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 2409.14154cs.CVcs.AI
收藏

MSSDA:用于糖尿病足神经病变识别的多子源域自适应

MSSDA: Multi-Sub-Source Adaptation for Diabetic Foot Neuropathy Recognition

South China University of Technology(华南理工大学);City University of Hong Kong(香港城市大学);The First Affiliated Hospital of Jinan University(暨南大学附属第一医院)

Yan Zhong, Zhixin Yan, Yi Xie, Shibin Wu, Huaidong Zhang, Lin Shu, Peiru Zhou

AI总结:

针对糖尿病足神经病变识别中数据域差异问题,提出基于卷积特征统计的多子源域自适应方法,通过拆分数据集、选择子源域并对其分布以最小化域差距,有效避免了负迁移并提升了识别效率。

摘要:

糖尿病足神经病变(DFN)是导致糖尿病足溃疡的关键因素,后者是糖尿病(DM)最常见且最严重的并发症之一,且伴随高截肢和死亡风险。尽管其意义重大,但现有数据集并非直接来源于足底数据,且缺乏连续的、长期的足部特定信息。为了推进 DFN 研究,我们收集了一个包含连续足底压力数据的新颖数据集,以识别糖尿病足神经病变。该数据集包含来自 94 名患有 DFN 的 DM 患者和 41 名未患 DFN 的 DM 患者的数据。此外,传统方法按个体划分数据集,由于缺乏中间域数据,这可能导致在某些特征空间中出现显著的域差异。在本文中,我们提出了一种有效的域自适应方法来解决此问题。我们基于卷积特征统计数据拆分数据集,并选择合适的子源域以提高效率并避免负迁移。然后,我们在特定特征空间中对齐每个源域和目标域对的分布,以最小化域差距。综合结果验证了我们的方法在用于 DFN 识别的新提出数据集和现有数据集上的有效性。

英文摘要:

Diabetic foot neuropathy (DFN) is a critical factor leading to diabetic foot ulcers, which is one of the most common and severe complications of diabetes mellitus (DM) and is associated with high risks of amputation and mortality. Despite its significance, existing datasets do not directly derive from plantar data and lack continuous, long-term foot-specific information. To advance DFN research, we have collected a novel dataset comprising continuous plantar pressure data to recognize diabetic foot neuropathy. This dataset includes data from 94 DM patients with DFN and 41 DM patients without DFN. Moreover, traditional methods divide datasets by individuals, potentially leading to significant domain discrepancies in some feature spaces due to the absence of mid-domain data. In this paper, we propose an effective domain adaptation method to address this proplem. We split the dataset based on convolutional feature statistics and select appropriate sub-source domains to enhance efficiency and avoid negative transfer. We then align the distributions of each source and target domain pair in specific feature spaces to minimize the domain gap. Comprehensive results validate the effectiveness of our method on both the newly proposed dataset for DFN recognition and an existing dataset.

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。

↑