eprintid: 16273 rev_number: 8 eprint_status: archive userid: 2 dir: disk0/00/01/62/73 datestamp: 2025-01-22 23:30:09 lastmod: 2025-01-22 23:30:10 status_changed: 2025-01-22 23:30:09 type: article metadata_visibility: show creators_name: Aboulmira, Amina creators_name: Hrimech, Hamid creators_name: Lachgar, Mohamed creators_name: Hanine, Mohamed creators_name: Osorio García, Carlos Manuel creators_name: Méndez Mezquita, Gerardo creators_name: Ashraf, Imran creators_id: creators_id: creators_id: creators_id: creators_id: carlos.osorio@uneatlantico.es creators_id: creators_id: title: Hybrid Model with Wavelet Decomposition and EfficientNet for Accurate Skin Cancer Classification ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: unic_produccion_cientifica full_text_status: public keywords: skin lesion, transfer learning, wavelet decomposition, image processing, convolutional neural networks abstract: Faced with anomalies in medical images, Deep learning is facing major challenges in detecting, diagnosing, and classifying the various pathologies that can be treated via medical imaging. The main challenges encountered are mainly due to the imbalance and variability of the data, as well as its complexity. The detection and classification of skin diseases is one such challenge that researchers are trying to overcome, as these anomalies present great variability in terms of appearance, texture, color, and localization, which sometimes makes them difficult to identify accurately and quickly, particularly by doctors, or by the various Deep Learning techniques on offer. In this study, an innovative and robust hybrid architecture is unveiled, underscoring the symbiotic potential of wavelet decomposition in conjunction with EfficientNet models. This approach integrates wavelet transformations with an EfficientNet backbone and incorporates advanced data augmentation, loss function, and optimization strategies. The model tested on the publicly accessible HAM10000 and ISIC2017 datasets has achieved an accuracy rate of 94.7%, and 92.2% respectively. date: 2025-01 publication: Journal of Cancer volume: 16 number: 2 pagerange: 506-520 id_number: doi:10.7150/jca.101574 refereed: TRUE issn: 1837-9664 official_url: http://doi.org/10.7150/jca.101574 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional do Cuanza > Investigación > Artículos y libros Abierto Inglés Faced with anomalies in medical images, Deep learning is facing major challenges in detecting, diagnosing, and classifying the various pathologies that can be treated via medical imaging. The main challenges encountered are mainly due to the imbalance and variability of the data, as well as its complexity. The detection and classification of skin diseases is one such challenge that researchers are trying to overcome, as these anomalies present great variability in terms of appearance, texture, color, and localization, which sometimes makes them difficult to identify accurately and quickly, particularly by doctors, or by the various Deep Learning techniques on offer. In this study, an innovative and robust hybrid architecture is unveiled, underscoring the symbiotic potential of wavelet decomposition in conjunction with EfficientNet models. This approach integrates wavelet transformations with an EfficientNet backbone and incorporates advanced data augmentation, loss function, and optimization strategies. The model tested on the publicly accessible HAM10000 and ISIC2017 datasets has achieved an accuracy rate of 94.7%, and 92.2% respectively. metadata Aboulmira, Amina; Hrimech, Hamid; Lachgar, Mohamed; Hanine, Mohamed; Osorio García, Carlos Manuel; Méndez Mezquita, Gerardo y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, carlos.osorio@uneatlantico.es, SIN ESPECIFICAR, SIN ESPECIFICAR (2025) Hybrid Model with Wavelet Decomposition and EfficientNet for Accurate Skin Cancer Classification. Journal of Cancer, 16 (2). pp. 506-520. ISSN 1837-9664 document_url: http://repositorio.unic.co.ao/id/eprint/16273/1/v16p0506.pdf