A Novel Hybrid Segmentation and Refinement Method for Automatic Lung Cancerous Nodules Extraction
P. Samundeeswari1, R. Gunasundari2
1P. Samundeeswari, Research Scholar, Department of Electronics and Communication Engineering, Pondicherry Engineering College, Puducherry (Tamil Nadu), India.
2Dr. R. Gunasundari, Professor, Department of Electronics and Communication Engineering, Pondicherry Engineering College, Puducherry (Tamil Nadu), India.
Manuscript received on 24 March 2019 | Revised Manuscript received on 03 April 2019 | Manuscript Published on 27 April 2019 | PP: 28-35 | Volume-7 Issue-6S2 April 2019 | Retrieval Number: F10060476S219/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The doctors uses chest Computed Tomography (CT) images to manually analyze the presence of cancerous nodule during cancer screening process. Due to heterogeneous and low intensity nature of CT image, manual image analyzing becomes difficult which leads to different problems like false positive detection, consumption huge analyzing time, observer error, etc. Developing an efficient automatic Computer Aided Detection (CAD) system is the most efficient approach to reduce the frequency of missed lung cancer and to make diagnosis simpler and time saving. The CAD system improves the accuracy of lung tumor detection and survival rate of the patient. In this paper, a fully automated model is presented for NSCLC nodule(s) segmentation from CT scan image. The proposed method follows three steps: (1) Preprocessing, (2) Automatic Lung Parenchyma Extraction and Border Repair (ALPE&BR) and (3) Automatic lung nodules segmentation using Connected Component Analysis (CCA) and Threshold Based Mathematical Nodule (TBMN) refinement algorithm. The ALPE&BR method consists of Automatic Single Seeded Region Growing (ASSRG) Algorithm for automatic lung parenchyma extraction and novel border concavity closing algorithm to get clear lung boundary. The proposed method successfully segments the true cancerous nodules by filtering out false region such as vessels, bone, fat, soft tissues, etc. The proposed method can provide the SN of 99.4%, SP of 98.5%, FPR of 0.6%, DSC of 0.982 and accuracy of 98.8%. These results are used to demonstrate that the proposed method outperforms the existing lung nodule segmentation method.
Keywords: Contrast Limited Adaptive Histogram Equalization, Lung CT Image, Automatic Lung Cancer Nodule Segmentation, Wiener Filter, Grow Cut Algorithm, Border Concavity Closing, Automatic Single Seeded Region Growing Algorithm.
Scope of the Article: Probabilistic Models and Methods