Ryohei Kaneko, Satoshi Akaishi, Rei Ogawa, Hiroaki Kuwahara
{"title":"Machine Learning-based Complementary Artificial Intelligence Model for Dermoscopic Diagnosis of Pigmented Skin Lesions in Resource-limited Settings.","authors":"Ryohei Kaneko, Satoshi Akaishi, Rei Ogawa, Hiroaki Kuwahara","doi":"10.1097/GOX.0000000000007004","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Rapid advancements in big data and machine learning have expanded their application in healthcare, introducing sophisticated diagnostics to settings with limited medical resources. Notably, free artificial intelligence (AI) services that require no programming skills are now accessible to healthcare professionals, allowing those in underresourced areas to leverage AI technology. This study aimed to evaluate the potential of these accessible services for diagnosing pigmented skin tumors, underscoring the democratization of advanced medical technologies.</p><p><strong>Methods: </strong>In this experimental diagnostic study, we collected 400 dermoscopic images (100 per tumor type) labeled through supervised learning from pathologically confirmed cases. The images were split into training, validation, and testing datasets (8:1:1 ratio) and uploaded to Vertex AI for model training. Supervised learning was performed using the Google Cloud Platform, Vertex AI, based on pathological diagnoses. The model's performance was assessed using confusion matrices and precision-recall curves.</p><p><strong>Results: </strong>The AI model achieved an average recall rate of 86.3%, precision rate of 87.3%, accuracy of 86.3%, and F1 score of 0.87. Misclassification rates were less than 20% for each category. Accuracy was 80% for malignant melanoma and 100% for both basal cell carcinoma and seborrheic keratosis. Testing on separate cases yielded an accuracy of approximately 70%.</p><p><strong>Conclusions: </strong>The metrics obtained in this study suggest that the model can reliably assist in the diagnostic process, even for practitioners without prior AI expertise. The study demonstrated that free AI tools can accurately classify pigmented skin lesions with minimal expertise, potentially providing high-precision diagnostic support in settings lacking dermatologists.</p>","PeriodicalId":20149,"journal":{"name":"Plastic and Reconstructive Surgery Global Open","volume":"13 7","pages":"e7004"},"PeriodicalIF":1.8000,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12303417/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Plastic and Reconstructive Surgery Global Open","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1097/GOX.0000000000007004","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/7/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"SURGERY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Rapid advancements in big data and machine learning have expanded their application in healthcare, introducing sophisticated diagnostics to settings with limited medical resources. Notably, free artificial intelligence (AI) services that require no programming skills are now accessible to healthcare professionals, allowing those in underresourced areas to leverage AI technology. This study aimed to evaluate the potential of these accessible services for diagnosing pigmented skin tumors, underscoring the democratization of advanced medical technologies.
Methods: In this experimental diagnostic study, we collected 400 dermoscopic images (100 per tumor type) labeled through supervised learning from pathologically confirmed cases. The images were split into training, validation, and testing datasets (8:1:1 ratio) and uploaded to Vertex AI for model training. Supervised learning was performed using the Google Cloud Platform, Vertex AI, based on pathological diagnoses. The model's performance was assessed using confusion matrices and precision-recall curves.
Results: The AI model achieved an average recall rate of 86.3%, precision rate of 87.3%, accuracy of 86.3%, and F1 score of 0.87. Misclassification rates were less than 20% for each category. Accuracy was 80% for malignant melanoma and 100% for both basal cell carcinoma and seborrheic keratosis. Testing on separate cases yielded an accuracy of approximately 70%.
Conclusions: The metrics obtained in this study suggest that the model can reliably assist in the diagnostic process, even for practitioners without prior AI expertise. The study demonstrated that free AI tools can accurately classify pigmented skin lesions with minimal expertise, potentially providing high-precision diagnostic support in settings lacking dermatologists.
期刊介绍:
Plastic and Reconstructive Surgery—Global Open is an open access, peer reviewed, international journal focusing on global plastic and reconstructive surgery.Plastic and Reconstructive Surgery—Global Open publishes on all areas of plastic and reconstructive surgery, including basic science/experimental studies pertinent to the field and also clinical articles on such topics as: breast reconstruction, head and neck surgery, pediatric and craniofacial surgery, hand and microsurgery, wound healing, and cosmetic and aesthetic surgery. Clinical studies, experimental articles, ideas and innovations, and techniques and case reports are all welcome article types. Manuscript submission is open to all surgeons, researchers, and other health care providers world-wide who wish to communicate their research results on topics related to plastic and reconstructive surgery. Furthermore, Plastic and Reconstructive Surgery—Global Open, a complimentary journal to Plastic and Reconstructive Surgery, provides an open access venue for the publication of those research studies sponsored by private and public funding agencies that require open access publication of study results. Its mission is to disseminate high quality, peer reviewed research in plastic and reconstructive surgery to the widest possible global audience, through an open access platform. As an open access journal, Plastic and Reconstructive Surgery—Global Open offers its content for free to any viewer. Authors of articles retain their copyright to the materials published. Additionally, Plastic and Reconstructive Surgery—Global Open provides rapid review and publication of accepted papers.