Comprehensive Analysis and Computing of Real-World Medical Images

Second MICCAI Challenge, CARE 2025, Held in Conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings
Erscheinungsjahr 2026
ISBN: 978-3-032-16270-0
Verlag: Springer

Buch, Englisch, Band 16257, 258 Seiten, Format (B × H): 155 mm x 235 mm, Gewicht: 423 g

Reihe: Lecture Notes in Computer Science

This book constitutes the proceedings of the Second MICCAI Challenge, CARE 2025, held in Conjunction with MICCAI 2025, in Daejeon, South Korea, on September 23, 2025.

The 23 full papers in this book were carefully reviewed and selected from 51 submissions.

These tracks aim to advance real-world medical image computing by bridging the gap between AI model development and practical clinical applications.

Zielgruppe

Research

Autoren/Hrsg.

Zhuang, Xiahai

Ding, Wangbin

Liu, Yuanye

Ma, Yingliang

Zhao, Jichao

Wang, Bomin

Fachgebiete

• Medizin | Veterinärmedizin Medizin | Public Health | Pharmazie | Zahnmedizin Medizin, Gesundheitswesen Medizintechnik, Biomedizintechnik, Medizinische Werkstoffe
• Technische Wissenschaften Sonstige Technologien | Angewandte Technik Medizintechnik, Biomedizintechnik

Inhaltsverzeichnis

.- A Unified 3D Cardiac Structure Segmentation Framework for Heterogeneous Medical Data.
.- Uncertainty-Guided Curriculum Learning for Automated Liver Fibrosis Staging on Heterogeneous MRI.
.- Uncertainty-Guided Hard–Soft Priors for Myocardial Scar and Edema Segmentation on Multi-Sequence CMR Images.
.- MA2: Unifying Modality-Agnostic Segmentation and Modality-Aware Staging for Real-World Liver Fibrosis Analysis.
.- Transfer Learning for Multimodal Whole Heart Segmentation Supported by Intensity Transformations.
.- CoSSeg-TTA: Contrast-Aware Semi-Supervised Segmentation with Domain Generalization and Test-Time Adaptation.
.- CardioSeqM: A Scalable and Context-Aware Model for Unified Heart Segmentation from Volumetric Cardiac Data.
.- A Latent-Guided Hybrid Architecture for Liver Segmentation in Contrast-Enhanced MRI.
.- IE-UNet: Implicit Neural Representation-Driven Whole Heart Segmentation.
,- Multi-Modal MRI Fusion for Liver Fibrosis Staging and Semi-Supervised Pipeline for Liver Segmentation.
.- Two-Stage Approach for Myocardial Scar and Edema Segmentation Using Synthetic Multi-Sequence MRI and Auxiliary Scar Prediction.
.- Semi-supervised Liver Segmentation and Patch-based Fibrosis Staging with Registration-aided Multi-parametric MRI.
.- A Two-stage Myocardial Pathology Segmentation Method Based on Multi-sequence CMR images.
.- Decoupled Teacher-Student Framework for Few-shot Liver Segmentation with Boundary-Aware Learning.
.- Label-Efficient Cross-Modality Generalization for Liver Segmentation in Multi-Phase MRI.
.- UniCarSeg: A Unified Framework for Multi-Task Cardiac Image Segmentation.
.- Improved mmFormer for Liver Fibrosis Staging via Missing-Modality Compensation.
.- SSL-MedSAM2: A Semi-supervised Medical Image Segmentation Framework Powered by Few-shot Learning of SAM2.
.- Early Fusion-Based Multimodal Cardiac MRI Segmentation with Domain-Aware Augmentation.
.- Dual-Task Multi-Modal 2.5D Swin Transformer for Liver Fibrosis Staging.
.- EHU-Mamba2: Enhanced U-Mamba for Multi-Center Cardiac MR Segmentation with Dynamic Alignment and Adaptive Upsampling.
.- Multi-modal Liver Segmentation and Fibrosis Staging Using Real-world MRI Images.
.- Multi-b ranch Attention Network for Liver Fibrosis Staging in Multi-Phase MRI.