研究人员正在开发先进的医学图像分割技术，以应对域偏移和提示依赖等挑战。一种方法侧重于SAM2等模型的无提示、参数高效微调，在降低计算成本的同时显著提高了准确性。另一项研究对医学分割的持续学习方法进行了基准测试，评估了遗忘之外的性能，并突出了基于重放方法的优势。此外，一个名为MedFlowSeg的新框架利用流匹配技术在医学图像分割中进行高效灵活的生成建模，其性能优于现有的基于扩散的方法。 AI
影响 医学图像分割技术的进步有望提供更准确、更高效的诊断工具，从而可能改善患者的治疗效果。
排序理由 多篇arXiv论文提出了用于医学图像分割的新颖方法和基准研究。
AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →
arXiv:2605.05979v1 Announce Type: new Abstract: Segment Anything Model 2 (SAM2) demonstrated impressive zero-shot capabilities on natural images but faces challenges in biomedical segmentation due to significant domain shifts and prompt dependency. To address these limitations, w…
arXiv:2604.19675v2 Announce Type: replace Abstract: Flow matching has recently emerged as a principled framework for learning continuous-time transport maps, enabling efficient ODE-based sampling without relying on stochastic diffusion processes. While generative modeling has sho…
arXiv:2605.06160v1 Announce Type: new Abstract: Continual learning (CL) is essential for deploying medical image segmentation models in clinical environments where imaging domains, anatomical targets, and diagnostic tasks evolve over time. However, continual segmentation still fa…
Continual learning (CL) is essential for deploying medical image segmentation models in clinical environments where imaging domains, anatomical targets, and diagnostic tasks evolve over time. However, continual segmentation still faces three main challenges. First, the scenarios …
Segment Anything Model 2 (SAM2) demonstrated impressive zero-shot capabilities on natural images but faces challenges in biomedical segmentation due to significant domain shifts and prompt dependency. To address these limitations, we propose a prompt-free, parameter-efficient fin…
arXiv:2509.10784v3 Announce Type: replace-cross Abstract: Medical vision foundation models remain limited in downstream tasks, particularly volumetric medical image segmentation. While fine-tuning on labeled target-domain data improves performance, existing approaches typically r…
arXiv:2601.19690v2 Announce Type: replace Abstract: Vision Mamba models have been extensively researched in various fields, which address the limitations of previous models by effectively managing long-range dependencies with a linear-time overhead. Several prospective studies ha…
arXiv:2605.01563v1 Announce Type: new Abstract: We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our …