针对病理图像域偏移问题，提出自适应卷积网络提升癌症分割精度。
Domain and Content Adaptive Convolutions for Cross-Domain Adenocarcinoma Segmentation
- 设计可适应领域与内容的卷积模块，增强模型泛化能力。
- 在跨器官与跨扫描仪任务上分别达到0.8020和0.8527的Dice分数。
- 适合需要处理真实世界病理图像差异的研究者与临床应用开发者。
近年来，深度学习推动了组织病理学计算机辅助诊断的发展，广泛应用于自动图像分析。尽管这些模型性能可媲美医学专家，但其表现常受限于分布外数据。跨器官与跨扫描仪腺癌分割挑战（COSAS）旨在解决因形态差异和扫描仪引入的域偏移导致的跨域腺癌分割问题。本文提出一种基于U-Net的分割框架，以应对该挑战。所提方法在最终挑战测试集上，跨器官赛道获得0.8020的分割分数，跨扫描仪赛道获得0.8527的分割分数，为最优提交结果。
原文摘要 · Abstract (English)
Recent advances in computer-aided diagnosis for histopathology have been largely driven by the use of deep learning models for automated image analysis. While these networks can perform on par with medical experts, their performance can be impeded by out-of-distribution data. The Cross-Organ and Cross-Scanner Adenocarcinoma Segmentation (COSAS) challenge aimed to address the task of cross-domain adenocarcinoma segmentation in the presence of morphological and scanner-induced domain shifts. In this paper, we present a U-Net-based segmentation framework designed to tackle this challenge. Our approach achieved segmentation scores of 0.8020 for the cross-organ track and 0.8527 for the cross-scanner track on the final challenge test sets, ranking it the best-performing submission.
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。