Coşar Soğukkuyu Derya Yeliz, Ata Oğuz
Institute of Graduate Studies, Altinbas University, İstanbul, Turkey.
Department of Information Technology, Altinbas University, İstanbul, Turkey.
PeerJ Comput Sci. 2023 Aug 24;9:e1533. doi: 10.7717/peerj-cs.1533. eCollection 2023.
Nail diseases are malformations that appear on the nail plate and are classified according to their own signs and symptoms that may be related to other medical conditions. Although most nail diseases have distinct symptoms, making a differential diagnosis of nail problems can be challenging for medical experts.
One early diagnosis method for any dermatological disease is designing an image analysis system based on artificial intelligence (AI) techniques. This article implemented a novel model using a publicly available nail disease dataset to determine the occurrence of three common types of nail diseases. Two classification models based on transfer learning using visual geometry group (VGGNet) were utilized to detect and classify nail diseases from images.
The experimental design results showed good accuracy: VGG16 had a score of 94% accuracy and VGG19 had a 93% accuracy rate. These findings suggest that computer-aided diagnostic systems based on transfer learning can be used to identify multiple-lesion nail diseases.
指甲疾病是出现在指甲板上的畸形，根据其自身的体征和症状进行分类，这些体征和症状可能与其他医疗状况相关。尽管大多数指甲疾病有明显的症状，但对医学专家来说，对指甲问题进行鉴别诊断可能具有挑战性。
任何皮肤病的一种早期诊断方法是基于人工智能（AI）技术设计一个图像分析系统。本文使用一个公开可用的指甲疾病数据集实现了一个新颖的模型，以确定三种常见指甲疾病的发生情况。利用基于视觉几何组（VGGNet）迁移学习的两种分类模型从图像中检测和分类指甲疾病。
实验设计结果显示出良好的准确率：VGG16的准确率为94%，VGG19的准确率为93%。这些发现表明，基于迁移学习的计算机辅助诊断系统可用于识别多病灶指甲疾病。
