arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.02555cs.CVeess.IV
收藏

糖尿病足溃疡分割模型具有通用性吗?CNN和Transformer架构的跨数据集基准测试

Do Diabetic Foot Ulcer Segmentation Models Generalize? A Cross-Dataset Benchmark of CNN and Transformer Architectures

King Saud University(沙特国王大学)

Abderrahmane Benfatah

AI总结:

研究糖尿病足溃疡分割模型跨数据集的通用性,用U-Net、DeepLabV3+和SegFormer-B2在特定协议下测试,发现模型域内表现好但跨数据集性能下降,且SegFormer-B2通用性最佳。

摘要:

用于糖尿病足溃疡(DFU)分割的深度学习模型通常报告高精度,但几乎总是在同一数据集上训练和测试,其在来自不同临床来源的数据上的行为很大程度上未得到衡量。我们在相同的、经过泄漏筛选的协议下对三种代表性分割架构进行基准测试……

英文摘要:

Deep learning models for diabetic foot ulcer (DFU) segmentation routinely report high accuracy, but they are almost always trained and tested on the same dataset, leaving their behaviour on data from a different clinical source largely unmeasured. We benchmark three representative segmentation architectures -- U-Net and DeepLabV3+ (convolutional) and SegFormer-B2 (Transformer) -- under an identical, leakage-screened protocol: training on the combined FUSeg/AZH wound data and evaluating, without fine-tuning, on two independent external datasets (DFUC2022 and Medetec). All models achieve strong in-domain performance (Dice 0.80--0.83) but degrade substantially across datasets. The degradation is, however, architecture-dependent: SegFormer-B2 generalizes best on both external sets (DFUC2022 Dice 0.557, Medetec Dice 0.786), outperforming both convolutional models, while the more complex DeepLabV3+ generalizes worse than the simpler U-Net. Per-image failure analysis on 2,160 images across both external test sets confirms that SegFormer-B2 produces the fewest catastrophic failures on DFUC2022 (31.1%), compared with U-Net (38.5%) and DeepLabV3+ (43.0%). The consistent ranking across two independent external sources, confirmed by Wilcoxon signed-rank tests (p < 0.001 on both datasets), indicates that architecture family, not model complexity, drives cross-hospital generalization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑