Domain adaptation (DA) techniques have the potential in machine learning to alleviate distribution differences between training and test sets by leveraging information from source domains. In image classification, most advances in DA have been made using natural images rather than medical data, which are harder to work with. Moreover, even for natural images, the use of mainstream datasets can lead to performance bias. {With the aim of better understanding the benefits of DA for both natural and medical images, this study performs 557 simulation studies using seven widely-used DA techniques for image classification in five natural and eight medical datasets that cover various scenarios, such as out-of-distribution, dynamic data streams, and limited training samples.} Our experiments yield detailed results and insightful observations highlighting the performance and medical applicability of these techniques. Notably, our results have shown the outstanding performance of the Deep Subdomain Adaptation Network (DSAN) algorithm. This algorithm achieved feasible classification accuracy (91.2\%) in the COVID-19 dataset using Resnet50 and showed an important accuracy improvement in the dynamic data stream DA scenario (+6.7\%) compared to the baseline. Our results also demonstrate that DSAN exhibits remarkable level of explainability when evaluated on COVID-19 and skin cancer datasets. These results contribute to the understanding of DA techniques and offer valuable insight into the effective adaptation of models to medical data.

In this work, we propose a novel framework to enhance the efficiency and accuracy of neural operators through self-composition, offering both theoretical guarantees and practical benefits. Inspired by iterative methods in solving numerical partial differential equations (PDEs), we design a specific neural operator by repeatedly applying a single neural operator block, we progressively deepen the model without explicitly adding new blocks, improving the model's capacity. To train these models efficiently, we introduce an adaptive train-and-unroll approach, where the depth of the neural operator is gradually increased during training. This approach reveals an accuracy scaling law with model depth and offers significant computational savings through our adaptive training strategy. Our architecture achieves state-of-the-art (SOTA) performance on standard benchmarks. We further demonstrate its efficacy on a challenging high-frequency ultrasound computed tomography (USCT) problem, where a multigrid-inspired backbone enables superior performance in resolving complex wave phenomena. The proposed framework provides a computationally tractable, accurate, and scalable solution for large-scale data-driven scientific machine learning applications.

Breast cancer is one of the leading causes of cancer-related mortality in women, and early detection is essential for improving outcomes. Magnetic resonance imaging (MRI) is a highly sensitive tool for breast cancer detection, particularly in women at high risk or with dense breast tissue, where mammography is less effective. The ODELIA consortium organized a multi-center challenge to foster AI-based solutions for breast cancer diagnosis and classification. The dataset included 511 studies from six European centers, acquired on scanners from multiple vendors at both 1.5 T and 3 T. Each study was labeled for the left and right breast as no lesion, benign lesion, or malignant lesion. We developed a SwinUNETR-based deep learning framework that incorporates breast region masking, extensive data augmentation, and ensemble learning to improve robustness and generalizability. Our method achieved second place on the challenge leaderboard, highlighting its potential to support clinical breast MRI interpretation. We publicly share our codebase at https://github.com/smriti-joshi/bcnaim-odelia-challenge.git.

Accurate gross tumor volume segmentation on multi-modal medical data is critical for radiotherapy planning in nasopharyngeal carcinoma and glioblastoma. Recent advances in deep neural networks have brought promising results in medical image segmentation, leading to an increasing demand for labeled data. Since labeling medical images is time-consuming and labor-intensive, active learning has emerged as a solution to reduce annotation costs by selecting the most informative samples to label and adapting high-performance models with as few labeled samples as possible. Previous active domain adaptation (ADA) methods seek to minimize sample redundancy by selecting samples that are farthest from the source domain. However, such one-off selection can easily cause negative transfer, and access to source medical data is often limited. Moreover, the query strategy for multi-modal medical data remains unexplored. In this work, we propose an active and sequential domain adaptation framework for dynamic multi-modal sample selection in ADA. We derive a query strategy to prioritize labeling and training on the most valuable samples based on their informativeness and representativeness. Empirical validation on diverse gross tumor volume segmentation tasks demonstrates that our method achieves favorable segmentation performance, significantly outperforming state-of-the-art ADA methods. Code is available at the git repository: \href{https://github.com/Hiyoochan/mmActS}{mmActS}.

Metastasis remains the major challenge in the clinical management of head and neck squamous cell carcinoma (HNSCC). Reliable pre-treatment prediction of metastatic risk is crucial for optimizing treatment strategies and prognosis. This study develops a deep learning-based multimodal framework to predict metastasis risk in HNSCC patients by integrating computed tomography (CT) images, radiomics, and clinical data. 1497 HNSCC patients were included. Tumor and organ masks were derived from pretreatment CT images. A 3D Swin Transformer extracted deep features from tumor regions. Meanwhile, 1562 radiomics features were obtained using PyRadiomics, followed by correlation filtering and random forest selection, leaving 36 features. Clinical variables including age, sex, smoking, and alcohol status were encoded and fused with imaging-derived features. Multimodal features were fed into a fully connected network to predict metastasis risk. Performance was evaluated using five-fold cross-validation with area under the curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). The proposed fusion model outperformed single-modality models. The 3D deep learning module alone achieved an AUC of 0.715, and when combined with radiomics and clinical features, predictive performance improved (AUC = 0.803, ACC = 0.752, SEN = 0.730, SPE = 0.758). Stratified analysis showed generalizability across tumor subtypes. Ablation studies indicated complementary information from different modalities. Evaluation showed the 3D Swin Transformer provided more robust representation learning than conventional networks. This multimodal fusion model demonstrated high accuracy and robustness in predicting metastasis risk in HNSCC, offering a comprehensive representation of tumor biology. The interpretable model has potential as a clinical decision-support tool for personalized treatment planning.

Recently, Transformer has been widely used in medical imaging analysis for its competitive potential when given enough data. However, Transformer conducts attention on a global scale by utilizing self-attention mechanisms across all input patches, thereby requiring substantial computational power and memory, especially when dealing with large 3D images such as MRI images. In this study, we proposed Residual Global Scoring Network (ResGSNet), a novel architecture combining ResNet with Global Scoring Module (GSM), achieving high computational efficiency while incorporating both local and global features. First, our proposed GSM utilized local attention to conduct information exchange within local brain regions, subsequently assigning global scores to each of these local regions, demonstrating the capability to encapsulate local and global information with reduced computational burden and superior performance compared to existing methods. Second, we utilized Grad-CAM＋＋ and the Attention Map to interpret model predictions, uncovering brain regions related to Alzheimer's Disease (AD) Detection. Third, our extensive experiments on the ADNI dataset show that our proposed ResGSNet achieved satisfactory performance with 95.1% accuracy in predicting AD, a 1.3% increase compared to state-of-the-art methods, and 93.4% accuracy for Mild Cognitive Impairment (MCI). Our model for detecting MCI can potentially serve as a screening tool for identifying individuals at high risk of developing AD and allow for early intervention. Furthermore, the Grad-CAM＋＋ and Attention Map not only identified brain regions commonly associated with AD and MCI but also revealed previously undiscovered regions, including putamen, cerebellum cortex, and caudate nucleus, holding promise for further research into the etiology of AD.

Positron Emission Tomography-Computed Tomography (PET-CT) evolution is critical for liver lesion diagnosis. However, data scarcity, privacy concerns, and cross-institutional imaging heterogeneity impede accurate deep learning model deployment. We propose a Federated Transfer Learning (FTL) framework that integrates federated learning's privacy-preserving collaboration with transfer learning's pre-trained model adaptation, enhancing liver lesion segmentation in PET-CT imaging. By leveraging a Feature Co-learning Block (FCB) and privacy-enhancing technologies (DP, HE), our approach ensures robust segmentation without sharing sensitive patient data. (1) A privacy-preserving FTL framework combining federated learning and adaptive transfer learning; (2) A multi-modal FCB for improved PET-CT feature integration; (3) Extensive evaluation across diverse institutions with privacy-enhancing technologies like Differential Privacy (DP) and Homomorphic Encryption (HE). Experiments on simulated multi-institutional PET-CT datasets demonstrate superior performance compared to baselines, with robust privacy guarantees. The FTL framework reduces data requirements and enhances generalizability, advancing liver lesion diagnostics.

Peripheral artery disease (PAD) is a progressive vascular condition affecting >237 million individuals worldwide. Accurate diagnosis and patient-specific treatment planning are critical but are often hindered by limited access to advanced imaging tools and real-time analytical support. This study presents DECODE, an open-source, cloud-based platform that integrates artificial intelligence, interactive 3D visualization, and computational modeling to improve the noninvasive management of PAD. The DECODE platform was designed as a modular backend (Django) and frontend (React) architecture that combines deep learning-based segmentation, real-time volume rendering, and finite element simulations. Peripheral artery and intima-media thickness segmentation were implemented via convolutional neural networks, including extended U-Net and nnU-Net architectures. Centreline extraction algorithms provide quantitative vascular geometry analysis. Balloon angioplasty simulations were conducted via nonlinear finite element models calibrated with experimental data. Usability was evaluated via the System Usability Scale (SUS), and user acceptance was assessed via the Technology Acceptance Model (TAM). Peripheral artery segmentation achieved an average Dice coefficient of 0.91 and a 95th percentile Hausdorff distance 1.0 mm across 22 computed tomography dataset. Intima-media segmentation evaluated on 300 intravascular optical coherence tomography images demonstrated Dice scores 0.992 for the lumen boundaries and 0.980 for the intima boundaries, with corresponding Hausdorff distances of 0.056 mm and 0.101 mm, respectively. Finite element simulations successfully reproduced the mechanical interactions between balloon and artery models in both idealized and subject-specific geometries, identifying pressure and stress distributions relevant to treatment outcomes. The platform received an average SUS score 87.5, indicating excellent usability, and an overall TAM score 4.21 out of 5, reflecting high user acceptance. DECODE provides an automated, cloud-integrated solution for PAD diagnosis and intervention planning, combining deep learning, computational modeling, and high-fidelity visualization. The platform enables precise vascular analysis, real-time procedural simulation, and interactive clinical decision support. By streamlining image processing, enhancing segmentation accuracy, and enabling in-silico trials, DECODE offers a scalable infrastructure for personalized vascular care and sets a new benchmark in digital health technologies for PAD.

IntroductionBreast cancer is one of the most common cancers globally. Its incidence in Africa has increased sharply, surpassing that in high-income countries. Mortality remains high due to late-stage diagnosis, when treatment is less effetive. We propose the first open, longitudinal breast imaging dataset from Africa comprising point-of-care ultrasound scans, mammograms, biopsy pathology, and clinical profiles to support early detection using machine learning. Methods and AnalysisWe will engage women through community outreach and train them in self-examination. Those with suspected lesions, particularly with a family history of breast cancer, will be invited to participate. A total of 100 women will undergo baseline assessment at medical centers, including clinical exams, blood tests, and mammograms. Follow-up point-of-care ultrasound scans and clinical data will be collected at 3 and 6 months, with final assessments at 9 months including mammograms. Ethics and DisseminationThe study has been approved by the Institutional Review Boards at ECUREI and the MAI Lab. Findings will be disseminated through peer-reviewed journals and scientific conferences.

Traumatic brain injury (TBI) is one of the most prevalent health conditions, with severity assessment serving as an initial step for management, prognosis, and targeted therapy. Existing studies on automated outcome prediction using machine learning (ML) often overlook the importance of TBI features in decision-making and the challenges posed by limited and imbalanced training data. Furthermore, many attempts have focused on quantitatively evaluating ML algorithms without explaining the decisions, making the outcomes difficult to interpret and apply for less-experienced doctors. This study presents a novel supportive tool, named E-TBI (explainable outcome prediction after TBI), designed with a user-friendly web-based interface to assist doctors in outcome prediction after TBI using machine learning. The tool is developed with the capability to visualize rules applied in the decision-making process. At the tool's core is a feature selection and classification module that receives multimodal data from TBI patients (demographic data, clinical data, laboratory test results, and CT findings). It then infers one of four TBI severity levels. This research investigates various machine learning models and feature selection techniques, ultimately identifying the optimal combination of gradient boosting machine and random forest for the task, which we refer to as GBMRF. This method enabled us to identify a small set of essential features, reducing patient testing costs by 35%, while achieving the highest accuracy rates of 88.82% and 89.78% on two datasets (a public TBI dataset and our self-collected dataset, TBI_MH103). Classification modules are available at https://github.com/auverngo110/Traumatic_Brain_Injury_103 .