Preprint Article Version 1 This version is not peer-reviewed

3-D Segmentation of Lung Nodules Using Hybrid Levelsets

Version 1 : Received: 4 April 2019 / Approved: 5 April 2019 / Online: 5 April 2019 (15:36:24 CEST)

A peer-reviewed article of this Preprint also exists.

Shakir, H.; Khan, T.M.R.; Rasheed, H. 3-D segmentation of lung nodules using hybrid level sets. Computers in Biology and Medicine 2018, 96, 214-226. Shakir, H.; Khan, T.M.R.; Rasheed, H. 3-D segmentation of lung nodules using hybrid level sets. Computers in Biology and Medicine 2018, 96, 214-226.

Journal reference: Elsevier Computers in Biology and Medicine 2018
DOI: 10.1016/j.compbiomed.2018.03.015

Abstract

Lung nodule segmentation in CT images and its subsequent volume analysis can help determinethe malignancy status of a lung nodule. While several efficient segmentation schemes have beenproposed, only a few studies evaluated the segmentation’s performance for large nodules. In thisresearch, we contribute a semi-automatic system which is capable of performing robust 3-D segmen-tations on both small and large nodules with good accuracy. The target CT volume is de-noisedwith an anisotropic diffusion filter and a region of interest is selected around the target nodule ona reference slice. The proposed model performs nodule segmentation by incorporating a mean in-tensity based threshold in Geodesic Active Contour model in level sets. We also devise an adaptivetechnique using image intensity histogram to estimate the desired mean intensity of the nodule.The proposed system is validated on both lung nodules and phantoms collected from publicly avail-able diverse databases. Quantitative and visual comparative analysis of the proposed work withthe Chan-Vese algorithm and statistic active contour model of 3D Slicer platform is also presented.The resulting mean spatial overlap between segmented nodules and reference nodules is 0.855, themean volume bias is 0.10±0.2 ml and the algorithm repeatability is 0.060 ml. The achieved resultssuggest that the proposed method can be used for volume estimations of small as well as large-sizednodules.

Subject Areas

hybrid level-sets, active contours, nodule segmentation, hybrid deformable model

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.