Semi‐supervised medical image segmentation via cross‐guidance and feature‐level consistency dual regularization schemes

正规化(语言学) 人工智能 计算机科学 分割 编码器 模式识别(心理学) 医学影像学 深度学习 变压器 图像分割 特征提取 量子力学 操作系统 物理 电压
作者
Yang Xiaosu,Jiya Tian,Yaping Wan,Mingzhi Chen,Lingna Chen,Junxi Chen
出处
期刊:Medical Physics [Wiley]
卷期号:50 (7): 4269-4281 被引量:9
标识
DOI:10.1002/mp.16217
摘要

Semi-supervised learning is becoming an effective solution for medical image segmentation because of the lack of a large amount of labeled data.Consistency-based strategy is widely used in semi-supervised learning. However, it is still a challenging problem because of the coupling of CNN-based isomorphic models. In this study, we propose a new semi-supervised medical image segmentation network (DRS-Net) based on a dual-regularization scheme to address this challenge.The proposed model consists of a CNN and a multidecoder hybrid Transformer, which adopts two regularization schemes to extract more generalized representations for unlabeled data. Considering the difference in learning paradigm, we introduce the cross-guidance between CNN and hybrid Transformer, which uses the pseudo label output from one model to supervise the other model better to excavate valid representations from unlabeled data. In addition, we use feature-level consistency regularization to effectively improve the feature extraction performance. We apply different perturbations to the feature maps output from the hybrid Transformer encoder and keep an invariance of the predictions to enhance the encoder's representations.We have extensively evaluated our approach on three typical medical image datasets, including CT slices from Spleen, MRI slices from the Heart, and FM Nuclei. We compare DRS-Net with state-of-the-art methods, and experiment results show that DRS-Net performs better on the Spleen dataset, where the dice similarity coefficient increased by about 3.5%. The experimental results on the Heart and Nuclei datasets show that DRS-Net also improves the segmentation effect of the two datasets.The proposed DRS-Net enhances the segmentation performance of the datasets with three different medical modalities, where the dual-regularization scheme extracts more generalized representations and solves the overfitting problem.
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
穿堂风完成签到,获得积分10
刚刚
1秒前
缥缈忻完成签到,获得积分10
1秒前
2秒前
ASH发布了新的文献求助10
5秒前
852应助如意代秋采纳,获得10
6秒前
祝愿发布了新的文献求助10
6秒前
9秒前
9秒前
daoyi完成签到,获得积分10
10秒前
10秒前
11秒前
14秒前
flow完成签到,获得积分10
15秒前
123gg发布了新的文献求助10
15秒前
zong2807完成签到,获得积分10
16秒前
阿菜完成签到,获得积分10
16秒前
泥嚎发布了新的文献求助10
17秒前
19秒前
tuanheqi应助研友_LXjjOZ采纳,获得150
19秒前
酷波er应助北北采纳,获得10
22秒前
田様应助CHRIS采纳,获得10
22秒前
小焦儿完成签到,获得积分10
23秒前
万能图书馆应助坚定白风采纳,获得10
23秒前
丘比特应助小任性采纳,获得10
23秒前
所所应助liziqi采纳,获得10
24秒前
雪白的夏山完成签到,获得积分10
31秒前
失眠的广山完成签到 ,获得积分10
31秒前
36秒前
37秒前
星辰大海应助大喵采纳,获得10
39秒前
40秒前
41秒前
41秒前
keyantong发布了新的文献求助10
41秒前
薛妖怪发布了新的文献求助10
41秒前
小任性发布了新的文献求助10
42秒前
南瓜饼完成签到,获得积分10
43秒前
漂亮白枫发布了新的文献求助10
44秒前
zhxq发布了新的文献求助10
45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 3989797
求助须知:如何正确求助?哪些是违规求助? 3531910
关于积分的说明 11255394
捐赠科研通 3270563
什么是DOI,文献DOI怎么找? 1805008
邀请新用户注册赠送积分活动 882157
科研通“疑难数据库(出版商)”最低求助积分说明 809190