不同机器学习算法在皮肤癌和黑色素瘤检测中的应用及其相关性能

IF 1.2 Q3 DERMATOLOGY
Suboh Alkhushayni, Du’a Al-zaleq, Luwis Andradi, Patrick Flynn
{"title":"不同机器学习算法在皮肤癌和黑色素瘤检测中的应用及其相关性能","authors":"Suboh Alkhushayni, Du’a Al-zaleq, Luwis Andradi, Patrick Flynn","doi":"10.1155/2022/2839162","DOIUrl":null,"url":null,"abstract":"Skin cancer, and its less common form melanoma, is a disease affecting a wide variety of people. Since it is usually detected initially by visual inspection, it makes for a good candidate for the application of machine learning. With early detection being key to good outcomes, any method that can enhance the diagnostic accuracy of dermatologists and oncologists is of significant interest. When comparing different existing implementations of machine learning against public datasets and several we seek to create, we attempted to create a more accurate model that can be readily adapted to use in clinical settings. We tested combinations of models, including convolutional neural networks (CNNs), and various layers of data manipulation, such as the application of Gaussian functions and trimming of images to improve accuracy. We also created more traditional data models, including support vector classification, K-nearest neighbor, Naïve Bayes, random forest, and gradient boosting algorithms, and compared them to the CNN-based models we had created. Results had indicated that CNN-based algorithms significantly outperformed other data models we had created. Partial results of this work were presented at the CSET Presentations for Research Month at the Minnesota State University, Mankato.","PeriodicalId":17172,"journal":{"name":"Journal of Skin Cancer","volume":"3 1","pages":""},"PeriodicalIF":1.2000,"publicationDate":"2022-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"The Application of Differing Machine Learning Algorithms and Their Related Performance in Detecting Skin Cancers and Melanomas\",\"authors\":\"Suboh Alkhushayni, Du’a Al-zaleq, Luwis Andradi, Patrick Flynn\",\"doi\":\"10.1155/2022/2839162\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Skin cancer, and its less common form melanoma, is a disease affecting a wide variety of people. Since it is usually detected initially by visual inspection, it makes for a good candidate for the application of machine learning. With early detection being key to good outcomes, any method that can enhance the diagnostic accuracy of dermatologists and oncologists is of significant interest. When comparing different existing implementations of machine learning against public datasets and several we seek to create, we attempted to create a more accurate model that can be readily adapted to use in clinical settings. We tested combinations of models, including convolutional neural networks (CNNs), and various layers of data manipulation, such as the application of Gaussian functions and trimming of images to improve accuracy. We also created more traditional data models, including support vector classification, K-nearest neighbor, Naïve Bayes, random forest, and gradient boosting algorithms, and compared them to the CNN-based models we had created. Results had indicated that CNN-based algorithms significantly outperformed other data models we had created. Partial results of this work were presented at the CSET Presentations for Research Month at the Minnesota State University, Mankato.\",\"PeriodicalId\":17172,\"journal\":{\"name\":\"Journal of Skin Cancer\",\"volume\":\"3 1\",\"pages\":\"\"},\"PeriodicalIF\":1.2000,\"publicationDate\":\"2022-05-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Skin Cancer\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1155/2022/2839162\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"DERMATOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Skin Cancer","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1155/2022/2839162","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"DERMATOLOGY","Score":null,"Total":0}
引用次数: 3

摘要

皮肤癌及其不太常见的黑色素瘤是一种影响多种人群的疾病。由于它通常是通过视觉检查来检测的,因此它是机器学习应用的一个很好的候选者。由于早期发现是取得良好结果的关键,任何能够提高皮肤科医生和肿瘤学家诊断准确性的方法都是值得关注的。在将不同的现有机器学习实现与公共数据集和我们试图创建的几个数据集进行比较时,我们试图创建一个更准确的模型,可以很容易地适应临床环境。我们测试了模型的组合,包括卷积神经网络(cnn),以及各种数据操作层,例如高斯函数的应用和图像的修剪以提高准确性。我们还创建了更传统的数据模型,包括支持向量分类、k近邻、Naïve贝叶斯、随机森林和梯度增强算法,并将它们与我们创建的基于cnn的模型进行比较。结果表明,基于cnn的算法明显优于我们创建的其他数据模型。这项工作的部分结果在曼卡托明尼苏达州立大学的CSET研究月报告中发表。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
The Application of Differing Machine Learning Algorithms and Their Related Performance in Detecting Skin Cancers and Melanomas
Skin cancer, and its less common form melanoma, is a disease affecting a wide variety of people. Since it is usually detected initially by visual inspection, it makes for a good candidate for the application of machine learning. With early detection being key to good outcomes, any method that can enhance the diagnostic accuracy of dermatologists and oncologists is of significant interest. When comparing different existing implementations of machine learning against public datasets and several we seek to create, we attempted to create a more accurate model that can be readily adapted to use in clinical settings. We tested combinations of models, including convolutional neural networks (CNNs), and various layers of data manipulation, such as the application of Gaussian functions and trimming of images to improve accuracy. We also created more traditional data models, including support vector classification, K-nearest neighbor, Naïve Bayes, random forest, and gradient boosting algorithms, and compared them to the CNN-based models we had created. Results had indicated that CNN-based algorithms significantly outperformed other data models we had created. Partial results of this work were presented at the CSET Presentations for Research Month at the Minnesota State University, Mankato.
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
Journal of Skin Cancer
Journal of Skin Cancer DERMATOLOGY-
CiteScore
2.30
自引率
18.20%
发文量
12
审稿时长
21 weeks
期刊介绍: Journal of Skin Cancer is a peer-reviewed, Open Access journal that publishes clinical and translational research on the detection, diagnosis, prevention, and treatment of skin malignancies. The journal encourages the submission of original research articles, review articles, and clinical studies related to pathology, prognostic indicators and biomarkers, novel therapies, as well as drug sensitivity and resistance.
×
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