An artificial intelligence model for the semantic segmentation of neoplasms on images of the skin

We present here an artificial intelligence model based on deep learning for semantic segmentation of dermatoscopic images of skin neoplasms. The model was trained using an annotated image database. This paper discusses the challenge of increasing diagnostic accuracy using a two-level procedure based on artificial intelligence: 1) first, the object of medical interest is segmented; 2) the object is then classified. The present work is proposed as part of the first stage. Experimental studies (training set 583 images, test set 73 images) demonstrated high segmentation accuracy (Jaccard index 0.93) as compared with known methods. The approach proposed here can be used to recognize skin diseases using neural network technologies.