The purpose of a recent study published in Frontiers in Medicine aimed to design a novel framework based on deep learning, trained by a dataset representing the real clinical environment in a tertiary class hospital, for better adaptation of artificial intelligence (AI) in clinical practice among Asian patients.

The dataset comprised of 13,603 dermatologist-labeled dermoscopic images with 14 categories of diseases – lichen planus (LP), rosacea (Rosa), viral warts (VW), acne vulgaris (AV), keloid and hypertrophic scar (KAHS), eczema and dermatitis (EAD), dermatofibroma (DF), seborrheic dermatitis (SD), seborrheic keratosis (SK), melanocytic nevus (MN), hemangioma (Hem), psoriasis (Pso), port wine stain (PWS) and basal cell carcinoma (BCC).

The results showed that the proposed framework achieved a high level of classification performance with an overall accuracy of 0.948, a sensitivity of 0.934 and a specificity of 0.950. The proposed framework outperformed existing models with the highest area under curve (AUC) of 0.985.  When compared with 280 board-certificated dermatologists, the results of this model at par in performance level in an 8-class diagnostic task.

Therefore, the proposed framework retrained by the dataset that represented the real clinical environment could accurately classify most common dermatoses encountered during outpatient practice including infectious and inflammatory dermatoses, benign and malignant cutaneous tumors.

Source: Front Med (Lausanne). 2021;8:626369.