MLK-Net: Leveraging multi-scale and large kernel convolutions for robust skin lesion segmentation

IF 7.5 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Expert Systems with Applications Pub Date : 2025-03-13 DOI:10.1016/j.eswa.2025.127135
Yuxuan Luo , Yongquan Xue , Yifei Teng , Liejun Wang, Panpan Zheng
{"title":"MLK-Net: Leveraging multi-scale and large kernel convolutions for robust skin lesion segmentation","authors":"Yuxuan Luo ,&nbsp;Yongquan Xue ,&nbsp;Yifei Teng ,&nbsp;Liejun Wang,&nbsp;Panpan Zheng","doi":"10.1016/j.eswa.2025.127135","DOIUrl":null,"url":null,"abstract":"<div><div>Accurate medical image segmentation, especially for skin lesions, is challenging due to fuzzy boundaries, diverse shapes, and varying lesion sizes. Most existing SSM-based skin lesion segmentation methods use pure SSM or simply combine CNN with SSM as the network backbone, but often fail to fully consider background information and multi-scale features. To address these issues, we propose a novel network that integrates large convolution kernels for rich background feature extraction and combines multi-head mixed convolutions with small and large kernels to capture multi-scale features. This design improves the segmentation of complex structures and diverse lesion scales. Experiments on three benchmark skin lesion segmentation datasets demonstrate that our method consistently outperforms state-of-the-art approaches across multiple evaluation metrics, showcasing its robustness and effectiveness in tackling critical segmentation challenges. For reproduction, the implementation codes can be checked out at <span><span>https://github.com/yuxl2023/MLK-Net</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"276 ","pages":"Article 127135"},"PeriodicalIF":7.5000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Expert Systems with Applications","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0957417425007572","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Accurate medical image segmentation, especially for skin lesions, is challenging due to fuzzy boundaries, diverse shapes, and varying lesion sizes. Most existing SSM-based skin lesion segmentation methods use pure SSM or simply combine CNN with SSM as the network backbone, but often fail to fully consider background information and multi-scale features. To address these issues, we propose a novel network that integrates large convolution kernels for rich background feature extraction and combines multi-head mixed convolutions with small and large kernels to capture multi-scale features. This design improves the segmentation of complex structures and diverse lesion scales. Experiments on three benchmark skin lesion segmentation datasets demonstrate that our method consistently outperforms state-of-the-art approaches across multiple evaluation metrics, showcasing its robustness and effectiveness in tackling critical segmentation challenges. For reproduction, the implementation codes can be checked out at https://github.com/yuxl2023/MLK-Net.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
由于边界模糊、形状各异和病变大小不一,准确的医学图像分割,尤其是皮肤病变的分割,具有很大的挑战性。现有的基于 SSM 的皮损分割方法大多使用纯 SSM 或简单地将 CNN 与 SSM 结合起来作为网络骨干,但往往不能充分考虑背景信息和多尺度特征。为了解决这些问题,我们提出了一种新型网络,它集成了大卷积核以提取丰富的背景特征,并将多头混合卷积与大小核相结合以捕捉多尺度特征。这种设计提高了对复杂结构和不同尺度病变的分割能力。在三个基准皮损分割数据集上的实验表明,我们的方法在多个评估指标上始终优于最先进的方法,展示了它在应对关键分割挑战方面的鲁棒性和有效性。如需转载,可在 https://github.com/yuxl2023/MLK-Net 网站上查看实现代码。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Expert Systems with Applications
Expert Systems with Applications 工程技术-工程:电子与电气
CiteScore
13.80
自引率
10.60%
发文量
2045
审稿时长
8.7 months
期刊介绍: Expert Systems With Applications is an international journal dedicated to the exchange of information on expert and intelligent systems used globally in industry, government, and universities. The journal emphasizes original papers covering the design, development, testing, implementation, and management of these systems, offering practical guidelines. It spans various sectors such as finance, engineering, marketing, law, project management, information management, medicine, and more. The journal also welcomes papers on multi-agent systems, knowledge management, neural networks, knowledge discovery, data mining, and other related areas, excluding applications to military/defense systems.
期刊最新文献
SR_ColorNet: Multi-path attention aggregated and mask enhanced network for the super resolution and colorization of panchromatic image MLK-Net: Leveraging multi-scale and large kernel convolutions for robust skin lesion segmentation Dual learning based Pareto evolutionary algorithm for a kind of multi-objective task assignment problem Demystifying SAR with attention Disturbance observer-based adaptive fuzzy finite-time cooperative control for high-order multi-agent systems with input saturation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1