清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

3D medical image segmentation based on semi-supervised learning using deep co-training

人工智能 计算机科学 过度拟合 深度学习 分割 图像分割 模式识别(心理学) 一致性(知识库) 可视化 机器学习 人工神经网络
作者
Jingdong Yang,Haoqiu Li,Han Wang,Han Man
出处
期刊:Applied Soft Computing [Elsevier BV]
卷期号:159: 111641-111641 被引量:2
标识
DOI:10.1016/j.asoc.2024.111641
摘要

In recent years, artificial intelligence has been applied to 3D COVID-19 medical image diagnosis, which reduces detection costs and missed diagnosis rates with higher predictive accuracy, and diagnostic efficiency. However, the limited size and low quality of clinical 3D medical image samples have hindered the segmentation performance of 3D models. Therefore, we propose a 3D medical image segmentation model based on semi-supervised learning using co-training. Multi-view and multi-modal images are generated using spatial flipping and windowing techniques to enhance the spatial diversity of 3D image samples. A pseudo label generation module based on confidence-weights is employed to generate reliable pseudo labels for non-annotated data, thereby increasing the sample size and reducing overfitting. The proposed approach utilizes a three-stage training process: firstly, training a single network based on annotated data; secondly, incorporating non-annotated data to train a dual-modal network and generate pseudo labels; finally, jointly training six models in three dimensions using both annotated and pseudo labels generated from multi-view and multi-modal images, aiming to enhance segmentation accuracy and generalization performance. Additionally, a consistency regularization loss is applied to reduce noises and accelerate convergence of the training. Moreover, a heatmap visualization method is employed to focus on the attention of features at each stage of training, providing effective reference for clinical diagnosis. Experiments were conducted on an open dataset of 3D COVID-19 CT samples and a non-annotated dataset from TCIA, including 771 NIFTI-format CT images from 661 COVID-19 patients. The results of 5-fold cross-validation show that the proposed model achieves a segmentation accuracy of Dice=73.30%, ASD=10.633, Sensitivity=63.00%, and Specificity=99.60%. Compared to various typical semi-supervised learning 3D segmentation models, it demonstrates better segmentation accuracy and generalization performance.
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
benzene完成签到 ,获得积分10
5秒前
5433完成签到 ,获得积分10
6秒前
KINGAZX完成签到 ,获得积分10
6秒前
muriel完成签到,获得积分10
9秒前
小马甲应助傲娇的夜山采纳,获得10
11秒前
11秒前
orixero应助Demi_Ming采纳,获得10
12秒前
17秒前
可爱的函函应助mo采纳,获得10
22秒前
科研通AI2S应助雪白小丸子采纳,获得10
24秒前
傲娇的夜山完成签到,获得积分10
29秒前
mo完成签到,获得积分20
42秒前
好天气完成签到 ,获得积分20
1分钟前
好天气关注了科研通微信公众号
1分钟前
领导范儿应助533采纳,获得10
1分钟前
1分钟前
Demi_Ming发布了新的文献求助10
1分钟前
1分钟前
1分钟前
1分钟前
1分钟前
张哈完成签到 ,获得积分10
1分钟前
科研通AI2S应助科研通管家采纳,获得10
2分钟前
SciGPT应助科研通管家采纳,获得10
2分钟前
2分钟前
2分钟前
和谐乌龟发布了新的文献求助10
2分钟前
葫芦芦芦完成签到 ,获得积分10
2分钟前
张琦完成签到 ,获得积分10
2分钟前
2分钟前
雪白小丸子完成签到,获得积分10
3分钟前
naczx完成签到,获得积分0
3分钟前
喵叽完成签到 ,获得积分20
3分钟前
冷傲半邪完成签到,获得积分10
3分钟前
冠冠冠冠发布了新的文献求助150
3分钟前
喵叽关注了科研通微信公众号
3分钟前
冠冠冠冠完成签到,获得积分10
3分钟前
简单的雅蕊完成签到,获得积分10
3分钟前
4分钟前
4分钟前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
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 3968504
求助须知:如何正确求助?哪些是违规求助? 3513331
关于积分的说明 11167297
捐赠科研通 3248697
什么是DOI,文献DOI怎么找? 1794417
邀请新用户注册赠送积分活动 875030
科研通“疑难数据库(出版商)”最低求助积分说明 804652