Abstract
An artificial intelligence algorithm to detect mycosis fungoides (MF), psoriasis (PSO), and atopic dermatitis (AD) is demonstrated. Results showed that 10 s was consumed by the single shot multibox detector (SSD) model to analyze 292 test images, among which 273 images were correctly detected. Verification of ground truth samples of this research come from pathological tissue slices and OCT analysis. The SSD diagnosis accuracy rate was 93%. The sensitivity values of the SSD model in diagnosing the skin lesions according to the symptoms of PSO, AD, MF, and normal were 96%, 80%, 94%, and 95%, and the corresponding precision were 96%, 86%, 98%, and 90%. The highest sensitivity rate was found in MF probably because of the spread of cancer cells in the skin and relatively large lesions of MF. Many differences were found in the accuracy between AD and the other diseases. The collected AD images were all in the elbow or arm and other joints, the area with AD was small, and the features were not obvious. Hence, the proposed SSD could be used to identify the four diseases by using skin image detection, but the diagnosis of AD was relatively poor.
Highlights
Mycosis fungoides (MF) is a rare disease, unlike common skin cancers, such as squamous cell carcinoma, basal cell carcinoma, and melanoma, which are mainly caused by long-term exposure to the sun
Given that the early symptoms of MF are similar to the foci of psoriasis (PSO) and atopic dermatitis (AD), MF is often mistaken for the later skin disorders, delaying the time for treatment
Comparison of the ground truth and bounding box showed whether single shot multibox detector (SSD) could diagnose MF
Summary
Mycosis fungoides (MF) is a rare disease, unlike common skin cancers, such as squamous cell carcinoma, basal cell carcinoma, and melanoma, which are mainly caused by long-term exposure to the sun. The capability of artificial intelligence (AI) in interpreting images can be used to achieve the recognition level similar to those of traditional inspection methods and the detection accuracy of noninvasive diagnosis. Explained that the combination of human skills and AI CNN to detect suspicious skin cancer images is better than the independent method. This research is performed to propose a rapid and universal disease detection method, which can be applied to images of skin diseases. The authors hope to use the interpretation ability of AI in images to achieve the same level of recognition as those of traditional inspection methods and the detection effect similar to noninvasive diagnosis
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
