The Classification of Six Common Skin Diseases Based on Xiangya-Derm: Development of a Chinese Database for Artificial Intelligence

Abstract

Background Skin and subcutaneous disease is the fourth-leading cause of the nonfatal disease burden worldwide and constitutes one of the most common burdens in primary care. However, there is a severe lack of dermatologists, particularly in rural Chinese areas. Furthermore, although artificial intelligence (AI) tools can assist in diagnosing skin disorders from images, the database for the Chinese population is limited. Objective This study aims to establish a database for AI based on the Chinese population and presents an initial study on six common skin diseases. Methods Each image was captured with either a digital camera or a smartphone, verified by at least three experienced dermatologists and corresponding pathology information, and finally added to the Xiangya-Derm database. Based on this database, we conducted AI-assisted classification research on six common skin diseases and then proposed a network called Xy-SkinNet. Xy-SkinNet applies a two-step strategy to identify skin diseases. First, given an input image, we segmented the regions of the skin lesion. Second, we introduced an information fusion block to combine the output of all segmented regions. We compared the performance with 31 dermatologists of varied experiences. Results Xiangya-Derm, as a new database that consists of over 150,000 clinical images of 571 different skin diseases in the Chinese population, is the largest and most diverse dermatological data set of the Chinese population. The AI-based six-category classification achieved a top 3 accuracy of 84.77%, which exceeded the average accuracy of dermatologists (78.15%). Conclusions Xiangya-Derm, the largest database for the Chinese population, was created. The classification of six common skin conditions was conducted based on Xiangya-Derm to lay a foundation for product research.

Basic principles of artificial intelligence in dermatology explained using melanoma

“…81 They usually focus on distinct conditions or specific questions rather than being open to general inclusion. 82 Relying on the diagnosis of an algorithm alone needs to be scrutinized ethically, especially if many of the named challenges cannot be solved. Moreover, there is a lack of large-scale clinical trials to properly validate the results thus far.…”

“…Data acquisition is aggravated by unconnected and individually established databases 81 . They usually focus on distinct conditions or specific questions rather than being open to general inclusion 82 . Relying on the diagnosis of an algorithm alone needs to be scrutinized ethically, especially if many of the named challenges cannot be solved.…”

Artificial intelligence in psoriasis: Where we are and where we are going

“…Furthermore, it is encouraging that Xiangya‐Derm, the largest database for the Chinese population, has been created. Professionals at this institution are working on developing AI diagnostic instruments based on skin images, which is foreseen to change healthcare in a fundamental way 35 …”

“…Professionals at this institution are working on developing AI diagnostic instruments based on skin images, which is foreseen to change healthcare in a fundamental way. 35 In addition to skin images, Chinese researchers and clinicians have attempted to utilize dermatoscopic images for AI diagnosis.…”

Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text

“…At the same time, the performance is highly dependent on the demographic data used in the training set, and current prevalent AI diagnostic models for skin diseases are not aiming at Asian populations. Thus, it is critical to develop an AI model with a wide range enough of dermatological diseases and accurate enough diagnoses to be applicable to Asian populations 27 .Xiangya-Derm, the Chinese dermatology database established in 2020, classified 6 category of common diseases and had achieved an accuracy of 84.77% of the top 3, which is higher than the average rate of dermatologists (78.15%) 28 . However, the amount number of training set and testing set are 2400 and 600 respectively (the ratio of training size: testing size is 4:1).…”