Hybrid intelligent approach for diagnosis of the lung nodule from CT images using spatial kernelized fuzzy c-means and ensemble learning

Lung cancer is one of the most common forms of cancer leading to over a million deaths per year throughout the world. The aim of this paper is to identify the pulmonary nodules in computed tomography (CT) images of the lung using a hybrid intelligent approach. At first, the proposed approach utilizes a type-II fuzzy algorithm to improve the quality of raw CT images. Then, a novel segmentation algorithm based on fuzzy c-means clustering, called modified spatial kernelized fuzzy c-means (MSFCM) clustering, is offered in order to achieve another representation of lung regions through an optimization methodology. Next, nodule candidates are detected among all available objects in the lung regions by a morphological procedure. This is followed by extracting significant statistical and morphological features from such nodule candidates and finally, an ensemble of three classifiers comprising Multilayer Perceptron (MLP), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM) is employed for the actual diagnosis and determining whether the nodule candidate is nodule (cancerous) or non-nodule (healthy). The effectiveness of the hybrid intelligent approach is evaluated using a public dataset for lung CT images, viz.: Lung Image Database Consortium (LIDC). The experimental results positively demonstrate that the modified spatial kernelized FCM segmentation is superior to the other techniques existing in the literature. More importantly, a number of useful performance measurements in medical applications including accuracy, sensitivity, specificity, confusion matrix, as well as the area under the Receiver Operating Characteristic (ROC) curve are computed. The obtained results confirm the promising performance of the proposed hybrid approach in undertaking pulmonary nodules diagnosis.