用于标记高效组织病理学图像分割的人机交互组织原型学习

W. Pan, Jiangpeng Yan, Hanbo Chen, Jiawei Yang, Zhe Xu, Xiu Li, Jianhua Yao
{"title":"用于标记高效组织病理学图像分割的人机交互组织原型学习","authors":"W. Pan, Jiangpeng Yan, Hanbo Chen, Jiawei Yang, Zhe Xu, Xiu Li, Jianhua Yao","doi":"10.48550/arXiv.2211.14491","DOIUrl":null,"url":null,"abstract":"Recently, deep neural networks have greatly advanced histopathology image segmentation but usually require abundant annotated data. However, due to the gigapixel scale of whole slide images and pathologists' heavy daily workload, obtaining pixel-level labels for supervised learning in clinical practice is often infeasible. Alternatively, weakly-supervised segmentation methods have been explored with less laborious image-level labels, but their performance is unsatisfactory due to the lack of dense supervision. Inspired by the recent success of self-supervised learning methods, we present a label-efficient tissue prototype dictionary building pipeline and propose to use the obtained prototypes to guide histopathology image segmentation. Particularly, taking advantage of self-supervised contrastive learning, an encoder is trained to project the unlabeled histopathology image patches into a discriminative embedding space where these patches are clustered to identify the tissue prototypes by efficient pathologists' visual examination. Then, the encoder is used to map the images into the embedding space and generate pixel-level pseudo tissue masks by querying the tissue prototype dictionary. Finally, the pseudo masks are used to train a segmentation network with dense supervision for better performance. Experiments on two public datasets demonstrate that our human-machine interactive tissue prototype learning method can achieve comparable segmentation performance as the fully-supervised baselines with less annotation burden and outperform other weakly-supervised methods. Codes will be available upon publication.","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"89 1","pages":"679-691"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Human-machine Interactive Tissue Prototype Learning for Label-efficient Histopathology Image Segmentation\",\"authors\":\"W. Pan, Jiangpeng Yan, Hanbo Chen, Jiawei Yang, Zhe Xu, Xiu Li, Jianhua Yao\",\"doi\":\"10.48550/arXiv.2211.14491\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, deep neural networks have greatly advanced histopathology image segmentation but usually require abundant annotated data. However, due to the gigapixel scale of whole slide images and pathologists' heavy daily workload, obtaining pixel-level labels for supervised learning in clinical practice is often infeasible. Alternatively, weakly-supervised segmentation methods have been explored with less laborious image-level labels, but their performance is unsatisfactory due to the lack of dense supervision. Inspired by the recent success of self-supervised learning methods, we present a label-efficient tissue prototype dictionary building pipeline and propose to use the obtained prototypes to guide histopathology image segmentation. Particularly, taking advantage of self-supervised contrastive learning, an encoder is trained to project the unlabeled histopathology image patches into a discriminative embedding space where these patches are clustered to identify the tissue prototypes by efficient pathologists' visual examination. Then, the encoder is used to map the images into the embedding space and generate pixel-level pseudo tissue masks by querying the tissue prototype dictionary. Finally, the pseudo masks are used to train a segmentation network with dense supervision for better performance. Experiments on two public datasets demonstrate that our human-machine interactive tissue prototype learning method can achieve comparable segmentation performance as the fully-supervised baselines with less annotation burden and outperform other weakly-supervised methods. Codes will be available upon publication.\",\"PeriodicalId\":73379,\"journal\":{\"name\":\"Information processing in medical imaging : proceedings of the ... conference\",\"volume\":\"89 1\",\"pages\":\"679-691\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Information processing in medical imaging : proceedings of the ... conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2211.14491\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Information processing in medical imaging : proceedings of the ... conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2211.14491","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

近年来,深度神经网络在组织病理图像分割方面取得了很大进展,但通常需要大量的注释数据。然而,由于整个幻灯片图像的十亿像素规模和病理学家的日常工作繁重,在临床实践中获得用于监督学习的像素级标签往往是不可行的。另一种方法是使用不那么费力的图像级标签探索弱监督分割方法,但由于缺乏密集的监督,它们的性能不令人满意。受近年来成功的自监督学习方法的启发,我们提出了一个标签高效的组织原型词典构建管道,并提出使用获得的原型来指导组织病理图像分割。特别是,利用自监督对比学习的优势,训练编码器将未标记的组织病理学图像块投影到判别嵌入空间中,这些块被聚类,从而通过高效的病理学家视觉检查识别组织原型。然后,利用编码器将图像映射到嵌入空间中,通过查询组织原型字典生成像素级伪组织掩模;最后,利用伪掩码训练具有密集监督的分割网络,以获得更好的分割性能。在两个公共数据集上的实验表明,我们的人机交互组织原型学习方法可以获得与全监督基线相当的分割性能,并且注释负担更少,优于其他弱监督方法。代码将在出版后提供。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Human-machine Interactive Tissue Prototype Learning for Label-efficient Histopathology Image Segmentation
Recently, deep neural networks have greatly advanced histopathology image segmentation but usually require abundant annotated data. However, due to the gigapixel scale of whole slide images and pathologists' heavy daily workload, obtaining pixel-level labels for supervised learning in clinical practice is often infeasible. Alternatively, weakly-supervised segmentation methods have been explored with less laborious image-level labels, but their performance is unsatisfactory due to the lack of dense supervision. Inspired by the recent success of self-supervised learning methods, we present a label-efficient tissue prototype dictionary building pipeline and propose to use the obtained prototypes to guide histopathology image segmentation. Particularly, taking advantage of self-supervised contrastive learning, an encoder is trained to project the unlabeled histopathology image patches into a discriminative embedding space where these patches are clustered to identify the tissue prototypes by efficient pathologists' visual examination. Then, the encoder is used to map the images into the embedding space and generate pixel-level pseudo tissue masks by querying the tissue prototype dictionary. Finally, the pseudo masks are used to train a segmentation network with dense supervision for better performance. Experiments on two public datasets demonstrate that our human-machine interactive tissue prototype learning method can achieve comparable segmentation performance as the fully-supervised baselines with less annotation burden and outperform other weakly-supervised methods. Codes will be available upon publication.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Vicinal Feature Statistics Augmentation for Federated 3D Medical Volume Segmentation Better Generalization of White Matter Tract Segmentation to Arbitrary Datasets with Scaled Residual Bootstrap Unsupervised Adaptation of Polyp Segmentation Models via Coarse-to-Fine Self-Supervision Weakly Semi-supervised Detection in Lung Ultrasound Videos Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-Aware Contrastive Distillation.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1