Boundary-Aware Gradient Operator Network for Medical Image Segmentation

计算机科学 卷积(计算机科学) 人工智能 卷积神经网络 边界(拓扑) 特征(语言学) 图像分割 分割 模式识别(心理学) 初始化 图像渐变 计算机视觉 人工神经网络 图像纹理 数学 数学分析 哲学 语言学 程序设计语言
作者
Li Yu,Wenwen Min,Shunfang Wang
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:28 (8): 4711-4723 被引量:5
标识
DOI:10.1109/jbhi.2024.3404273
摘要

Medical image segmentation is a crucial task in computer-aided diagnosis. Although convolutional neural networks (CNNs) have made significant progress in the field of medical image segmentation, the convolution kernels of CNNs are optimized from random initialization without explicitly encoding gradient information, leading to a lack of specificity for certain features, such as blurred boundary features. Furthermore, the frequently applied down-sampling operation also loses the fine structural features in shallow layers. Therefore, we propose a boundary-aware gradient operator network (BG-Net) for medical image segmentation, in which the gradient convolution (GConv) and the boundary-aware mechanism (BAM) modules are developed to simulate image boundary features and the remote dependencies between channels. The GConv module transforms the gradient operator into a convolutional operation that can extract gradient features; it attempts to extract more features such as images boundaries and textures, thereby fully utilizing limited input to capture more features representing boundaries. In addition, the BAM can increase the amount of global contextual information while suppressing invalid information by focusing on feature dependencies and the weight ratios between channels. Thus, the boundary perception ability of BG-Net is improved. Finally, we use a multi-modal fusion mechanism to effectively fuse lightweight gradient convolution and U-shaped branch features into a multilevel feature, enabling global dependencies and low-level spatial details to be effectively captured in a shallower manner. We conduct extensive experiments on eight datasets that broadly cover medical images to evaluate the effectiveness of the proposed BG-Net. The experimental results demonstrate that BG-Net outperforms the state-of-the-art methods, particularly those focused on boundary segmentation.
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
ADcal完成签到 ,获得积分10
1秒前
1秒前
GXLong完成签到,获得积分10
2秒前
祝你勇敢完成签到 ,获得积分10
3秒前
paper reader完成签到,获得积分10
12秒前
呆呆完成签到 ,获得积分10
12秒前
纯真雁菱完成签到,获得积分10
15秒前
xuhanghang完成签到,获得积分10
18秒前
hhh完成签到,获得积分10
19秒前
皮皮蛙完成签到,获得积分10
20秒前
鸡蛋完成签到 ,获得积分10
24秒前
Xiaoxiao应助科研通管家采纳,获得10
24秒前
Xiaoxiao应助科研通管家采纳,获得10
24秒前
玩命的十三完成签到 ,获得积分10
25秒前
眰恦完成签到 ,获得积分10
26秒前
HY完成签到,获得积分10
26秒前
yulian完成签到,获得积分10
28秒前
28秒前
无与伦比完成签到 ,获得积分10
29秒前
独行者完成签到,获得积分10
31秒前
32秒前
蓝桉完成签到 ,获得积分10
32秒前
Yue完成签到 ,获得积分10
37秒前
GB完成签到 ,获得积分10
38秒前
长风与海浪完成签到 ,获得积分10
39秒前
无为完成签到 ,获得积分10
41秒前
Zo完成签到,获得积分10
42秒前
iwsaml完成签到 ,获得积分10
42秒前
SciEngineerX完成签到,获得积分10
43秒前
43秒前
不吃芹菜完成签到,获得积分0
44秒前
曾经小伙完成签到 ,获得积分10
44秒前
YANGMJ完成签到,获得积分10
45秒前
小杨完成签到,获得积分10
48秒前
49秒前
wu8577完成签到 ,获得积分10
53秒前
愛愛愛愛发布了新的文献求助10
54秒前
54秒前
kk完成签到,获得积分10
57秒前
sally发布了新的文献求助10
58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 3968578
求助须知:如何正确求助?哪些是违规求助? 3513391
关于积分的说明 11167428
捐赠科研通 3248822
什么是DOI,文献DOI怎么找? 1794499
邀请新用户注册赠送积分活动 875116
科研通“疑难数据库(出版商)”最低求助积分说明 804664