Deep generative models have demonstrated remarkable success in medical image synthesis. However, ensuring conditioning faithfulness and high-quality synthetic images for direct or counterfactual generation remains a challenge. In this work, we introduce a cycle training framework to fine-tune diffusion models for improved conditioning adherence and enhanced synthetic image realism. Our approach, Cycle Diffusion Model (CDM), enforces consistency between generated and original images by incorporating cycle constraints, enabling more reliable direct and counterfactual generation. Experiments on a combined 3D brain MRI dataset (from ABCD, HCP aging & young adults, ADNI, and PPMI) show that our method improves conditioning accuracy and enhances image quality as measured by FID and SSIM. The results suggest that the cycle strategy used in CDM can be an effective method for refining diffusion-based medical image generation, with applications in data augmentation, counterfactual, and disease progression modeling.

Prostate cancer (PCa) is the most frequently diagnosed malignancy in men and the eighth leading cause of cancer death worldwide. Multiparametric MRI (mpMRI) has become central to the diagnostic pathway for men at intermediate risk, improving de-tection of clinically significant PCa (csPCa) while reducing unnecessary biopsies and over-diagnosis. However, mpMRI remains limited by false positives, false negatives, and moderate to substantial interobserver agreement. Time-dependent diffusion (TDD) MRI, a novel sequence that enables tissue microstructure characterization, has shown encouraging preclinical performance in distinguishing clinically significant from insignificant PCa. Combining TDD-derived metrics with machine learning may provide robust, zone-specific risk prediction with less dependence on reader training and improved accuracy compared to current standard-of-care. This study protocol out-lines the rationale and describes the prospective evaluation of a home-developed AI-enhanced TDD-MRI software (PROSTDAI) in routine diagnostic care, assessing its added value against PI-RADS v2.1 and validating results against MRI-guided prostate biopsy.

Vision foundation models like the Segment Anything Model (SAM), pretrained on large-scale natural image datasets, often struggle in medical image segmentation due to a lack of domain-specific adaptation. In clinical practice, fine-tuning such models efficiently for medical downstream tasks with minimal resource demands, while maintaining strong performance, is challenging. To address these issues, we propose BALR-SAM, a boundary-aware low-rank adaptation framework that enhances SAM for medical imaging. It combines three tailored components: (1) a Complementary Detail Enhancement Network (CDEN) using depthwise separable convolutions and multi-scale fusion to capture boundary-sensitive features essential for accurate segmentation; (2) low-rank adapters integrated into SAM's Vision Transformer blocks to optimize feature representation and attention for medical contexts, while simultaneously significantly reducing the parameter space; and (3) a low-rank tensor attention mechanism in the mask decoder, cutting memory usage by 75% and boosting inference speed. Experiments on standard medical segmentation datasets show that BALR-SAM, without requiring prompts, outperforms several state-of-the-art (SOTA) methods, including fully fine-tuned MedSAM, while updating just 1.8% (11.7M) of its parameters.

The early and accurate classification of brain tumors is crucial for guiding effective treatment strategies and improving patient outcomes. This study presents BrainFusion, a significant advancement in brain tumor analysis using magnetic resonance imaging (MRI) by combining fine-tuned convolutional neural networks (CNNs) for tumor classification--including VGG16, ResNet50, and Xception--with YOLOv8 for precise tumor localization with bounding boxes. Leveraging the Brain Tumor MRI Dataset, our experiments reveal that the fine-tuned VGG16 model achieves test accuracy of 99.86%, substantially exceeding previous benchmarks. Beyond setting a new accuracy standard, the integration of bounding-box localization and explainable AI techniques further enhances both the clinical interpretability and trustworthiness of the system's outputs. Overall, this approach underscores the transformative potential of deep learning in delivering faster, more reliable diagnoses, ultimately contributing to improved patient care and survival rates.

Despite the promise of foundation models in medical AI, current systems remain limited - they are modality-specific and lack transparent reasoning processes, hindering clinical adoption. To address this gap, we present EVLF-FM, a multimodal vision-language foundation model (VLM) designed to unify broad diagnostic capability with fine-grain explainability. The development and testing of EVLF-FM encompassed over 1.3 million total samples from 23 global datasets across eleven imaging modalities related to six clinical specialties: dermatology, hepatology, ophthalmology, pathology, pulmonology, and radiology. External validation employed 8,884 independent test samples from 10 additional datasets across five imaging modalities. Technically, EVLF-FM is developed to assist with multiple disease diagnosis and visual question answering with pixel-level visual grounding and reasoning capabilities. In internal validation for disease diagnostics, EVLF-FM achieved the highest average accuracy (0.858) and F1-score (0.797), outperforming leading generalist and specialist models. In medical visual grounding, EVLF-FM also achieved stellar performance across nine modalities with average mIOU of 0.743 and [email protected] of 0.837. External validations further confirmed strong zero-shot and few-shot performance, with competitive F1-scores despite a smaller model size. Through a hybrid training strategy combining supervised and visual reinforcement fine-tuning, EVLF-FM not only achieves state-of-the-art accuracy but also exhibits step-by-step reasoning, aligning outputs with visual evidence. EVLF-FM is an early multi-disease VLM model with explainability and reasoning capabilities that could advance adoption of and trust in foundation models for real-world clinical deployment.

Objective: Gadolinium-based contrast agents (GBCAs) are commonly employed with T1w MRI to enhance lesion visualization but are restricted in patients at risk of nephrogenic systemic fibrosis and variations in GBCA administration can introduce imaging inconsistencies. This study develops an efficient 3D deep-learning framework to generate T1-contrast enhanced images (T1C) from pre-contrast multiparametric MRI. Approach: We propose the 3D latent rectified flow (T1C-RFlow) model for generating high-quality T1C images. First, T1w and T2-FLAIR images are input into a pretrained autoencoder to acquire an efficient latent space representation. A rectified flow diffusion model is then trained in this latent space representation. The T1C-RFlow model was trained on a curated dataset comprised of the BraTS 2024 glioma (GLI; 1480 patients), meningioma (MEN; 1141 patients), and metastases (MET; 1475 patients) datasets. Selected patients were split into train (N=2860), validation (N=612), and test (N=614) sets. Results: Both qualitative and quantitative results demonstrate that the T1C-RFlow model outperforms benchmark 3D models (pix2pix, DDPM, Diffusion Transformers (DiT-3D)) trained in the same latent space. T1C-RFlow achieved the following metrics - GLI: NMSE 0.044 +/- 0.047, SSIM 0.935 +/- 0.025; MEN: NMSE 0.046 +/- 0.029, SSIM 0.937 +/- 0.021; MET: NMSE 0.098 +/- 0.088, SSIM 0.905 +/- 0.082. T1C-RFlow had the best tumor reconstruction performance and significantly faster denoising times (6.9 s/volume, 200 steps) than conventional DDPM models in both latent space (37.7s, 1000 steps) and patch-based in image space (4.3 hr/volume). Significance: Our proposed method generates synthetic T1C images that closely resemble ground truth T1C in much less time than previous diffusion models. Further development may permit a practical method for contrast-agent-free MRI for brain tumors.

Neoadjuvant chemotherapy (NAC) is a common therapy option before the main surgery for breast cancer. Response to NAC is monitored using follow-up dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Accurate prediction of NAC response helps with treatment planning. Here, we adopt maximum intensity projection images from DCE-MRI to generate post-treatment images (i.e., 3 or 12 weeks after NAC) from pre-treatment images leveraging the emerging diffusion model. We introduce prompt tuning to account for the known clinical factors affecting response to NAC. Our model performed better than other generative models in image quality metrics. Our model was better at generating images that reflected changes in tumor size according to pCR compared to other models. Ablation study confirmed the design choices of our method. Our study has the potential to help with precision medicine.

Sepsis, a severe complication of infection, often leads to acute kidney injury (AKI), which significantly increases the risk of death. Despite its clinical importance, early prediction of AKI remains challenging. Current tools rely on blood and urine tests, which are costly, variable, and not always available in time for intervention. Pneumonia is the most common cause of sepsis, accounting for over one-third of cases. In such patients, pulmonary inflammation and perilesional tissue alterations may serve as surrogate markers of systemic disease progression. However, these imaging features are rarely used in clinical decision-making. To overcome this limitation, our study aims to extract informative imaging features from pneumonia-associated sepsis cases using deep learning, with the goal of predicting the development of AKI. This dual-center retrospective study included pneumonia-associated sepsis patients (Jan 2020-Jul 2024). Chest CT images, clinical records, and laboratory data at admission were collected. We propose MCANet (Multimodal Cross-Attention Network), a two-stage deep learning framework designed to predict the occurrence of pneumonia-associated sepsis-related acute kidney injury (pSA-AKI). In the first stage, region-specific features were extracted from the lungs, epicardial adipose tissue, and T4-level subcutaneous adipose tissue using ResNet-18, which was chosen for its lightweight architecture and efficiency in processing multi-regional 2D CT slices with low computational cost. In the second stage, the extracted features were fused via a Multiscale Feature Attention Network (MSFAN) employing cross-attention mechanisms to enhance interactions among anatomical regions, followed by classification using ResNet-101, selected for its deeper architecture and strong ability to model global semantic representations and complex patterns.Model performance was evaluated using AUC, accuracy, precision, recall, and F1-score. Grad-CAM and PyRadiomics were employed for visual interpretation and radiomic analysis, respectively. A total of 399 patients with pneumonia-associated sepsis were included in this study. The modality ablation experiments demonstrated that the model integrating features from the lungs, T4-level subcutaneous adipose tissue, and epicardial adipose tissue achieved the best performance, with an accuracy of 0.981 and an AUC of 0.99 on the external test set from an independent center. For the prediction of AKI onset time, the LightGBM model incorporating imaging and clinical features achieved the highest accuracy of 0.8409 on the external test set. Furthermore, the multimodal model combining deep features, radiomics features, and clinical data further improved predictive performance, reaching an accuracy of 0.9773 and an AUC of 0.961 on the external test set. This study developed MCAnet, a multimodal deep learning framework that integrates imaging features from the lungs, epicardial adipose tissue, and T4-level subcutaneous adipose tissue. The framework significantly improved the accuracy of AKI occurrence and temporal prediction in pneumonia-associated sepsis patients, highlighting the synergistic role of adipose tissue and lung characteristics. Furthermore, explainability analysis revealed potential decision-making mechanisms underlying the temporal progression of pSA-AKI, offering new insights for clinical management.

To explore whether machine learning models of bone tumors can improve the diagnostic performance of imaging physicians. Retrospective radiographic and clinical data collection from bone tumor patients to construct multiple machine learning models. Area under the curve (AUC) values were used as the primary assessment metric to select auxiliary models for this study. Seven readers were selected based on pre-experiment results from the Multireader multicase (MRMC) study. Two reading experiments were conducted using an independent test set to validate the value of interpretable models as clinician aids. We used the Obuchowski-Rockette method to compare differences in physician categorization. The extreme gradient boosting (XGBoost) model based on clinical information and radiomics features performed best for classification with an AUC value of 0.905 (95% CI: 0.841, 0.949). The interpretable algorithm suggested that gray level co-occurrence matrix (GLCM) features provided the most crucial predictive information for the classification model. The AUC was significantly higher for senior physicians (with 7-11 years of experience) than for junior physicians (with 2-5 years of experience) in reading musculoskeletal radiographs (0.929-0.956 vs. 0.812-0.906). The mean AUC value of the independent reading by the seven physicians was 0.904, and the mean AUC value of the model-assisted reading result was improved by 0.037 (95% CI: -0.074, -0.001%), which was statistically significant (P=0.047). The machine learning model based on the radiomics features and clinical information of knee X-ray images can effectively assist clinicians in completing the preoperative diagnosis of benign and malignant bone tumors.

To evaluate a commercial deep-learning based auto-contouring software specifically trained for high-dose-rate gynecological brachytherapy. We collected CT images from 30 patients treated with gynecological brachytherapy (19.5-28 Gy in 3-4 fractions) at our institution from January 2018 to December 2022. Clinical and artificial intelligence (AI) generated contours for bladder, bowel, rectum, and sigmoid were obtained. Five patients were randomly selected from the test set and manually re-contoured by 4 radiation oncologists. Contouring was repeated 2 weeks later using AI contours as the starting point ("AI-assisted" approach). Comparisons amongst clinical, AI, AI-assisted, and manual retrospective contours were made using various metrics, including Dice similarity coefficient (DSC) and unsigned D2cc difference. Between clinical and AI contours, DSC was 0.92, 0.79, 0.62, 0.66, for bladder, rectum, sigmoid, and bowel, respectively. Rectum and sigmoid had the lowest median unsigned D2cc difference of 0.20 and 0.21 Gy/fraction respectively between clinical and AI contours, while bowel had the largest median difference of 0.38 Gy/fraction. Agreement between fully automated AI and clinical contours was generally not different compared to agreement between AI-assisted and clinical contours. AI-assisted interobserver agreement was better than manual interobserver agreement for all organs and metrics. The median time to contour all organs for manual and AI-assisted approaches was 14.8 and 6.9 minutes/patient (p < 0.001), respectively. The agreement between AI or AI-assisted contours against the clinical contours was similar to manual interobserver agreement. Implementation of the AI-assisted contouring approach could enhance clinical workflow by decreasing both contouring time and interobserver variability.