A Novel Multilevel Hybrid Segmentation and Refinement Method for Automatic Heterogeneous True NSCLC Nodules Extraction

The experts 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 of huge analyzing time, observer error, etc. Developing an efficient automatic Computer Aided Detection (CAD) system is essential to reduce the frequency of missed lung cancer nodules, 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 four steps: (1) Preprocessing, (2) Automatic Lung Parenchyma Extraction and Border Repair (ALPE&BR), (3) Automatic lung nodules segmentation using Connected Component Analysis (CCA) and Threshold BasedMathematical Nodule (TBMN) refinement algorithm and (4) Nodules filtering using Hounsfield Unit (HU) value and true cancerous nodule extraction. The ALPE&BR method consists of Automatic Single Seeded Region Growing (ASSRG) algorithm for automatic lung parenchyma extraction and novel hybrid 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 99.41%, SP of 99.97%, FPR of 0.019%, DSC of 0.98, and accuracy of 99.97%. These results are used to demonstrate that the proposed method outperforms the existing lung nodule segmentation method.

[1]  Ezhil E. Nithila,et al.  Segmentation of lung nodule in CT data using active contour model and Fuzzy C-mean clustering , 2016 .

[2]  Caroline Dive,et al.  Progress and prospects of early detection in lung cancer , 2017, Open Biology.

[3]  Yan Qiang,et al.  An automated pulmonary parenchyma segmentation method based on an improved region growing algorithmin PET-CT imaging , 2015, Frontiers of Computer Science.

[4]  Yifei Zhang,et al.  A novel approach of lung segmentation on chest CT images using graph cuts , 2015, Neurocomputing.

[5]  Joseph M. Reinhardt,et al.  Anatomy-Guided Lung Lobe Segmentation in X-Ray CT Images , 2009, IEEE Transactions on Medical Imaging.

[6]  M. Rajasekar,et al.  Identification of Lung Cancer Cell using Watershed Segmentation on CT Images , 2016 .

[7]  Nishat Khan,et al.  REVIEW ON LUNG CANCER DETECTION USING IMAGE PROCESSING TECHNIQUE , 2016 .

[8]  David Gur,et al.  A Computational Geometry Approach to Automated Pulmonary Fissure Segmentation in CT Examinations , 2009, IEEE Transactions on Medical Imaging.

[9]  Preprocessing on Digital Image using Histogram Equalization : An Experiment Study on MRI Brain Image , 2016 .

[10]  B Sasidhar,et al.  Automated Segmentation of Lung Regions using Morphological Operators in CT scan , 2013 .

[11]  N. Anupama,et al.  Automated Detection and Classification of Cancerous Lung Nodule using Level Set Segmentation and ANN , 2017 .

[12]  Geoffrey D Rubin,et al.  Lung Nodule and Cancer Detection in Computed Tomography Screening , 2015, Journal of thoracic imaging.

[13]  Sanjay Talbar,et al.  Deep Deconvolutional Residual Network Based Automatic Lung Nodule Segmentation , 2020, Journal of Digital Imaging.

[14]  Wei Shen,et al.  Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification , 2017, Pattern Recognit..

[15]  Christopher Nimsky,et al.  Vertebral body segmentation with GrowCut: Initial experience, workflow and practical application , 2017, SAGE open medicine.

[16]  A. Madabhushi,et al.  An integrated segmentation and shape‐based classification scheme for distinguishing adenocarcinomas from granulomas on lung CT , 2017, Medical physics.

[17]  Richard C. Pais,et al.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. , 2011, Medical physics.

[18]  Lianfang Tian,et al.  Automatic benign and malignant classification of pulmonary nodules in thoracic computed tomography based on RF algorithm , 2018, IET Image Process..

[19]  A. Jemal,et al.  Cancer statistics, 2017 , 2017, CA: a cancer journal for clinicians.

[20]  A. Brintha Therese,et al.  Detection of Cancer in Lung with K-NN Classification Using Genetic Algorithm , 2015 .

[21]  Lorenzo Bonomo,et al.  Missed lung cancer: when, where, and why? , 2017, Diagnostic and interventional radiology.

[22]  Nourhan Zayed,et al.  Automatic Classification of Normal and Cancer Lung CT Images Using Multiscale AM-FM Features , 2015, Int. J. Biomed. Imaging.

[23]  He Ma,et al.  An Automatic Detection System of Lung Nodule Based on Multigroup Patch-Based Deep Learning Network , 2018, IEEE Journal of Biomedical and Health Informatics.

[24]  P. Mildenberger,et al.  Introduction to the DICOM standard , 2002, European Radiology.

[25]  Chunming Li,et al.  A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI , 2011, IEEE Transactions on Image Processing.

[26]  Hoon Ko,et al.  Automatic Lung Segmentation With Juxta-Pleural Nodule Identification Using Active Contour Model and Bayesian Approach , 2018, IEEE Journal of Translational Engineering in Health and Medicine.