Leprosy Skin Lesion Detection: An AI Approach Using Few Shot Learning in a Small Clinical Dataset

This is an exploratory research study to check if artificial intelligence (AI) based image marker tool can aid leprosy screening to detect leprosy cases early in field situation and reduce the financial and personnel burden. We aimed to collect clinical leprosy skin lesion images and develop an AI model to identify and differentiate them. A total of 368 clinically diagnosed leprosy and 28 non-leprosy skin lesions were collected by an expert leprologist from 151 eligible patients using a multimodal imaging protocol. A Siamese-based Few Shot Learning (FSL) model was trained as it is a meta learning approach on an extremely small data set with fewer disease classes (disease conditions as categories). The number of class labels were increased by fine-grained grouping of skin lesions based on skin morphology (Nine leprosy subgroups) and further divided into train-set and test-set. An AI model was successfully developed, and the results indicated an accuracy of 91.25% and 73.12% on train-set and test-set for two-way one-shot task, respectively. The best sensitivity-specificity for the test-set were 72.39%-73.66% (two-way one-shot task). This early research data indicates that the development of AI based leprosy screening application is feasible using the skin lesion image as marker. The FSL method was successfully used in this training the small data set. However, this is a small sample size study, and more leprosy cases need to be enrolled along with an equal number of non- leprosy cases while improving model architecture to reduce overfit or bias problem. Moreover, as of now this tool cannot be used for neural leprosy (having no skin lesion) as well as lepromatous leprosy having diffuse infiltration. This tool will need further development and validation on pictures taken by different categories of common health care workers using available mobile phones.

Skin imaging and noninvasive measurements for rosacea / 中华皮肤科杂志

Rosacea is a chronic inflammatory disease. In addition to subjective evaluation, some objective quantifiable indices are needed for the diagnosis and treatment of rosacea. Some skin imaging and noninvasive measurement tools have been applied to clinical practice, and can provide quantitative or semi-quantitative indices to assist the diagnosis and treatment of rosacea. This review summarizes relevant research progress to provide evidence for clinical standardized application.

Application value of high-frequency ultrasonography in some disfiguring dermatoses / 中华皮肤科杂志

Disfiguring dermatoses are a group of cutaneous diseases that affects the appearance and mental health of patients to various extents. Patients usually have high expectations for the treatment outcome, and there is an urgent need for convenient and accurate non-invasive auxiliary evaluation tools for better diagnosis and treatment. With the development of high-frequency ultrasonography, more and more skin diseases, including disfiguring dermatoses, have been objectively and accurately assessed by this technology. This review summarizes research progress in the application of high-frequency ultrasonography in the diagnosis and treatment of some disfiguring dermatoses.

Skin imaging technologies for photoaging / 中华皮肤科杂志

Skin photoaging not only affects the appearance, but also is associated with skin tumors. It is very important to objectively and effectively evaluate photoaging. Histopathological examination is the gold standard for the diagnosis of photoaging, but it can not be used repeatedly because of its invasiveness, and is not suitable for dynamic monitoring and evaluation of photoaging. Skin imaging technologies can realize in vivo, real-time and non-invasive two- or three-dimensional image analysis, which facilitate the visual assessment of skin photoaging. This review summarizes research progress in dermoscopy, reflectance confocal microscopy, high-frequency ultrasound and optical coherence tomography in evaluation of photoaging.

Morphological analysis of melasma lesions at different clinical stages by using three different skin imaging techniques / 中华皮肤科杂志

Objective To investigate morphological characteristics of female melasma lesions at different clinical stages by using three skin imaging techniques.Methods A total of 253 female outpatients with melasma were enrolled from the Third Affiliated Hospital of Zhejiang Chinese Medicine University between June 2017 and January 2018.According to the clinical staging criteria,melasma lesions at different clinical stages were observed with reflectance confocal microscopy (RCM),VISIA skin imaging detector and dermoscopy,and correlations of clinical staging with dendritic melanocytes,subclinical melasma and morphological changes of blood vessels were analyzed.Statistical analysis was carried out with SPSS19.0 software by using chi-square test and Mann-Whitney U test for the comparison of enumeration data.Results Of 253 patients with melasma,100 were with progressive melasma,and 153 with stablemelasma.RCM showed that dendritic melanocytes were observed in 78 (78％) patients with progressive melasma,as well as in 22 (14.4％)patients with stable melasma,and there was a significant difference between the 2 groups (x2 =102.40,P ＜ 0.01).VISIA skin imaging detector showed that subclinical melasma was observed in 78 (78％) patients with progressive melasma,as well as in 25 (16.3％) patients with stable melasma,and the prevalance of subclinical melasma was significantly higher in the patients with progressive melasma than in those with stable melasma (x2 =95.26,P ＜ 0.01).Dermoscopy showed that the frequency of morphological changes in blood vessels did not differ between the patients with progressive melasma (74％,74/100) and those with stable melasma (68.6％,105/153;x2 =0.84,P =0.39).Conclusion The dendritic melanocytes and subclinical manifestations under RCM and VISIA skin imaging detector can serve as reference indices for clinical staging of melasma.

Application and development of artificial intelligence in dermatology / 中华皮肤科杂志

Artificial intelligence,known as the science and engineering of manufacturing intelligent machines,is one of the frontier science and technology that affects the development of modern society.With the progress of computer science and internet technology,artificial intelligence has gradually formed 3 main branches:cognitive computing,machine learning and deep learning.In recent years,the cooperation between artificial intelligence and medicine has been applied in many aspects,such as image recognition,assistant diagnosis,medical robots,drug research and development.Furthermore,characteristics of dermatology and advantages of artificial intelligence in image recognition make the application of artificial intelligence in dermatology become a focus nowadays.The authors summarize the application scope of artificial intelligence in dermatology,such as skin imaging,skin pathology and medical robots,analyze the current situation of artificial intelligence application in dermatology,and make prospects for the trend of development in the future.