Download Full Text (2.9 MB)


Lung cancer is the leading cause of cancerous disease in the United States. Lung cancer usually exhibits its presence with the formation of pulmonary nodules. Nodules are round or oval-shaped growth present in the lung. Chest radiographs are used by radiologists to detect and treat such nodules, but nodules are quite difficult to detect with human eye and are sometimes misinterpreted with lesions present. Thus, automated analysis of such data is very essential and would be of valuable help in lung cancer screening. A new Computer Aided Detection (CAD) system in chest radiography is proposed in this paper. The algorithmic steps of the CAD system include: (i) local contrast enhancement of chest radiographs; (ii) automated anatomical segmentation; (iii) detection of nodule candidates; (iv) feature extraction; (v) candidate classification. In this research, we present facets of the proposed algorithm using a publically available dataset and we explore new set of features and other classifiers. The publically available dataset was created by Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI). LIDC-IDRI dataset is comprised of 276 patient chest radiographs containing nodules of various types and sizes. The centroids of the nodules are provided by at least one of four board certified radiologists. Local contrast enhancement of chest radiographs is achieved using a Gaussian low pass filter. Automated anatomical segmentation is performed using an active shape model. Potential candidate nodules can then be determined by using an adaptive distance –based threshold algorithm limited to the delineated lung fields. Later, a set of features are computed for each potential candidate. Based on those tailored features, a learning based system such as neural network can be used to classify the candidates into true or false positives. This CAD system could serve as an express way for processing an x-ray and would aid in providing a second opinion to radiologists.

Publication Date


Project Designation

Graduate Research

Primary Advisor

Russel C. Hardie, Temesguen M. Kebede

Primary Advisor's Department

Electrical and Computer Engineering and Electro-Optics


Stander Symposium poster


Arts and Humanities | Business | Education | Engineering | Life Sciences | Medicine and Health Sciences | Physical Sciences and Mathematics | Social and Behavioral Sciences