Computer-Aided Diagnosis of Lung Nodules in Computed Tomography by Using Phylogenetic Diversity, Genetic Algorithm, and SVM

Abstract

Lung cancer is pointed as the major cause of death among patients with cancer throughout the world. This work is intended to develop a methodology for diagnosis of lung nodules using images from the Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI). The proposed methodology uses image processing and pattern recognition techniques. In order to differentiate between the patterns of malignant and benign nodules, we used phylogenetic diversity by means of particular indexes, that are: intensive quadratic entropy, extensive quadratic entropy, average taxonomic distinctness, total taxonomic distinctness, and pure diversity indexes. After that, we applied the genetic algorithm for selection of the best model. In the tests' stage, we applied the proposed methodology to 1405 (394 malignant and 1011 benign) nodules. The proposed work presents promising results at the classification into malignant and benign, achieving accuracy of 92.52%, sensitivity of 93.1% and specificity of 92.26%. The results demonstrated a good rate of correct detections using texture features. Since a precocious detection allows a faster therapeutic intervention, thus a more favorable prognostic to the patient, we propose herein a methodology that contributes to the area in this aspect.

Keywords: Genetic algorithm; Lung cancer; Medical image; Phylogenetic diversity index.

Fig. 1

Proposed methodology

Fig. 2

Four iterations of the Otsu algorithm to separate the original ROI until there is only one species on each leaf. In a, the first iteration; in b, the second iteration; in c, d, the third and fourth ones

Fig. 3

Dendrogram generated from the ROI is shown in Fig. 2

Fig. 4

Ilustration of how to choose the best training model [3]