M&M:用多视图和多实例学习稀疏检测器处理乳房x光检查中的假阳性

Yen Nhi Truong Vu, Dan Guo, Ahmed Taha, Jason Su, Thomas P. Matthews
{"title":"M&M:用多视图和多实例学习稀疏检测器处理乳房x光检查中的假阳性","authors":"Yen Nhi Truong Vu, Dan Guo, Ahmed Taha, Jason Su, Thomas P. Matthews","doi":"10.48550/arXiv.2308.06420","DOIUrl":null,"url":null,"abstract":"Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike natural images, a malignant mammogram typically contains only one malignant finding; (2) mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment; (3) most mammograms are negative and do not contain any findings. In this work, we tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; (3) incorporating multi-instance learning (MIL) to train with unannotated images and perform breast-level classification. The resulting model, M&M, is a Multi-view and Multi-instance learning system that can both localize malignant findings and provide breast-level predictions. We validate M&M's detection and classification performance using five mammography datasets. In addition, we demonstrate the effectiveness of each proposed component through comprehensive ablation studies.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"238 1","pages":"778-788"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector\",\"authors\":\"Yen Nhi Truong Vu, Dan Guo, Ahmed Taha, Jason Su, Thomas P. Matthews\",\"doi\":\"10.48550/arXiv.2308.06420\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike natural images, a malignant mammogram typically contains only one malignant finding; (2) mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment; (3) most mammograms are negative and do not contain any findings. In this work, we tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; (3) incorporating multi-instance learning (MIL) to train with unannotated images and perform breast-level classification. The resulting model, M&M, is a Multi-view and Multi-instance learning system that can both localize malignant findings and provide breast-level predictions. We validate M&M's detection and classification performance using five mammography datasets. In addition, we demonstrate the effectiveness of each proposed component through comprehensive ablation studies.\",\"PeriodicalId\":18289,\"journal\":{\"name\":\"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention\",\"volume\":\"238 1\",\"pages\":\"778-788\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-08-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2308.06420\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2308.06420","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

基于深度学习的目标检测方法有望改善乳房x光筛查,但高假阳性率会阻碍其在临床实践中的有效性。为了减少假阳性,我们确定了三个挑战:(1)与自然图像不同,恶性乳房x光片通常只包含一个恶性发现;(2)乳房x光检查包含每个乳房的两个视图,应该考虑这两个视图以做出正确的评估;大多数乳房x光片都是阴性的,没有任何发现。在这项工作中,我们通过以下方式解决了上述三个挑战:(1)利用稀疏R-CNN,并表明稀疏检测器比密集检测器更适合乳房x光检查;(2)包含多视角交叉关注模块,综合不同视角信息;(3)结合多实例学习(multi-instance learning, MIL)对未标注的图像进行训练,并进行乳房级分类。由此产生的模型M&M是一个多视图和多实例学习系统,既可以定位恶性发现,又可以提供乳房水平预测。我们使用五个乳房x线摄影数据集验证了M&M的检测和分类性能。此外,我们通过全面的烧蚀研究证明了每个提出的组件的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector
Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice. To reduce false positives, we identify three challenges: (1) unlike natural images, a malignant mammogram typically contains only one malignant finding; (2) mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment; (3) most mammograms are negative and do not contain any findings. In this work, we tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; (3) incorporating multi-instance learning (MIL) to train with unannotated images and perform breast-level classification. The resulting model, M&M, is a Multi-view and Multi-instance learning system that can both localize malignant findings and provide breast-level predictions. We validate M&M's detection and classification performance using five mammography datasets. In addition, we demonstrate the effectiveness of each proposed component through comprehensive ablation studies.
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