| Title |
Enhancing multi-class prediction of skin lesions with feature importance assessment / |
| Authors |
Paulauskaite-Taraseviciene, Agne ; Sutiene, Kristina ; Dimsa, Nojus ; Valiukeviciene, Skaidra |
| DOI |
10.61822/amcs-2024-0041 |
| Full Text |
|
| Is Part of |
International journal of applied mathematics and computer science.. Warsaw : Sciendo. 2024, vol. 34, iss. 4, p. 617-629.. ISSN 1641-876X. eISSN 2083-8492 |
| Keywords [eng] |
skin lesion ; feature extraction ; graph theory ; multi-class prediction ; SHAP values. |
| Abstract [eng] |
Numerous image processing techniques have been developed for the identification of various types of skin lesions. In real-world scenarios, the specific lesion type is often unknown in advance, leading to a multi-class prediction challenge. The available evidence underscores the importance of employing a comprehensive array of diverse features and subsequently identifying the most important ones as a crucial step in visual diagnostics. For this purpose, we addressed both binary and five-class classification tasks using a small dataset, with skin lesions prevalent in Lithuania. The model was trained using a rich set of 662 features, encompassing both conventional image features and graph-based ones, which were obtained from the superpixel graph generated using Delaunay triangulation. We explored the influence of feature importance determined by SHAP values, resulting in a weighted F1-score of 92.48% for the two-class classification and 71.21% for the five-class prediction. |
| Published |
Warsaw : Sciendo |
| Type |
Journal article |
| Language |
English |
| Publication date |
2024 |
| CC license |
|
