{"title":"具有同群感知注意力和逆向互信息最小化功能的多同群框架,用于整张幻灯片图像分类","authors":"Sharon Peled, Yosef E. Maruvka, Moti Freiman","doi":"arxiv-2409.11119","DOIUrl":null,"url":null,"abstract":"Whole Slide Images (WSIs) are critical for various clinical applications,\nincluding histopathological analysis. However, current deep learning approaches\nin this field predominantly focus on individual tumor types, limiting model\ngeneralization and scalability. This relatively narrow focus ultimately stems\nfrom the inherent heterogeneity in histopathology and the diverse morphological\nand molecular characteristics of different tumors. To this end, we propose a\nnovel approach for multi-cohort WSI analysis, designed to leverage the\ndiversity of different tumor types. We introduce a Cohort-Aware Attention\nmodule, enabling the capture of both shared and tumor-specific pathological\npatterns, enhancing cross-tumor generalization. Furthermore, we construct an\nadversarial cohort regularization mechanism to minimize cohort-specific biases\nthrough mutual information minimization. Additionally, we develop a\nhierarchical sample balancing strategy to mitigate cohort imbalances and\npromote unbiased learning. Together, these form a cohesive framework for\nunbiased multi-cohort WSI analysis. Extensive experiments on a uniquely\nconstructed multi-cancer dataset demonstrate significant improvements in\ngeneralization, providing a scalable solution for WSI classification across\ndiverse cancer types. Our code for the experiments is publicly available at\n<link>.","PeriodicalId":501289,"journal":{"name":"arXiv - EE - Image and Video Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-Cohort Framework with Cohort-Aware Attention and Adversarial Mutual-Information Minimization for Whole Slide Image Classification\",\"authors\":\"Sharon Peled, Yosef E. Maruvka, Moti Freiman\",\"doi\":\"arxiv-2409.11119\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Whole Slide Images (WSIs) are critical for various clinical applications,\\nincluding histopathological analysis. However, current deep learning approaches\\nin this field predominantly focus on individual tumor types, limiting model\\ngeneralization and scalability. This relatively narrow focus ultimately stems\\nfrom the inherent heterogeneity in histopathology and the diverse morphological\\nand molecular characteristics of different tumors. To this end, we propose a\\nnovel approach for multi-cohort WSI analysis, designed to leverage the\\ndiversity of different tumor types. We introduce a Cohort-Aware Attention\\nmodule, enabling the capture of both shared and tumor-specific pathological\\npatterns, enhancing cross-tumor generalization. Furthermore, we construct an\\nadversarial cohort regularization mechanism to minimize cohort-specific biases\\nthrough mutual information minimization. Additionally, we develop a\\nhierarchical sample balancing strategy to mitigate cohort imbalances and\\npromote unbiased learning. Together, these form a cohesive framework for\\nunbiased multi-cohort WSI analysis. Extensive experiments on a uniquely\\nconstructed multi-cancer dataset demonstrate significant improvements in\\ngeneralization, providing a scalable solution for WSI classification across\\ndiverse cancer types. Our code for the experiments is publicly available at\\n<link>.\",\"PeriodicalId\":501289,\"journal\":{\"name\":\"arXiv - EE - Image and Video Processing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - EE - Image and Video Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11119\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - EE - Image and Video Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11119","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
全切片图像(WSI)对于包括组织病理学分析在内的各种临床应用至关重要。然而,目前该领域的深度学习方法主要集中在单个肿瘤类型上,限制了模型的通用性和可扩展性。这种相对狭隘的关注点最终源于组织病理学固有的异质性以及不同肿瘤形态和分子特征的多样性。为此,我们提出了一种新的多队列 WSI 分析方法,旨在利用不同肿瘤类型的多样性。我们引入了群组感知注意力模块(Cohort-Aware Attentionmodule),能够捕捉共有的和肿瘤特有的病理模式,从而增强跨肿瘤的概括能力。此外,我们还构建了一种对抗群组正则化机制,通过互信息最小化来最小化群组特异性偏差。此外,我们还开发了一种分层样本平衡策略,以减轻队列不平衡,促进无偏学习。这些措施共同构成了无偏多队列 WSI 分析的内聚框架。在一个独特构建的多癌症数据集上进行的广泛实验表明,该方法的泛化能力有了显著提高,为不同癌症类型的 WSI 分类提供了一个可扩展的解决方案。我们的实验代码可在以下网址公开获取。
Multi-Cohort Framework with Cohort-Aware Attention and Adversarial Mutual-Information Minimization for Whole Slide Image Classification
Whole Slide Images (WSIs) are critical for various clinical applications,
including histopathological analysis. However, current deep learning approaches
in this field predominantly focus on individual tumor types, limiting model
generalization and scalability. This relatively narrow focus ultimately stems
from the inherent heterogeneity in histopathology and the diverse morphological
and molecular characteristics of different tumors. To this end, we propose a
novel approach for multi-cohort WSI analysis, designed to leverage the
diversity of different tumor types. We introduce a Cohort-Aware Attention
module, enabling the capture of both shared and tumor-specific pathological
patterns, enhancing cross-tumor generalization. Furthermore, we construct an
adversarial cohort regularization mechanism to minimize cohort-specific biases
through mutual information minimization. Additionally, we develop a
hierarchical sample balancing strategy to mitigate cohort imbalances and
promote unbiased learning. Together, these form a cohesive framework for
unbiased multi-cohort WSI analysis. Extensive experiments on a uniquely
constructed multi-cancer dataset demonstrate significant improvements in
generalization, providing a scalable solution for WSI classification across
diverse cancer types. Our code for the experiments is publicly available at
.