arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.09574cs.LGcs.AIcs.CV
收藏

LymphoML：一种基于可解释人工智能的方法识别与淋巴瘤亚型相关的形态学特征

LymphoML: An interpretable artificial intelligence-based method identifies morphologic features that correlate with lymphoma subtype

Stanford University（斯坦福大学）；Stanford University School of Medicine（斯坦福大学医学院）；Harvard Medical School（哈佛医学院）；La Liga Nacional Contra el Cáncer de Guatemala (INCAN)（危地马拉国家抗癌联盟（INCAN））；Fred Hutchinson Cancer Research Center（弗雷德·哈钦森癌症研究中心）；Dana-Farber Cancer Institute（达纳-法伯癌症研究所）
Vivek Shankar, Xiaoli Yang, Vrishab Krishna, Brent Tan, Oscar Silva, Rebecca Rojansky, Andrew Ng, Fabiola Valvert, Edward Briercheck, David Weinstock, Yasodha N… 展开作者

Vivek Shankar, Xiaoli Yang, Vrishab Krishna, Brent Tan, Oscar Silva, Rebecca Rojansky, Andrew Ng, Fabiola Valvert, Edward Briercheck, David Weinstock, Yasodha Natkunam, Sebastian Fernandez-Pol, Pranav Rajpurkar

备注：
To be published in Proceedings of the 3rd Machine Learning for Health symposium, Proceedings of Machine Learning Research (PMLR)
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出可解释机器学习方法LymphoML，通过处理H&E染色组织、分割细胞并训练梯度提升模型，在670例数据上优于黑盒深度学习，并首次证明结合6种免疫染色的模型准确率接近46种染色组合。

摘要：

使用苏木精和伊红（H&E）染色的组织对淋巴瘤亚型进行准确分类，因这些癌症可能表现出广泛的形态学特征而变得复杂。我们提出了LymphoML——一种可解释的机器学习方法，能够识别与淋巴瘤亚型相关的形态学特征。该方法应用一系列步骤来处理H&E染色的组织微阵列芯，分割细胞核和细胞，计算涵盖形态、纹理和结构的特征，并训练梯度提升模型以做出诊断预测。LymphoML的可解释模型在有限体积的H&E染色组织上开发，实现了与病理学家使用全切片图像不相上下的诊断准确率，并在来自危地马拉的670例病例（涵盖8种淋巴瘤亚型）的数据集上优于黑盒深度学习。使用SHapley Additive exPlanation（SHAP）分析，我们评估了每个特征对模型预测的影响，发现细胞核形状特征对DLBCL（F1分数：78.7%）和经典型霍奇金淋巴瘤（F1分数：74.5%）最具区分力。最后，我们首次证明，将H&E染色组织的特征与6种免疫染色的标准化组合的特征相结合的模型，其诊断准确率（85.3%）与46种染色组合（86.1%）相似。

英文摘要：

The accurate classification of lymphoma subtypes using hematoxylin and eosin (H&E)-stained tissue is complicated by the wide range of morphological features these cancers can exhibit. We present LymphoML - an interpretable machine learning method that identifies morphologic features that correlate with lymphoma subtypes. Our method applies steps to process H&E-stained tissue microarray cores, segment nuclei and cells, compute features encompassing morphology, texture, and architecture, and train gradient-boosted models to make diagnostic predictions. LymphoML's interpretable models, developed on a limited volume of H&E-stained tissue, achieve non-inferior diagnostic accuracy to pathologists using whole-slide images and outperform black box deep-learning on a dataset of 670 cases from Guatemala spanning 8 lymphoma subtypes. Using SHapley Additive exPlanation (SHAP) analysis, we assess the impact of each feature on model prediction and find that nuclear shape features are most discriminative for DLBCL (F1-score: 78.7%) and classical Hodgkin lymphoma (F1-score: 74.5%). Finally, we provide the first demonstration that a model combining features from H&E-stained tissue with features from a standardized panel of 6 immunostains results in a similar diagnostic accuracy (85.3%) to a 46-stain panel (86.1%).

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。

↑