为医学图像分割设计提供数据驱动的评估框架，让模型选择更透明可靠。
MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models
- 基于数据特性构建知识卡片，明确分割任务需求
- 不同数据集需匹配不同模型设计与评价指标
- 实验证明框架能提升模型适配性与风险可控性
医学图像分割常聚焦于寻找更强的网络结构，却忽视了一个根本问题：数据集对模型有何要求？在医学影像中，这一需求由前景占据率、形态特征、边界模糊性、拓扑敏感性、标注质量、采集差异和工作点决定。本文提出医学分割数据集知识卡（MS-DKC）框架，通过图像/采集、形态、监督、上下文依赖和部署风险等描述符，显式记录数据证据，并映射到故障模式、设计先验和风险对齐标准，使分割设计比架构对比更具可追溯性。在DRIVE、ISIC2018和ACDC三个代表不同场景的数据集上评估：DRIVE中细长血管要求细节保留，DKC-TNet-v2达Dice 0.8044、IoU 0.6730（35103参数），SA-UNetv2-DKC-AmbRef达Dice 0.8141、IoU 0.6865、敏感度0.8265、特异度0.9804、AUC 0.9853；ISIC2018中病变紧凑但外观多变，经验证约束的评分函数选择后，MS-DKC-AttNextTopo-VCSF-NoAug达Dice 0.8872、IoU 0.8214、精确度0.9173、边界F1 0.4878、ASSD 4.13，增补无效；ACDC为四类心脏结构，推荐使用四分类softmax、类别平衡的Dice/CE损失及类别表面评估。结果支持数据条件化设计：不同数据集需不同先验、工作点和证据支撑才能判断模型适用性。
原文摘要 · Abstract (English)
Medical image segmentation is often framed as a search for stronger architectures, but this can obscure a more fundamental question: what does the dataset require from the model? In medical imaging, this requirement is shaped by foreground occupancy, morphology, boundary ambiguity, topology sensitivity, annotation quality, acquisition variation, and operating point. This paper introduces the Medical Segmentation Dataset Knowledge Card (MS-DKC), a framework for making these factors explicit. MS-DKC records dataset evidence through image/acquisition, morphology, supervision, context-dependence, and deployment-risk descriptors. These descriptors are mapped to failure modes, design priors, and risk-aligned criteria, making segmentation design more traceable than architecture-first comparison. We evaluate MS-DKC on DRIVE, ISIC2018, and ACDC, representing distinct regimes. DRIVE contains sparse, thin, branching vessels, favoring detail-preserving models, sensitivity-aware optimization, threshold analysis, and topology-aware metrics. DKC-TNet-v2 achieved Dice 0.8044 and IoU 0.6730 with 35103 parameters, while SA-UNetv2-DKC-AmbRef reached Dice 0.8141, IoU 0.6865, sensitivity 0.8265, specificity 0.9804, and AUC 0.9853. ISIC2018 involves compact but appearance-variable lesions; validation-constrained score-function selection on Att-Next-Topo/ATTNext produced MS-DKC-AttNextTopo-VCSF-NoAug with Dice 0.8872, IoU 0.8214, precision 0.9173, Boundary F1 0.4878, and ASSD 4.13, while plausible additions failed to improve the risk-aligned profile. ACDC provides a multi-class cardiac case, where MS-DKC recommends four-class softmax segmentation, class-balanced Dice/CE supervision, and class-wise surface evaluation. Overall, the results support dataset-conditioned design: different datasets require different priors, operating points, and evidence before a model can be judged appropriate.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。