Automatic Localization of Five Relevant Dermoscopic Structures Based on YOLOv8 for Diagnosis Improvement.
Fiche publication
Date publication
juillet 2023
Journal
Journal of imaging
Auteurs
Membres identifiés du Cancéropôle Est :
Pr GOUTON Pierre
Tous les auteurs :
Chabi Adjobo E, Sanda Mahama AT, Gouton P, Tossa J
Lien Pubmed
Résumé
The automatic detection of dermoscopic features is a task that provides the specialists with an image with indications about the different patterns present in it. This information can help them fully understand the image and improve their decisions. However, the automatic analysis of dermoscopic features can be a difficult task because of their small size. Some work was performed in this area, but the results can be improved. The objective of this work is to improve the precision of the automatic detection of dermoscopic features. To achieve this goal, an algorithm named yolo-dermoscopic-features is proposed. The algorithm consists of four points: (i) generate annotations in the JSON format for supervised learning of the model; (ii) propose a model based on the latest version of Yolo; (iii) pre-train the model for the segmentation of skin lesions; (iv) train five models for the five dermoscopic features. The experiments are performed on the ISIC 2018 task2 dataset. After training, the model is evaluated and compared to the performance of two methods. The proposed method allows us to reach average performances of 0.9758, 0.954, 0.9724, 0.938, and 0.9692, respectively, for the Dice similarity coefficient, Jaccard similarity coefficient, precision, recall, and average precision. Furthermore, comparing to other methods, the proposed method reaches a better Jaccard similarity coefficient of 0.954 and, thus, presents the best similarity with the annotations made by specialists. This method can also be used to automatically annotate images and, therefore, can be a solution to the lack of features annotation in the dataset.
Mots clés
dermoscopic images, features detection, single-shot object detection algorithm
Référence
J Imaging. 2023 07 21;9(7):