Incremental Learning for Dermatological Imaging Modality Classification

• Tipo: Artigo em Revista Científica Internacional
• Data: 2021

Autores

Morgado, AC (Autor) Outra; Andrade, C (Autor) Outra; Luis F Teixeira (Autor) FEUP; Vasconcelos, MJM (Autor) Outra

Revista

Título: Journal of Imaging

Vol. 20

Página Final: 180

Editora: MDPI

Indexação

ISI Web of Knowledge - 2 Citações

Scopus - 4 Citações

Outras Informações

ID Authenticus: P-00V-CN1

DOI: 10.3390/jimaging7090180

Abstract (EN): With the increasing adoption of teledermatology, there is a need to improve the automatic organization of medical records, being dermatological image modality a key filter in this process. Although there has been considerable effort in the classification of medical imaging modalities, this has not been in the field of dermatology. Moreover, as various devices are used in teledermatological consultations, image acquisition conditions may differ. In this work, two models (VGG-16 and MobileNetV2) were used to classify dermatological images from the Portuguese National Health System according to their modality. Afterwards, four incremental learning strategies were applied to these models, namely naive, elastic weight consolidation, averaged gradient episodic memory, and experience replay, enabling their adaptation to new conditions while preserving previously acquired knowledge. The evaluation considered catastrophic forgetting, accuracy, and computational cost. The MobileNetV2 trained with the experience replay strategy, with 500 images in memory, achieved a global accuracy of 86.04% with only 0.0344 of forgetting, which is 6.98% less than the second-best strategy. Regarding efficiency, this strategy took 56 s per epoch longer than the baseline and required, on average, 4554 megabytes of RAM during training. Promising results were achieved, proving the effectiveness of the proposed approach.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 18