基于解剖感知对比蒸馏的自举半监督医学图像分割

Chenyu You, Weichen Dai, L. Staib, J. Duncan
{"title":"基于解剖感知对比蒸馏的自举半监督医学图像分割","authors":"Chenyu You, Weichen Dai, L. Staib, J. Duncan","doi":"10.48550/arXiv.2206.02307","DOIUrl":null,"url":null,"abstract":"Contrastive learning has shown great promise over annotation scarcity problems in the context of medical image segmentation. Existing approaches typically assume a balanced class distribution for both labeled and unlabeled medical images. However, medical image data in reality is commonly imbalanced (i.e., multi-class label imbalance), which naturally yields blurry contours and usually incorrectly labels rare objects. Moreover, it remains unclear whether all negative samples are equally negative. In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation. Specifically, we first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs. We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data. Second, we raise a more important question: Can we really handle imbalanced samples to yield better performance? Hence, the key innovation in ACTION is to learn global semantic relationship across the entire dataset and local anatomical features among the neighbouring pixels with minimal additional memory footprint. During the training, we introduce anatomical contrast by actively sampling a sparse set of hard negative pixels, which can generate smoother segmentation boundaries and more accurate predictions. Extensive experiments across two benchmark datasets and different unlabeled settings show that ACTION significantly outperforms the current state-of-the-art semi-supervised methods.","PeriodicalId":73379,"journal":{"name":"Information processing in medical imaging : proceedings of the ... conference","volume":"13939 1","pages":"641-653"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"32","resultStr":"{\"title\":\"Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation\",\"authors\":\"Chenyu You, Weichen Dai, L. Staib, J. Duncan\",\"doi\":\"10.48550/arXiv.2206.02307\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Contrastive learning has shown great promise over annotation scarcity problems in the context of medical image segmentation. Existing approaches typically assume a balanced class distribution for both labeled and unlabeled medical images. However, medical image data in reality is commonly imbalanced (i.e., multi-class label imbalance), which naturally yields blurry contours and usually incorrectly labels rare objects. Moreover, it remains unclear whether all negative samples are equally negative. In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation. Specifically, we first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs. We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data. Second, we raise a more important question: Can we really handle imbalanced samples to yield better performance? Hence, the key innovation in ACTION is to learn global semantic relationship across the entire dataset and local anatomical features among the neighbouring pixels with minimal additional memory footprint. During the training, we introduce anatomical contrast by actively sampling a sparse set of hard negative pixels, which can generate smoother segmentation boundaries and more accurate predictions. Extensive experiments across two benchmark datasets and different unlabeled settings show that ACTION significantly outperforms the current state-of-the-art semi-supervised methods.\",\"PeriodicalId\":73379,\"journal\":{\"name\":\"Information processing in medical imaging : proceedings of the ... conference\",\"volume\":\"13939 1\",\"pages\":\"641-653\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-06-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"32\",\"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.2206.02307\",\"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.2206.02307","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 32

摘要

在医学图像分割的背景下,对比学习在解决注释稀缺问题方面表现出了巨大的前景。现有的方法通常假设标记的和未标记的医学图像都具有平衡的类别分布。然而,现实中的医学图像数据通常是不平衡的(即多类标签不平衡),这自然会产生模糊的轮廓,并且通常会错误地标记稀有对象。此外,目前尚不清楚是否所有阴性样本均为阴性。在这项工作中,我们提出了ACTION,一种解剖学感知ConTrastive dStillation框架,用于半监督医学图像分割。具体来说,我们首先开发了一种迭代对比提取算法,通过对否定进行软标记,而不是在正负对之间进行二元监督。与阳性集相比,我们还从随机选择的阴性集中捕获了更多语义相似的特征,以增强采样数据的多样性。其次,我们提出了一个更重要的问题:我们真的能处理不平衡的样本以获得更好的性能吗?因此,ACTION的关键创新是以最小的额外内存占用来学习整个数据集的全局语义关系和相邻像素之间的局部解剖特征。在训练过程中,我们通过主动采样一组稀疏的硬负像素来引入解剖对比度,这可以生成更平滑的分割边界和更准确的预测。在两个基准数据集和不同的未标记设置上进行的大量实验表明,ACTION显著优于当前最先进的半监督方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation
Contrastive learning has shown great promise over annotation scarcity problems in the context of medical image segmentation. Existing approaches typically assume a balanced class distribution for both labeled and unlabeled medical images. However, medical image data in reality is commonly imbalanced (i.e., multi-class label imbalance), which naturally yields blurry contours and usually incorrectly labels rare objects. Moreover, it remains unclear whether all negative samples are equally negative. In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation. Specifically, we first develop an iterative contrastive distillation algorithm by softly labeling the negatives rather than binary supervision between positive and negative pairs. We also capture more semantically similar features from the randomly chosen negative set compared to the positives to enforce the diversity of the sampled data. Second, we raise a more important question: Can we really handle imbalanced samples to yield better performance? Hence, the key innovation in ACTION is to learn global semantic relationship across the entire dataset and local anatomical features among the neighbouring pixels with minimal additional memory footprint. During the training, we introduce anatomical contrast by actively sampling a sparse set of hard negative pixels, which can generate smoother segmentation boundaries and more accurate predictions. Extensive experiments across two benchmark datasets and different unlabeled settings show that ACTION significantly outperforms the current state-of-the-art semi-supervised methods.
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
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信