Benign-Malignant Lung Nodule Classification with Geometric and Appearance Histogram Features

TL;DR

This paper introduces an automated system for classifying lung nodules as benign or malignant in CT images, utilizing geometric and histogram features combined with various classifiers, achieving high accuracy on a public dataset.

Contribution

It presents a novel combination of geometric and histogram features with multiple classifiers for lung nodule classification, validated on a large public dataset.

Findings

82% accuracy in malignant nodule classification

93% accuracy in benign nodule classification

Effective feature combination for improved diagnosis

Abstract

Lung cancer accounts for the highest number of cancer deaths globally. Early diagnosis of lung nodules is very important to reduce the mortality rate of patients by improving the diagnosis and treatment of lung cancer. This work proposes an automated system to classify lung nodules as malignant and benign in CT images. It presents extensive experimental results using a combination of geometric and histogram lung nodule image features and different linear and non-linear discriminant classifiers. The proposed approach is experimentally validated on the LIDC-IDRI public lung cancer screening thoracic computed tomography (CT) dataset containing nodule level diagnostic data. The obtained results are very encouraging correctly classifying 82% of malignant and 93% of benign nodules on unseen test data at best.