A weighted rule based method for predicting malignancy of pulmonary nodules by nodule characteristics

Abstract

Predicting malignancy of solitary pulmonary nodules from computer tomography scans is a difficult and important problem in the diagnosis of lung cancer. This paper investigates the contribution of nodule characteristics in the prediction of malignancy. Using data from Lung Image Database Consortium (LIDC) database, we propose a weighted rule based classification approach for predicting malignancy of pulmonary nodules. LIDC database contains CT scans of nodules and information about nodule characteristics evaluated by multiple annotators. In the first step of our method, votes for nodule characteristics are obtained from ensemble classifiers by using image features. In the second step, votes and rules obtained from radiologist evaluations are used by a weighted rule based method to predict malignancy. The rule based method is constructed by using radiologist evaluations on previous cases. Correlations between malignancy and other nodule characteristics and agreement ratio of radiologists are considered in rule evaluation. To handle the unbalanced nature of LIDC, ensemble classifiers and data balancing methods are used. The proposed approach is compared with the classification methods trained on image features. Classification accuracy, specificity and sensitivity of classifiers are measured. The experimental results show that using nodule characteristics for malignancy prediction can improve classification results.

Integration of convolutional neural networks for pulmonary nodule malignancy assessment in a lung cancer classification pipeline

“…In the past years numerous works have addressed the problem of classifying the malignancy of pulmonary nodules in CT scans; some of these works use as features only radiologists annotations of the nodules and perform classification for example with rule-based [6] and statistical learning [10] methods or by building a machine learning classifier [7] or classifiers ensemble [11,12].…”

“…Conventional solutions (e.g. [6,7]) propose engineering handcrafted features extracted directly from the CT image to build standard machine learning classifiers. This approach achieves satisfactory results when nodule candidates are well-defined, but shows some shortcomings when the nodules present complex and different sizes, shapes and context.…”

Fast and Adaptive Detection of Pulmonary Nodules in Thoracic CT Images Using a Contextual Clustering Based Region Growing

“…Extraction of two dimensional and three-dimensional features is done are for the first three categories. The difference in the image resolution is taken for the calculation of all related features [3,4]. Figure 1 and 2 shows the CC based region growing segmentation result and Initial Nodule candidates after rule-based filtering respectively.…”

Cloud-Based NoSQL Open Database of Pulmonary Nodules for Computer-Aided Lung Cancer Diagnosis and Reproducible Research

“…Despite the fact that the GLCM-based texture analysis may be dated as method, it is still relevant to scientific literature and recent works have used texture features as image descriptors, using bidimensional or tridimensional analysis [38][39][40]. Texture analysis over a pulmonary nodule slice was performed in a previous work [41].…”