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:17
标识
DOI:10.1002/mp.16217
摘要

BACKGROUND: Semi-supervised learning is becoming an effective solution for medical image segmentation because of the lack of a large amount of labeled data. PURPOSE: 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. METHODS: 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. RESULTS: 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. CONCLUSIONS: 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
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
企鹅不耐热完成签到,获得积分10
1秒前
杨媛发布了新的文献求助10
1秒前
JH_发布了新的文献求助10
1秒前
BINGBONG完成签到,获得积分10
1秒前
坦率的橘子完成签到,获得积分10
2秒前
辛勤的硬币完成签到,获得积分20
2秒前
2秒前
细胞核完成签到,获得积分10
2秒前
菠萝星猫发布了新的文献求助10
3秒前
3秒前
冲就完了发布了新的文献求助10
3秒前
lyl完成签到 ,获得积分10
3秒前
Yolotto3完成签到,获得积分10
3秒前
幸福黄蜂完成签到 ,获得积分10
3秒前
周xj完成签到,获得积分10
3秒前
pineapple完成签到 ,获得积分10
3秒前
英姑的应助被便便民工采纳,获得10
3秒前
剑兰先生完成签到,获得积分10
4秒前
4秒前
Stitch完成签到,获得积分10
4秒前
犹豫的冰香完成签到,获得积分10
4秒前
MingQue完成签到,获得积分10
5秒前
daigang发布了新的文献求助10
5秒前
李晓彤发布了新的文献求助10
5秒前
5秒前
巫马炎彬完成签到,获得积分0
6秒前
Hello的应助被cwp采纳,获得10
6秒前
Silieze完成签到,获得积分0
6秒前
6秒前
大力曲奇发布了新的文献求助10
6秒前
大橙子完成签到 ,获得积分10
6秒前
NexusExplorer的应助被pass采纳,获得10
7秒前
jjx完成签到,获得积分10
7秒前
titijaychou完成签到,获得积分10
7秒前
悲凉的新筠完成签到,获得积分10
7秒前
Domenico完成签到,获得积分10
7秒前
july7292完成签到,获得积分10
7秒前
HALO完成签到,获得积分10
7秒前
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180488
求助须知:如何正确求助?哪些是违规求助? 9570437
关于积分的说明 21812406
捐赠科研通 7776516
什么是DOI,文献DOI怎么找? 3433277
关于科研通互助平台的介绍 2557516
邀请新用户注册赠送积分活动 2479162