Your browser doesn't support javascript.
loading
Progressive growing of Generative Adversarial Networks for improving data augmentation and skin cancer diagnosis.
Pérez, Eduardo; Ventura, Sebastián.
Afiliación
  • Pérez E; Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI). University of Córdoba, Córdoba, Spain; Maimónides Biomedical Research Institute of Córdoba (IMIBIC). University of Córdoba, Córdoba, Spain.
  • Ventura S; Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI). University of Córdoba, Córdoba, Spain; Maimónides Biomedical Research Institute of Córdoba (IMIBIC). University of Córdoba, Córdoba, Spain. Electronic address: sventura@uco.es.
Artif Intell Med ; 141: 102556, 2023 07.
Article en En | MEDLINE | ID: mdl-37295899
Early melanoma diagnosis is the most important factor in the treatment of skin cancer and can effectively reduce mortality rates. Recently, Generative Adversarial Networks have been used to augment data, prevent overfitting and improve the diagnostic capacity of models. However, its application remains a challenging task due to the high levels of inter and intra-class variance seen in skin images, limited amounts of data, and model instability. We present a more robust Progressive Growing of Adversarial Networks based on residual learning, which is highly recommended to ease the training of deep networks. The stability of the training process was increased by receiving additional inputs from preceding blocks. The architecture is able to produce plausible photorealistic synthetic 512 × 512 skin images, even with small dermoscopic and non-dermoscopic skin image datasets as problem domains. In this manner, we tackle the lack of data and the imbalance problems. Additionally, the proposed approach leverages a skin lesion boundary segmentation algorithm and transfer learning to enhance the diagnosis of melanoma. Inception score and Matthews Correlation Coefficient were used to measure the performance of the models. The architecture was evaluated qualitatively and quantitatively through the use of an extensive experimental study on sixteen datasets, illustrating its effectiveness in the diagnosis of melanoma. Finally, four state-of-the-art data augmentation techniques applied in five convolutional neural network models were significantly outperformed. The results indicated that a bigger number of trainable parameters will not necessarily obtain a better performance in melanoma diagnosis.
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias Cutáneas / Aprendizaje Profundo / Melanoma Tipo de estudio: Diagnostic_studies / Prognostic_studies Límite: Humans Idioma: En Revista: Artif Intell Med Asunto de la revista: INFORMATICA MEDICA Año: 2023 Tipo del documento: Article País de afiliación: España Pais de publicación: Países Bajos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias Cutáneas / Aprendizaje Profundo / Melanoma Tipo de estudio: Diagnostic_studies / Prognostic_studies Límite: Humans Idioma: En Revista: Artif Intell Med Asunto de la revista: INFORMATICA MEDICA Año: 2023 Tipo del documento: Article País de afiliación: España Pais de publicación: Países Bajos