一种用于病理切片结直肠癌诊断的可解释机器学习系统
An interpretable machine learning system for colorectal cancer diagnosis from pathology slides
AI总结：
本文提出一种基于弱标签和混合监督的可解释深度学习系统，用于从全切片图像诊断结直肠癌，通过智能采样减少六倍训练样本，并在内部及TCGA、PAIP等外部数据集上验证了高准确率和灵敏度。
摘要：
考虑到病理实践正在经历的深刻变革，我们旨在开发一种可扩展的人工智能（AI）系统，用于从全切片图像（WSI）中诊断结直肠癌。为此，我们提出了一种深度学习（DL）系统，该系统能够从弱标签中学习；提出了一种采样策略，在不影响性能的情况下将训练样本数量减少六倍；提出了一种利用少量完全标注样本子集的方法；并提出了一个具有可解释预测、主动学习功能和并行化能力的原型。注意到文献中存在的一些问题，本研究使用了规模最大的结直肠癌WSI样本数据集之一进行，包含约10,500张WSI。其中900张为测试样本。此外，所提方法的鲁棒性通过两个额外的外部数据集（TCGA和PAIP）以及一个直接从所提原型采集的样本数据集进行了评估。我们提出的方法针对基于图块的切片，根据异型增生的严重程度预测类别，并利用该信息对整个切片进行分类。该方法采用可解释的混合监督方案进行训练，以利用病理学家通过空间标注引入的领域知识。混合监督方案支持一种智能采样策略，在多个不同场景下均得到了有效评估，且未影响性能。在内部数据集上，该方法显示出93.44%的准确率，阳性样本（低级别和高级别异型增生）与非肿瘤样本之间的灵敏度为0.996。在外部测试样本中，TCGA是最具挑战性的数据集，其总体准确率为84.91%，灵敏度为0.996。
英文摘要：
Considering the profound transformation affecting pathology practice, we aimed to develop a scalable artificial intelligence (AI) system to diagnose colorectal cancer from whole-slide images (WSI). For this, we propose a deep learning (DL) system that learns from weak labels, a sampling strategy that reduces the number of training samples by a factor of six without compromising performance, an approach to leverage a small subset of fully annotated samples, and a prototype with explainable predictions, active learning features and parallelisation. Noting some problems in the literature, this study is conducted with one of the largest WSI colorectal samples dataset with approximately 10,500 WSIs. Of these samples, 900 are testing samples. Furthermore, the robustness of the proposed method is assessed with two additional external datasets (TCGA and PAIP) and a dataset of samples collected directly from the proposed prototype. Our proposed method predicts, for the patch-based tiles, a class based on the severity of the dysplasia and uses that information to classify the whole slide. It is trained with an interpretable mixed-supervision scheme to leverage the domain knowledge introduced by pathologists through spatial annotations. The mixed-supervision scheme allowed for an intelligent sampling strategy effectively evaluated in several different scenarios without compromising the performance. On the internal dataset, the method shows an accuracy of 93.44% and a sensitivity between positive (low-grade and high-grade dysplasia) and non-neoplastic samples of 0.996. On the external test samples varied with TCGA being the most challenging dataset with an overall accuracy of 84.91% and a sensitivity of 0.996.
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。
