False positives reduction in pulmonary nodule detection using a connected component analysis-based approach. (11th July 2022)

• Record Type: Journal Article
• Authors: Sahu, Satya Prakash; Londhe, Narendra D.; Verma, Shrish; Agrawal, Priyanka; Banchhor, Sumit K.
• Is Part Of: International journal of biomedical engineering and technology. Volume 39:Number 2(2022)
• Page Start: 131
• Page End: 148
• Publication Date: 2022-07-11
• Subjects: K-means -- multi-thresholding -- connected component analysis -- CCA -- sensitivity -- false positives; Biomedical engineering -- Periodicals; 610.28
• Languages: English
• ISSNs: 1752-6418

Abstract

In this paper, we have proposed a connected component analysis (CCA)-based approach for reducing the false positives rate (FPR) per scan in the early detection of pulmonary lung nodules using computed tomography (CT) images. The lung CT scans were obtained from the lung image database consortium – image database resource initiative database. Proposed study consists of four stages: 1) segmentation of lung parenchyma through K-means clustering algorithm; 2) nodule extraction using an automated threshold-based approach (Santos); 3) noise removal using CCA-based approach; 4) detection of lung nodule by using the sphericity (roundness) feature. The results were validated against the annotated ground truth provided by four expert radiologists. The study showed a reduced FPs/scan rate of 0.76 with an overall accuracy of 84.03%. The proposed well-balanced system showed a reduction in the FPR while maintaining high accuracy in lung nodule detection and thus can be usable in clinical settings.