Semi-supervised medical image segmentation via hard positives oriented contrastive learning

计算机科学 人工智能 嵌入 分割 特征向量 模式识别(心理学) 编码器 特征(语言学) 边距(机器学习) 图像分割 特征学习 判别式 机器学习 语言学 操作系统 哲学
作者
Cheng Tang,Xinyi Zeng,Luping Zhou,Qizheng Zhou,Peng Wang,Xi Wu,Hongping Ren,Jiliu Zhou,Yan Wang
出处
期刊:Pattern Recognition [Elsevier BV]
卷期号:146: 110020-110020 被引量:23
标识
DOI:10.1016/j.patcog.2023.110020
摘要

Semi-supervised learning (SSL) has been a popular technique to resolve the annotation scarcity problem in pattern recognition and medical image segmentation, which usually focuses on two critical issues: 1) learning a well-structured categorizable embedding space, and 2) establishing a robust mapping from the embedding space to the pixel space. In this paper, to resolve the first issue, we propose a hard positives oriented contrastive (HPC) learning strategy to pre-train an encoder-decoder-based segmentation model. Different from vanilla contrastive learning tending to focus only on hard negatives, our HPC learning strategy additionally concentrates on hard positives (i.e., samples with the same category but dissimilar feature representations to the anchor), which are considered to play an even more crucial role in delivering discriminative knowledge for semi-supervised medical image segmentation. Specifically, the HPC is constructed from two levels, including an unsupervised image-level HPC (IHPC) and a supervised pixel-level HPC (PHPC), empowering the embedding space learned by the encoder with both local and global senses. Particularly, the PHPC learning strategy is implemented in a region-based manner, saving memory usage while delivering more multi-granularity information. In response to the second issue, we insert several feature swap (FS) modules into the pre-trained decoder. These FS modules aim to perturb the mapping from the intermediate embedding space towards the pixel space, trying to encourage more robust segmentation predictions. Experiments on two public clinical datasets demonstrate that our proposed framework surpasses the state-of-the-art methods by a large margin. Source codes are available at https://github.com/PerPerZXY/BHPC.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
无名发布了新的文献求助10
1秒前
NexusExplorer应助HOPE采纳,获得10
3秒前
4秒前
东晓发布了新的文献求助10
5秒前
Boren完成签到,获得积分10
5秒前
hanleiharry1发布了新的文献求助10
5秒前
天峰完成签到,获得积分10
5秒前
李健应助风趣的爆米花采纳,获得10
6秒前
FashionBoy应助无名采纳,获得10
7秒前
超级的丸子完成签到,获得积分10
8秒前
9秒前
隐形曼青应助murry123采纳,获得10
10秒前
ANG完成签到 ,获得积分10
10秒前
11秒前
李嘉欣发布了新的文献求助10
12秒前
12秒前
lascqy完成签到 ,获得积分10
13秒前
wbh发布了新的文献求助10
14秒前
JamesPei应助咚咚咚采纳,获得30
15秒前
小熊熊完成签到,获得积分10
16秒前
Tessa完成签到,获得积分10
16秒前
王心耳完成签到,获得积分10
17秒前
扁舟灬完成签到,获得积分10
17秒前
周婷发布了新的文献求助10
17秒前
17秒前
puff关注了科研通微信公众号
18秒前
18秒前
20秒前
稳重岩完成签到 ,获得积分10
22秒前
loski发布了新的文献求助10
23秒前
步一发布了新的文献求助10
23秒前
24秒前
24秒前
hanleiharry1发布了新的文献求助10
24秒前
24秒前
murry123发布了新的文献求助10
25秒前
痴情的寒云完成签到 ,获得积分10
25秒前
CAOHOU应助张wx_100采纳,获得10
26秒前
27秒前
ppg123应助NightGlow采纳,获得10
28秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989390
求助须知:如何正确求助?哪些是违规求助? 3531487
关于积分的说明 11254109
捐赠科研通 3270153
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809174