Image Processing Methods for Oral Macules and Spots Segmentation

Abstract

Oral cancers are the 16th most common type of cancer in the world and present a high mortality rate. This is mainly because they are frequently discovered in an advanced stage due to the lack of specialized professionals. Some clinical characteristics such as borders and symmetry can aid in cancer diagnosis, and therefore the segmentation of the lesions is important. In light of this, this work aimed to present and evaluate different analytic methods to perform automatic segmentation of oral macules and spots from 21 clinical images. From the tested methods, the one with the best result reached an accuracy of 84.9%, a precision of 70.1%, a recall of 75.3%, and an f1-score of 60.8%, which are similar outcomes of published works that used artificial intelligence.