Optical Flow Methods for Lung Nodule Segmentation on LIDC-IDRI Images
- PDF / 1,979,886 Bytes
- 19 Pages / 595.224 x 790.955 pts Page_size
- 37 Downloads / 163 Views
ORIGINAL PAPER
Optical Flow Methods for Lung Nodule Segmentation on LIDC-IDRI Images R. Jenkin Suji1 · Sarita Singh Bhadouria2 · Joydip Dhar1 · W. Wilfred Godfrey1
© Society for Imaging Informatics in Medicine 2020
Abstract Lung nodule segmentation is an essential step in any CAD system for lung cancer detection and diagnosis. Traditional approaches for image segmentation are mainly morphology based or intensity based. Motion-based segmentation techniques tend to use the temporal information along with the morphology and intensity information to perform segmentation of regions of interest in videos. CT scans comprise of a sequence of dicom 2-D image slices similar to videos which also comprise of a sequence of image frames ordered on a timeline. In this work, Farneback, Horn-Schunck and Lucas-Kanade optical flow methods have been used for processing the dicom slices. The novelty of this work lies in the usage of optical flow methods, generally used in motion-based segmentation tasks, for the segmentation of nodules from CT images. Since thin-sliced CT scans are the imaging modality considered, they closely approximate the motion videos and are the primary motivation for using optical flow for lung nodule segmentation. This paper also provides a detailed comparative analysis and validates the effectiveness of using optical flow methods for segmentation. Finally, we propose methods to further improve the efficiency of segmentation using optical flow methods on CT scans. Keywords Optical flow · Pulmonary nodule · Computed tomography · Segmentation
Introduction Pulmonary nodules are oval-shaped lesions that occur in the lung. These nodules, which are smaller than 3 mm in diameter, are generally non-cancerous and are benign, and when they grow beyond 3 mm in diameter, are called pulmonary mass, and they pose a risk to be cancerous [11]. Lung cancer is associated with one of the highest mortality rates among patients who have cancer. The primary reason R. Jenkin Suji
[email protected] Sarita Singh Bhadouria [email protected] Joydip Dhar [email protected] W. Wilfred Godfrey [email protected] 1
ABV-IIITM Gwalior, ABV-IIITM Campus, Morena Link Road, Gwalior, MadhyaPradesh 474010, India
2
RGPV Bhopal, Gandhi Nagar, MadhyaPradesh 462033, India
for this is the delayed diagnosis. Hence, there is a need for robust mechanisms for detecting lung cancer at the early stages.
Challenges to Lung Cancer Detection Detection of a lung nodule, segmentation and classification only based on simple morphological and textural properties such as size or texture or shape features is not robust as suggested by Paing et al. [38] and does not reveal the exact magnitude of the underlying challenges in lung cancer detection and diagnosis. Researchers have used various techniques for lung nodule detection and segmentation such as 3D tensor filtering with local image feature analysis [18], global optimal active contour model [54], corner seeded region growing combined with differential evolution based optimal thresholding [35],
Data Loading...
