Open AccessAsymmetry analysis of melanoma based on ABCD rule
Author(s) -
Zhang Guo-lan,
Sisi Guo
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1883/1/012070
Subject(s) - melanoma , stage (stratigraphy) , medicine , harm , feature (linguistics) , dermatology , computer science , artificial intelligence , radiology , psychology , cancer research , social psychology , paleontology , linguistics , philosophy , biology
Malignant melanoma is a malignant tumor that is extremely harmful and prone to lymphatic metastasis. If it cannot be diagnosed and effectively treated at an early stage, it will cause irreversible consequences. There is a lot of evidence that if you can get the exact treatment in the early stage, it can effectively improve the recovery rate. At this stage, clinical diagnosis of melanoma is mainly performed manually, which has defects such as low overall efficiency. This article is based on ABCD rule, combined with the clinical features of melanoma in dermoscopic images, to determine the benign and malignant melanocytes. Firstly, the image processing technology and pattern recognition technology are used to acquire and preprocess the dermoscopic image, and the image feature points are extracted. Then, the microscopic asymmetry and macroscopic asymmetry of the image were analyzed. Finally, the symmetry score was calculated by TDS to judge the benign and malignant of melanocytes. It is expected to assist dermatologists in diagnosing melanoma, provide timely feedback information to patients and provide targeted treatment for patients, improve the efficiency and accuracy of medical clinical diagnosis, achieve the purpose of curing, and reduce the harm of melanoma to human health.