版权说明 操作指南
首页 > 成果 > 详情

SUTrans-NET: a hybrid transformer approach to skin lesion segmentation

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Li, Yaqin;Tian, Tonghe;Hu, Jing;Yuan, Cao
通讯作者:
Yuan, C
作者机构:
[Li, Yaqin; Hu, Jing; Yuan, C; Tian, Tonghe; Yuan, Cao] Wuhan Polytech Univ Sch, Sch Math & Comp Sci, Wuhan, Hubei, Peoples R China.
通讯机构:
[Yuan, C ] W
Wuhan Polytech Univ Sch, Sch Math & Comp Sci, Wuhan, Hubei, Peoples R China.
语种:
英文
关键词:
Convolutional neural networks;Decoding;Image segmentation;Multilayer neural networks;Oncology;Signal encoding;Textures;Convolutional neural network;Edge detail;Human health;Human lives;Image feature extractions;Lesion segmentations;Malignant skin tumor;Skin lesion;Skin lesion segmentation;Transformer;Dermatology
期刊:
PeerJ Computer Science
ISSN:
2376-5992
年:
2024
卷:
10
页码:
e1935
机构署名:
本校为第一且通讯机构
院系归属:
数学与计算机学院
摘要:
Melanoma is a malignant skin tumor that threatens human life and health. Early detection is essential for effective treatment. However, the low contrast between melanoma lesions and normal skin and the irregularity in size and shape make skin lesions difficult to detect with the naked eye in the early stages, making the task of skin lesion segmentation challenging. Traditional encoder-decoder built with U-shaped networks using convolutional neural network (CNN) networks have limitations in establishing long-term dependencies and global contextual connections, while the Transformer architecture...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com