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
刚刚
搞怪不斜完成签到,获得积分10
刚刚
刚刚
xinxiangshicheng完成签到 ,获得积分10
1秒前
愤怒的小鸟完成签到,获得积分10
1秒前
MY完成签到,获得积分10
1秒前
顾矜应助lenetivy采纳,获得10
2秒前
自觉寒梦发布了新的文献求助10
2秒前
美好斓发布了新的文献求助10
2秒前
郑文涛完成签到,获得积分10
3秒前
JamesPei应助专注的白柏采纳,获得10
4秒前
YHY发布了新的文献求助10
6秒前
好吃发布了新的文献求助10
6秒前
拾光完成签到,获得积分10
7秒前
long完成签到 ,获得积分10
7秒前
天天向上发布了新的文献求助10
8秒前
6260完成签到,获得积分10
8秒前
pcr163应助linhanwenzhou采纳,获得50
9秒前
9秒前
酷酷元风完成签到,获得积分10
10秒前
11秒前
天才幸运鱼完成签到,获得积分10
11秒前
12秒前
12秒前
粥游天下完成签到,获得积分10
13秒前
jcc完成签到,获得积分10
13秒前
哈哈哈哈完成签到,获得积分10
13秒前
lighthouse完成签到,获得积分10
14秒前
平凡中的限量版完成签到,获得积分10
14秒前
大伟完成签到,获得积分10
14秒前
long关注了科研通微信公众号
15秒前
懵懂的毛豆完成签到,获得积分10
15秒前
zzcherished发布了新的文献求助10
15秒前
zyq发布了新的文献求助10
15秒前
我是老大应助哦哦哦采纳,获得10
16秒前
YHY完成签到,获得积分10
16秒前
16秒前
天天呼的海角完成签到,获得积分10
19秒前
量子星尘发布了新的文献求助10
22秒前
22秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
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 4038368
求助须知:如何正确求助?哪些是违规求助? 3576068
关于积分的说明 11374313
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029