Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Biocybernetics and Biomedical Engineering

1 2024

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Skin cancer diagnosis using NIR spectroscopy data of skin lesions in vivo using machine learning algorithms

Rocha Matheus B., Loss Flavio P., da Cunha Pedro H., Zanoni Madson Poltronieri, de Lima Leandro M., Nascimento Isadora Tavares, Rezende Isabella, Canuto Tania R.P., de Paula Vieira Luciana, Rossoni Renan, Santos Maria C.S., Frasson Patricia Lyra, Romão Wanderson, Filgueiras Paulo R., Krohling Renato A.

Biocybernetics and Biomedical Engineering

2024

Vol. 44, no. 4

824--835

Skin lesions are classified in benign or malignant. Among the malignant, melanoma is a very aggressive cancer and the major cause of deaths. So, early diagnosis of skin cancer is very desired. In the last few years, there is a growing interest in computer aided diagnostic (CAD) of skin lesions. Near-Infrared (NIR) spectroscopy may provide an alternative source of information to automated CAD of skin lesions to be used with the modern techniques of machine learning and deep learning (MDL). One of the main limitations to apply MDL to spectroscopy is the lack of public datasets. Since there is no public dataset of NIR spectral data to skin lesions, as far as we know, an effort has been made and a new dataset named NIR-SC-UFES, has been collected, annotated and analyzed generating the gold-standard for classification of NIR spectral data to skin cancer. Next, the machine learning algorithms XGBoost, CatBoost, LightGBM, 1D-convolutional neural network (1D-CNN) and standard algorithms as SVM and PLS-DA were investigated to classify cancer and non-cancer skin lesions. Experimental results indicate that the best performance was obtained by LightGBM with pre-processing using standard normal variate (SNV), feature extraction and data augmentation with Generative Adversarial Networks (GAN) providing values of 0.839 for balanced accuracy, 0.851 for recall, 0.852 for precision, and 0.850 for F-score. The obtained results indicate the first steps in CAD of skin lesions aiming the automated triage of patients with skin lesions in vivo using NIR spectral data.