LeaNet: Lightweight U-shaped architecture for high-performance skin cancer image segmentation

计算机科学 分割 图像分割 特征(语言学) 人工智能 像素 模式识别(心理学) 计算机视觉 哲学 语言学
作者
Binbin Hu,Pan Zhou,Hongfang Yu,Yueyue Dai,Ming Wang,Shengbo Tan,Ying Sun
出处
期刊:Computers in Biology and Medicine [Elsevier BV]
卷期号:169: 107919-107919 被引量:29
标识
DOI:10.1016/j.compbiomed.2024.107919
摘要

Skin cancer diagnosis often relies on image segmentation as a crucial aid, and a high-performance segmentation can lower misdiagnosis risks. Part of the medical devices often have limited computing power for deploying image segmentation algorithms. However, existing high-performance algorithms for image segmentation primarily rely on computationally intensive large models, making it challenging to meet the lightweight deployment requirement of medical devices. State-of-the-art lightweight models are not able to capture both local and global feature information of lesion edges due to their model structures, result in pixel loss of lesion edge. To tackle this problem, we propose LeaNet, a novel U-shaped network for high-performance yet lightweight skin cancer image segmentation. Specifically, LeaNet employs multiple attention blocks in a lightweight symmetric U-shaped design. Each blocks contains a dilated efficient channel attention (DECA) module for global and local contour information and an inverted external attention (IEA) module to improve information correlation between data samples. Additionally, LeaNet uses an attention bridge (AB) module to connect the left and right sides of the U-shaped architecture, thereby enhancing the model's multi-level feature extraction capability. We tested our model on ISIC2017 and ISIC2018 datasets. Compared with large models like ResUNet, LeaNet improved the ACC, SEN, and SPEC metrics by 1.09 %, 2.58 %, and 1.6 %, respectively, while reducing the model's parameter number and computational complexity by 570x and 1182x. Compared with lightweight models like MALUNet, LeaNet achieved improvements of 2.07 %, 4.26 %, and 3.11 % in ACC, SEN, and SPEC, respectively, reducing the parameter number and computational complexity by 1.54x and 1.04x.
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
周少发布了新的文献求助10
刚刚
Jasper应助ruaruaburua采纳,获得10
2秒前
Lily完成签到,获得积分10
2秒前
高兴新梅发布了新的文献求助10
5秒前
Ava应助椰子冻采纳,获得10
6秒前
7秒前
burn发布了新的文献求助10
8秒前
贾克斯完成签到,获得积分20
9秒前
10秒前
玛卡巴卡发布了新的文献求助10
11秒前
GAO发布了新的文献求助10
12秒前
强健的雅绿完成签到,获得积分10
12秒前
酷波er应助贾克斯采纳,获得10
13秒前
聪明煎饼完成签到,获得积分10
13秒前
小马甲应助小白白采纳,获得10
14秒前
科目三应助松鼠桂鱼采纳,获得10
15秒前
科研通AI5应助碧蓝的青荷采纳,获得10
15秒前
alisa完成签到,获得积分10
16秒前
nobody发布了新的文献求助10
16秒前
16秒前
Lily发布了新的文献求助10
17秒前
华仔应助huan采纳,获得30
19秒前
19秒前
晚风完成签到,获得积分10
19秒前
alisa发布了新的文献求助10
20秒前
21秒前
21秒前
吉吉发布了新的文献求助10
21秒前
研友_VZG7GZ应助世界需要我采纳,获得10
22秒前
mmz666发布了新的文献求助10
22秒前
Dc发布了新的文献求助30
24秒前
嗯哼哈哈发布了新的文献求助10
24秒前
24秒前
burn发布了新的文献求助10
24秒前
ller发布了新的文献求助10
26秒前
mayumei完成签到 ,获得积分10
26秒前
27秒前
学分发布了新的文献求助30
27秒前
刘青秀完成签到,获得积分10
28秒前
Hellenzz发布了新的文献求助10
28秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
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 3976177
求助须知:如何正确求助?哪些是违规求助? 3520366
关于积分的说明 11202745
捐赠科研通 3256847
什么是DOI,文献DOI怎么找? 1798509
邀请新用户注册赠送积分活动 877704
科研通“疑难数据库(出版商)”最低求助积分说明 806516