Jesutofunmi A. Omiye , Babar K. Rao , Shazli Razi , Nadiya Chuchvara , Fred M. Baik , Roxana Daneshjou , Lisa C. Zaba
{"title":"Automated Detection of Benign and Malignant Skin Lesions from Reflectance Confocal Microscopy Images Using Deep Learning","authors":"Jesutofunmi A. Omiye , Babar K. Rao , Shazli Razi , Nadiya Chuchvara , Fred M. Baik , Roxana Daneshjou , Lisa C. Zaba","doi":"10.1016/j.xjidi.2025.100404","DOIUrl":null,"url":null,"abstract":"<div><div>Reflectance confocal microscopy offers a noninvasive approach for diagnosing skin lesions at the point of care, but it remains underutilized owing to the specialized skill required for interpretation. Artificial intelligence provides an opportunity to automate this process. We developed deep learning models to automate the analysis of reflectance confocal microscopy block images. Reflectance confocal microscopy images acquired from 3rd and 4th generation VivaScope 1500 devices were preprocessed and split for training and testing. Two models were developed: a modified convolutional neural network ResNet-18, for skin layer detection, and a ResNet-34 integrated with a gated recurrent unit for lesion classification. The models were pretrained on 3rd generation images and fine tuned on 4th generation data, utilizing 5-fold cross-validation. Our cohort included 845 patients, 1147 lesions, and 4391 VivaBlock images. The layer detection model identified the dermis, epidermis, and dermoepidermal junction, achieving an area under the curve of 0.70, 0.71, and 0.57, respectively. The lesion classification model distinguished malignant from benign lesions with an area under the curve of 0.80 and specificity of 0.91. Our convolutional neural network gated recurrent unit approach effectively distinguished benign from malignant lesions, showing impressive diagnostic accuracy mimicking expert dermatological assessments. This highlights artificial intelligence's potential in improving reflectance confocal microscopy image interpretation, reducing unnecessary biopsies, and paves the way for future research.</div></div>","PeriodicalId":73548,"journal":{"name":"JID innovations : skin science from molecules to population health","volume":"5 6","pages":"Article 100404"},"PeriodicalIF":0.0000,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JID innovations : skin science from molecules to population health","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667026725000608","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Reflectance confocal microscopy offers a noninvasive approach for diagnosing skin lesions at the point of care, but it remains underutilized owing to the specialized skill required for interpretation. Artificial intelligence provides an opportunity to automate this process. We developed deep learning models to automate the analysis of reflectance confocal microscopy block images. Reflectance confocal microscopy images acquired from 3rd and 4th generation VivaScope 1500 devices were preprocessed and split for training and testing. Two models were developed: a modified convolutional neural network ResNet-18, for skin layer detection, and a ResNet-34 integrated with a gated recurrent unit for lesion classification. The models were pretrained on 3rd generation images and fine tuned on 4th generation data, utilizing 5-fold cross-validation. Our cohort included 845 patients, 1147 lesions, and 4391 VivaBlock images. The layer detection model identified the dermis, epidermis, and dermoepidermal junction, achieving an area under the curve of 0.70, 0.71, and 0.57, respectively. The lesion classification model distinguished malignant from benign lesions with an area under the curve of 0.80 and specificity of 0.91. Our convolutional neural network gated recurrent unit approach effectively distinguished benign from malignant lesions, showing impressive diagnostic accuracy mimicking expert dermatological assessments. This highlights artificial intelligence's potential in improving reflectance confocal microscopy image interpretation, reducing unnecessary biopsies, and paves the way for future research.