Diagnosis of Non-Small Cell Lung Cancer Using Phylogenetic Diversity in Radiomics Context

Lung cancer is the most common type of cancer and has the highest mortality rate in the world. The automatic process for the diagnosis by computer vision systems, through medical images, provides an interpretation regarding the pathology. The idea of this work is to use the texture features using phylogenetic diversity indexes, to classify Non-Small Cell Lung Cancer. This work presents the development of texture descriptors based on phylogenetic diversity indices for characterization of the nodule. The tests showed promising results of 98.47% accuracy, a Kappa index of 0.979 and an ROC of 0.999.