November 2018 and October 2019 in this retrospective study. A combined DL model based on the dynamic contrast enhanced-MRI (DCE-MRI) and apparent diffusion coefficient (ADC) map was developed to characterize breast lesions. Model performance was evaluated by using areas under the receiver operating characteristic curve (AUC) in the validation dataset and an independent testing dataset consisting of 243 lesions in 225 patients, and compared with other combined and single-parametric DL models. The predictive performance for malignancy was also compared between the DCE-ADC combined DL model and human readers. The DCE-ADC combined DL model achieved the highest diagnostic efficiency with the AUC, accuracy, sensitivity, and specificity of 0.889, 82.5%, 80.7%, and 84.1% for predicting malignant breast lesions, surpassing other combined and single-parametric DL models. The DCE-ADC combined DL model achieved good performance (accuracy:82%) and outperformed both the junior radiologists (82% vs. 70%, p = 0.073; 82% vs. 72%, p = 0.142). The diagnostic performance of two junior radiologists was improved after artificial intelligence assistance with AUCs increased to 0.798 and 0.772 from 0.689 to 0.708, respectively. The DCE-ADC combined DL model shows promising diagnostic performance and has good potential to assist junior radiologists in improving diagnostic efficacy, which can facilitate clinical decision-making. Further studies will validate these findings in prospective, larger cohorts, multicenter, multiscanner and multinational studies.