Multimodal Learning and Fusion Across Scales for Clinical Decision Support
Description
This book constitutes the refereed proceedings of the 15th International Workshop, ML-CDS 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 27, 2025.
The 13 full papers presented in this book were carefully selected after review. Submissions are organized in the following topical sections: Multimodal analysis and fusion; Multimodal models for decision support.
More details
Content
.- Multimodal analysis and fusion.
.- Multi-View and Multimodal Radiological Grading Using Spinal MRIs.
.- MRI-Supervised Ultra-Low Dose CT for 3D Liver Fat Fraction Mapping.
.- Integrating Pathology and CT Imaging for Personalized Recurrence Risk Prediction in Renal Cancer.
.- Expert-Driven Contextual Fusion of Multisequence MRI and Heterogeneous Clinical Data for Pancreatic Cancer Prognostic Prediction.
.- MOSAIK: Microclip-Guided TEMS-VQA and Mosaic Integrated Scene Fusion for Surgical VLMs.
.- Imaging Biomarkers for Neurodegenerative Diseases from Detailed Segmentation of Medial Temporal Lobe Subregions on in vivo Brain MRI Using Upsampling Strategy Guided by High-resolution ex vivo MRI.
.- Multimodal models for decision support.
.- X2CT-CLIP: Enable Multi-Abnormality Detection in Computed Tomography from Chest Radiography via Tri-Modal Contrastive Learning.
.- No Modality Left Behind: Dynamic Model Generation for Incomplete Medical Data.
.- From Pixels to Graphs: SAM-KG for Tumor Segmentation and Knowledge Graphs.
.- Multimodal Hypergraph Learning with Self-Attention for Early Alzheimer's Diagnosis and Risk Factor Identification.
.- Leveraging generic foundation models for multimodal surgical data analysis.
.- Modality-agnostic input channels enable segmentation of brain lesions in multi-modal MRI with sequences unavailable during training.
.- Self-Supervised Contrastive Learning for Cardiac MR Sequence Classification.