[论文解读] FUSeg: The Foot Ulcer Segmentation Challenge

Chuanbo Wang, Amirreza Mahbod+5 more|arXiv (Cornell University)|Jan 2, 2022

Diabetic Foot Ulcer Assessment and Management被引用 7

一句话总结

FUSeg 引入了一个大规模、专家标注的足部溃疡图像数据集，包含1,210张图像，用于基准化自动伤口分割。该挑战在私有测试集上使用Dice系数评估深度学习模型，为糖尿病足溃疡的伤口分割设立了新标准，其中包含1,010张训练图像和200张测试图像。

ABSTRACT

Acute and chronic wounds with varying etiologies burden the healthcare systems economically. The advanced wound care market is estimated to reach $22 billion by 2024. Wound care professionals provide proper diagnosis and treatment with heavy reliance on images and image documentation. Segmentation of wound boundaries in images is a key component of the care and diagnosis protocol since it is important to estimate the area of the wound and provide quantitative measurement for the treatment. Unfortunately, this process is very time-consuming and requires a high level of expertise. Recently automatic wound segmentation methods based on deep learning have shown promising performance but require large datasets for training and it is unclear which methods perform better. To address these issues, we propose the Foot Ulcer Segmentation challenge (FUSeg) organized in conjunction with the 2021 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI). We built a wound image dataset containing 1,210 foot ulcer images collected over 2 years from 889 patients. It is pixel-wise annotated by wound care experts and split into a training set with 1010 images and a testing set with 200 images for evaluation. Teams around the world developed automated methods to predict wound segmentations on the testing set of which annotations were kept private. The predictions were evaluated and ranked based on the average Dice coefficient. The FUSeg challenge remains an open challenge as a benchmark for wound segmentation after the conference.

研究动机与目标

• 解决糖尿病伤口护理中缺乏大规模、高质量、专家标注的足部溃疡分割数据集的问题。
• 通过自动分割减少伤口面积测量所需的时间和专业知识。
• 在标准化基准上评估和比较最先进深度学习模型的性能。
• 在MICCAI 2021之后建立公开的、持续进行的伤口分割研究挑战。
• 支持临床实践中定量、可重复的伤口评估工具的开发。

提出的方法

• 从889名患者中收集了1,210张足部溃疡图像，历时两年。
• 由伤口护理专家进行像素级标注，最终形成1,010张图像的训练集和200张图像的测试集。
• 挑战赛与MICCAI 2021会议同期举办，参赛者需提交对私有测试集的预测结果。
• 模型性能以Dice系数为主要评估指标。
• 会议结束后，数据集和挑战赛仍对公众开放，支持持续研究。
• 深度学习模型在训练集上进行训练，并在未公开真实标签的测试集上进行推理评估。

实验结果

研究问题

• RQ1 哪些深度学习模型在从临床图像中分割足部溃疡方面达到最高准确率？
• RQ2 在真实世界数据集中，模型性能如何随不同伤口外观和患者人口统计学特征而变化？
• RQ3 自动分割在多大程度上可以减少伤口面积测量所需的时间和专业知识？
• RQ4 人类专家与最先进模型在伤口分割任务中的性能差距有多大？
• RQ5 当前分割模型在大规模、多样化的真实世界数据集上具有多大程度的泛化能力？

主要发现

• FUSeg挑战赛基于1,210张专家标注图像的数据集，为足部溃疡分割设立了新基准。
• 训练集包含1,010张图像，测试集包含200张图像，标注信息在评估期间保持私密。
• 模型性能通过Dice系数进行评估，该指标是分割准确率的通用标准。
• 挑战赛在MICCAI 2021之后仍对公众开放，支持持续研究和模型比较。
• 该数据集支持临床环境中定量、可重复的伤口评估工具的开发。
• 结果凸显了深度学习在自动化和标准化糖尿病足溃疡护理中伤口面积测量方面的潜力。