基于三维和二维网络交叉教学的稀疏标注三维医学图像分割

Heng Cai, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao
{"title":"基于三维和二维网络交叉教学的稀疏标注三维医学图像分割","authors":"Heng Cai, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao","doi":"10.48550/arXiv.2307.16256","DOIUrl":null,"url":null,"abstract":"Medical image segmentation typically necessitates a large and precisely annotated dataset. However, obtaining pixel-wise annotation is a labor-intensive task that requires significant effort from domain experts, making it challenging to obtain in practical clinical scenarios. In such situations, reducing the amount of annotation required is a more practical approach. One feasible direction is sparse annotation, which involves annotating only a few slices, and has several advantages over traditional weak annotation methods such as bounding boxes and scribbles, as it preserves exact boundaries. However, learning from sparse annotation is challenging due to the scarcity of supervision signals. To address this issue, we propose a framework that can robustly learn from sparse annotation using the cross-teaching of both 3D and 2D networks. Considering the characteristic of these networks, we develop two pseudo label selection strategies, which are hard-soft confidence threshold and consistent label fusion. Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods. Moreover, our approach achieves results that are comparable to the fully-supervised upper bound result.","PeriodicalId":18289,"journal":{"name":"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention","volume":"18 1","pages":"614-624"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks\",\"authors\":\"Heng Cai, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao\",\"doi\":\"10.48550/arXiv.2307.16256\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Medical image segmentation typically necessitates a large and precisely annotated dataset. However, obtaining pixel-wise annotation is a labor-intensive task that requires significant effort from domain experts, making it challenging to obtain in practical clinical scenarios. In such situations, reducing the amount of annotation required is a more practical approach. One feasible direction is sparse annotation, which involves annotating only a few slices, and has several advantages over traditional weak annotation methods such as bounding boxes and scribbles, as it preserves exact boundaries. However, learning from sparse annotation is challenging due to the scarcity of supervision signals. To address this issue, we propose a framework that can robustly learn from sparse annotation using the cross-teaching of both 3D and 2D networks. Considering the characteristic of these networks, we develop two pseudo label selection strategies, which are hard-soft confidence threshold and consistent label fusion. Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods. Moreover, our approach achieves results that are comparable to the fully-supervised upper bound result.\",\"PeriodicalId\":18289,\"journal\":{\"name\":\"Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention\",\"volume\":\"18 1\",\"pages\":\"614-624\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-07-30\",\"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.2307.16256\",\"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.2307.16256","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

医学图像分割通常需要一个大而精确注释的数据集。然而,获得逐像素注释是一项劳动密集型任务,需要领域专家付出大量努力,这使得在实际临床场景中获得它具有挑战性。在这种情况下,减少所需注释的数量是一种更实用的方法。一个可行的方向是稀疏注释,它只涉及注释几个片,并且比传统的弱注释方法(如边界框和涂鸦)有几个优点,因为它保留了精确的边界。然而,由于监督信号的稀缺性,从稀疏注释中学习是具有挑战性的。为了解决这个问题,我们提出了一个框架,可以使用3D和2D网络的交叉教学从稀疏注释中鲁棒学习。考虑到这些网络的特点,我们提出了两种伪标签选择策略,即软硬置信度阈值和一致标签融合。我们在MMWHS数据集上的实验结果表明,我们的方法优于最先进的(SOTA)半监督分割方法。此外,我们的方法获得了与完全监督上界结果相当的结果。
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
3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks
Medical image segmentation typically necessitates a large and precisely annotated dataset. However, obtaining pixel-wise annotation is a labor-intensive task that requires significant effort from domain experts, making it challenging to obtain in practical clinical scenarios. In such situations, reducing the amount of annotation required is a more practical approach. One feasible direction is sparse annotation, which involves annotating only a few slices, and has several advantages over traditional weak annotation methods such as bounding boxes and scribbles, as it preserves exact boundaries. However, learning from sparse annotation is challenging due to the scarcity of supervision signals. To address this issue, we propose a framework that can robustly learn from sparse annotation using the cross-teaching of both 3D and 2D networks. Considering the characteristic of these networks, we develop two pseudo label selection strategies, which are hard-soft confidence threshold and consistent label fusion. Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods. Moreover, our approach achieves results that are comparable to the fully-supervised upper bound result.
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
MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-Ray Images of Multiple Body Parts Self-pruning Graph Neural Network for Predicting Inflammatory Disease Activity in Multiple Sclerosis from Brain MR Images Self-Supervised Learning for Endoscopic Video Analysis Exploring Unsupervised Cell Recognition with Prior Self-activation Maps DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
×
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