Utilização de redes neurais convolucionais, descritores calculados e informações clínicas do paciente para diagnóstico de câncer de pele

Abstract

Skin lesions diagnostic is a challenging problem due to the variety of visual aspects of the lesions. Since dermatologists make use of visual cues, lesion data and pacient data (denominated here by clinical metadata), we investigate if the combination of features from convolutional neural networks (CNN), handcrafted features and clinical metadata can improve the performance of automated diagnoses of skin cancer. Most works on skin lesion diagnosis in the literature use dermoscopic images without clinical metadata. In order to address this problem, we used a clinical image dataset of skin lesion with patient information collected via smartphone named PAD-UFES-20. With the proposed fusion architecture we show that the results using clinical features as a complement to the CNN and handcrafted features improve the classification in terms of balanced accuracy by 7.1% for cancer and by 3.2% for melanoma as compared with only features extracted from a CNN. In addition, our findings show that combining only handcrafted features with deep features did not improve the results indicating the importance of using clinical metadata for skin lesion classification.