A medical image segmentation method for rectal tumors based on multi‐scale feature retention and multiple attention mechanisms

分割 计算机科学 人工智能 特征(语言学) 卷积神经网络 模式识别(心理学) 图像分割 特征提取 深度学习 骨干网 计算机视觉 医学影像学 哲学 语言学 计算机网络
作者
Jumin Zhao,Linjun Liu,Xiaotang Yang,Yanfen Cui,Dengao Li,Huiting Zhang,Kenan Zhang
出处
期刊:Medical Physics [Wiley]
卷期号:51 (5): 3275-3291
标识
DOI:10.1002/mp.17044
摘要

Abstract Background With the continuous development of deep learning algorithms in the field of medical images, models for medical image processing based on convolutional neural networks have made great progress. Since medical images of rectal tumors are characterized by specific morphological features and complex edges that differ from natural images, achieving good segmentation results often requires a higher level of enrichment through the utilization of semantic features. Purpose The efficiency of feature extraction and utilization has been improved to some extent through enhanced hardware arithmetic and deeper networks in most models. However, problems still exist with detail loss and difficulty in feature extraction, arising from the extraction of high‐level semantic features in deep networks. Methods In this work, a novel medical image segmentation model has been proposed for Magnetic Resonance Imaging (MRI) image segmentation of rectal tumors. The model constructs a backbone architecture based on the idea of jump‐connected feature fusion and solves the problems of detail feature loss and low segmentation accuracy using three novel modules: Multi‐scale Feature Retention (MFR), Multi‐branch Cross‐channel Attention (MCA), and Coordinate Attention (CA). Results Compared with existing methods, our proposed model is able to segment the tumor region more effectively, achieving 97.4% and 94.9% in Dice and mIoU metrics, respectively, exhibiting excellent segmentation performance and computational speed. Conclusions Our proposed model has improved the accuracy of both lesion region and tumor edge segmentation. In particular, the determination of the lesion region can help doctors identify the tumor location in clinical diagnosis, and the accurate segmentation of the tumor edge can assist doctors in judging the necessity and feasibility of surgery.
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
格子完成签到,获得积分10
1秒前
天天完成签到 ,获得积分10
1秒前
冷静傲丝完成签到 ,获得积分10
1秒前
ly完成签到,获得积分10
2秒前
2秒前
2秒前
罐罐儿完成签到,获得积分0
3秒前
秀丽的小懒虫完成签到,获得积分10
3秒前
林洛沁完成签到,获得积分10
3秒前
diaobk完成签到,获得积分20
3秒前
mj发布了新的文献求助10
4秒前
华国锋完成签到,获得积分10
4秒前
5秒前
5秒前
坚定的可愁完成签到,获得积分10
6秒前
可靠的老鼠完成签到,获得积分10
6秒前
ddd完成签到 ,获得积分10
6秒前
diaobk发布了新的文献求助10
7秒前
Zetlynn完成签到,获得积分10
7秒前
8秒前
jjj发布了新的文献求助1000
8秒前
iPhone7跑GWAS完成签到,获得积分10
9秒前
小瑞完成签到,获得积分20
9秒前
pmfgn完成签到,获得积分10
10秒前
阿V完成签到,获得积分10
10秒前
11秒前
luna完成签到,获得积分10
11秒前
iNk应助lu采纳,获得10
11秒前
阿yueyue完成签到 ,获得积分10
11秒前
eleven发布了新的文献求助10
12秒前
木木完成签到,获得积分10
13秒前
贪玩的万仇完成签到,获得积分10
13秒前
橘子石榴完成签到 ,获得积分10
13秒前
猫好好完成签到,获得积分10
15秒前
修好世界完成签到,获得积分10
15秒前
Lau完成签到,获得积分10
15秒前
liu完成签到,获得积分10
15秒前
mj完成签到,获得积分10
16秒前
Time完成签到,获得积分10
17秒前
完美世界应助炸药采纳,获得10
17秒前
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 3968608
求助须知:如何正确求助?哪些是违规求助? 3513486
关于积分的说明 11168243
捐赠科研通 3248926
什么是DOI,文献DOI怎么找? 1794540
邀请新用户注册赠送积分活动 875188
科研通“疑难数据库(出版商)”最低求助积分说明 804676