应对皮肤癌诊断中的挑战:卷积斯温变换器方法

Sudha Paraddy, Virupakshappa
{"title":"应对皮肤癌诊断中的挑战:卷积斯温变换器方法","authors":"Sudha Paraddy, Virupakshappa","doi":"10.1007/s10278-024-01290-9","DOIUrl":null,"url":null,"abstract":"<p><p>Skin cancer is one of the top three hazardous cancer types, and it is caused by the abnormal proliferation of tumor cells. Diagnosing skin cancer accurately and early is crucial for saving patients' lives. However, it is a challenging task due to various significant issues, including lesion variations in texture, shape, color, and size; artifacts (hairs); uneven lesion boundaries; and poor contrast. To solve these issues, this research proposes a novel Convolutional Swin Transformer (CSwinformer) method for segmenting and classifying skin lesions accurately. The framework involves phases such as data preprocessing, segmentation, and classification. In the first phase, Gaussian filtering, Z-score normalization, and augmentation processes are executed to remove unnecessary noise, re-organize the data, and increase data diversity. In the phase of segmentation, we design a new model \"Swinformer-Net\" integrating Swin Transformer and U-Net frameworks, to accurately define a region of interest. At the final phase of classification, the segmented outcome is input into the newly proposed module \"Multi-Scale Dilated Convolutional Neural Network meets Transformer (MD-CNNFormer),\" where the data samples are classified into respective classes. We use four benchmark datasets-HAM10000, ISBI 2016, PH2, and Skin Cancer ISIC for evaluation. The results demonstrated the designed framework's better efficiency against the traditional approaches. The proposed method provided classification accuracy of 98.72%, pixel accuracy of 98.06%, and dice coefficient of 97.67%, respectively. The proposed method offered a promising solution in skin lesion segmentation and classification, supporting clinicians to accurately diagnose skin cancer.</p>","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":"1755-1775"},"PeriodicalIF":0.0000,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092923/pdf/","citationCount":"0","resultStr":"{\"title\":\"Addressing Challenges in Skin Cancer Diagnosis: A Convolutional Swin Transformer Approach.\",\"authors\":\"Sudha Paraddy, Virupakshappa\",\"doi\":\"10.1007/s10278-024-01290-9\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Skin cancer is one of the top three hazardous cancer types, and it is caused by the abnormal proliferation of tumor cells. Diagnosing skin cancer accurately and early is crucial for saving patients' lives. However, it is a challenging task due to various significant issues, including lesion variations in texture, shape, color, and size; artifacts (hairs); uneven lesion boundaries; and poor contrast. To solve these issues, this research proposes a novel Convolutional Swin Transformer (CSwinformer) method for segmenting and classifying skin lesions accurately. The framework involves phases such as data preprocessing, segmentation, and classification. In the first phase, Gaussian filtering, Z-score normalization, and augmentation processes are executed to remove unnecessary noise, re-organize the data, and increase data diversity. In the phase of segmentation, we design a new model \\\"Swinformer-Net\\\" integrating Swin Transformer and U-Net frameworks, to accurately define a region of interest. At the final phase of classification, the segmented outcome is input into the newly proposed module \\\"Multi-Scale Dilated Convolutional Neural Network meets Transformer (MD-CNNFormer),\\\" where the data samples are classified into respective classes. We use four benchmark datasets-HAM10000, ISBI 2016, PH2, and Skin Cancer ISIC for evaluation. The results demonstrated the designed framework's better efficiency against the traditional approaches. The proposed method provided classification accuracy of 98.72%, pixel accuracy of 98.06%, and dice coefficient of 97.67%, respectively. The proposed method offered a promising solution in skin lesion segmentation and classification, supporting clinicians to accurately diagnose skin cancer.</p>\",\"PeriodicalId\":516858,\"journal\":{\"name\":\"Journal of imaging informatics in medicine\",\"volume\":\" \",\"pages\":\"1755-1775\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2025-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12092923/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of imaging informatics in medicine\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s10278-024-01290-9\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/10/22 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of imaging informatics in medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s10278-024-01290-9","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/10/22 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

皮肤癌是三大危险癌症之一,由肿瘤细胞异常增殖引起。准确、早期诊断皮肤癌对于挽救患者生命至关重要。然而,由于病变在质地、形状、颜色和大小上的变化,伪影(毛发),病变边界不均匀以及对比度差等各种重大问题,诊断皮肤癌是一项极具挑战性的任务。为了解决这些问题,本研究提出了一种新颖的卷积斯文变换器(CSwinformer)方法,用于准确分割和分类皮肤病变。该框架包括数据预处理、分割和分类等阶段。在第一阶段,我们会执行高斯滤波、Z-score 归一化和增强处理,以去除不必要的噪声、重新组织数据并增加数据多样性。在分割阶段,我们设计了一个整合了 Swin Transformer 和 U-Net 框架的新模型 "Swinformer-Net",以准确定义感兴趣的区域。在分类的最后阶段,分割结果被输入到新提出的模块 "多尺度稀释卷积神经网络与转换器(MD-CNNFormer)"中,数据样本在此被划分到相应的类别中。我们使用四个基准数据集--HAM10000、ISBI 2016、PH2 和皮肤癌 ISIC 进行评估。结果表明,与传统方法相比,所设计的框架具有更高的效率。所提方法的分类准确率为 98.72%,像素准确率为 98.06%,骰子系数为 97.67%。所提出的方法为皮肤病变的分割和分类提供了一种有前途的解决方案,有助于临床医生准确诊断皮肤癌。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Addressing Challenges in Skin Cancer Diagnosis: A Convolutional Swin Transformer Approach.

Skin cancer is one of the top three hazardous cancer types, and it is caused by the abnormal proliferation of tumor cells. Diagnosing skin cancer accurately and early is crucial for saving patients' lives. However, it is a challenging task due to various significant issues, including lesion variations in texture, shape, color, and size; artifacts (hairs); uneven lesion boundaries; and poor contrast. To solve these issues, this research proposes a novel Convolutional Swin Transformer (CSwinformer) method for segmenting and classifying skin lesions accurately. The framework involves phases such as data preprocessing, segmentation, and classification. In the first phase, Gaussian filtering, Z-score normalization, and augmentation processes are executed to remove unnecessary noise, re-organize the data, and increase data diversity. In the phase of segmentation, we design a new model "Swinformer-Net" integrating Swin Transformer and U-Net frameworks, to accurately define a region of interest. At the final phase of classification, the segmented outcome is input into the newly proposed module "Multi-Scale Dilated Convolutional Neural Network meets Transformer (MD-CNNFormer)," where the data samples are classified into respective classes. We use four benchmark datasets-HAM10000, ISBI 2016, PH2, and Skin Cancer ISIC for evaluation. The results demonstrated the designed framework's better efficiency against the traditional approaches. The proposed method provided classification accuracy of 98.72%, pixel accuracy of 98.06%, and dice coefficient of 97.67%, respectively. The proposed method offered a promising solution in skin lesion segmentation and classification, supporting clinicians to accurately diagnose skin cancer.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信