Automated cutaneous squamous cell carcinoma grading using deep learning with transfer learning.

IF 1.2 4区 医学 Q4 DEVELOPMENTAL BIOLOGY
Alexandra Buruiană, Mircea Sebastian Şerbănescu, Bogdan Pop, Bogdan Alexandru Gheban, Carmen Georgiu, Doiniţa Crişan, Maria Crişan
{"title":"Automated cutaneous squamous cell carcinoma grading using deep learning with transfer learning.","authors":"Alexandra Buruiană, Mircea Sebastian Şerbănescu, Bogdan Pop, Bogdan Alexandru Gheban, Carmen Georgiu, Doiniţa Crişan, Maria Crişan","doi":"10.47162/RJME.65.2.10","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Histological grading of cutaneous squamous cell carcinoma (cSCC) is crucial for prognosis and treatment decisions, but manual grading is subjective and time-consuming.</p><p><strong>Aim: </strong>This study aimed to develop and validate a deep learning (DL)-based model for automated cSCC grading, potentially improving diagnostic accuracy (ACC) and efficiency.</p><p><strong>Materials and methods: </strong>Three deep neural networks (DNNs) with different architectures (AlexNet, GoogLeNet, ResNet-18) were trained using transfer learning on a dataset of 300 histopathological images of cSCC. The models were evaluated on their ACC, sensitivity (SN), specificity (SP), and area under the curve (AUC). Clinical validation was performed on 60 images, comparing the DNNs' predictions with those of a panel of pathologists.</p><p><strong>Results: </strong>The models achieved high performance metrics (ACC>85%, SN>85%, SP>92%, AUC>97%) demonstrating their potential for objective and efficient cSCC grading. The high agreement between the DNNs and pathologists, as well as among different network architectures, further supports the reliability and ACC of the DL models. The top-performing models are publicly available, facilitating further research and potential clinical implementation.</p><p><strong>Conclusions: </strong>This study highlights the promising role of DL in enhancing cSCC diagnosis, ultimately improving patient care.</p>","PeriodicalId":54447,"journal":{"name":"Romanian Journal of Morphology and Embryology","volume":null,"pages":null},"PeriodicalIF":1.2000,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11384044/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Romanian Journal of Morphology and Embryology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.47162/RJME.65.2.10","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"DEVELOPMENTAL BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: Histological grading of cutaneous squamous cell carcinoma (cSCC) is crucial for prognosis and treatment decisions, but manual grading is subjective and time-consuming.

Aim: This study aimed to develop and validate a deep learning (DL)-based model for automated cSCC grading, potentially improving diagnostic accuracy (ACC) and efficiency.

Materials and methods: Three deep neural networks (DNNs) with different architectures (AlexNet, GoogLeNet, ResNet-18) were trained using transfer learning on a dataset of 300 histopathological images of cSCC. The models were evaluated on their ACC, sensitivity (SN), specificity (SP), and area under the curve (AUC). Clinical validation was performed on 60 images, comparing the DNNs' predictions with those of a panel of pathologists.

Results: The models achieved high performance metrics (ACC>85%, SN>85%, SP>92%, AUC>97%) demonstrating their potential for objective and efficient cSCC grading. The high agreement between the DNNs and pathologists, as well as among different network architectures, further supports the reliability and ACC of the DL models. The top-performing models are publicly available, facilitating further research and potential clinical implementation.

Conclusions: This study highlights the promising role of DL in enhancing cSCC diagnosis, ultimately improving patient care.

利用深度学习和迁移学习对皮肤鳞状细胞癌进行自动分级。
导言:皮肤鳞状细胞癌(cSCC)的组织学分级对预后和治疗决策至关重要,但人工分级主观且耗时。目的:本研究旨在开发和验证基于深度学习(DL)的cSCC自动分级模型,从而提高诊断准确率(ACC)和效率:在 300 张 cSCC 组织病理学图像的数据集上使用迁移学习训练了三种不同架构的深度神经网络(DNN)(AlexNet、GoogLeNet、ResNet-18)。对模型的 ACC、灵敏度 (SN)、特异性 (SP) 和曲线下面积 (AUC) 进行了评估。对 60 幅图像进行了临床验证,比较了 DNN 与病理学家小组的预测结果:结果:这些模型达到了很高的性能指标(ACC>85%、SN>85%、SP>92%、AUC>97%),证明了它们在客观、高效的 cSCC 分级方面的潜力。DNN 与病理学家之间以及不同网络架构之间的高度一致进一步证明了 DL 模型的可靠性和 ACC。表现最好的模型可以公开获得,这有助于进一步的研究和潜在的临床实施:本研究强调了 DL 在提高 cSCC 诊断方面的重要作用,并最终改善了患者护理。
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 求助全文
来源期刊
CiteScore
1.70
自引率
20.00%
发文量
221
审稿时长
3-8 weeks
期刊介绍: Romanian Journal of Morphology and Embryology (Rom J Morphol Embryol) publishes studies on all aspects of normal morphology and human comparative and experimental pathology. The Journal accepts only researches that utilize modern investigation methods (studies of anatomy, pathology, cytopathology, immunohistochemistry, histochemistry, immunology, morphometry, molecular and cellular biology, electronic microscopy, etc.).
×
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