SIGNIFICANT FEATURES TO DETECT PULMONARY NODULES FROM CT LUNG IMAGES

Lung cancer causes the most number of deaths worldwide in both men and women. Early detection and diagnosis can minimize the disease mortality rate. Commonly, chest computed tomography (CT) scans are used by clinicians to diagnose lung cancer. The lung cancer diagnosis relies on detection of the pulmonary nodules in CT scans. In this paper, we propose computer-aided diagnostic systems that can define and suggest the most important features that can distinguish lung nodule from nonnodule one. The proposed system can be described through the following six steps: (a) Patch Extraction, (b) Image Preprocessing, (c) Feature Extraction, (d) Normalization, (e) Feature Reduction, and (f) Patch Classification. Feature extraction and selection are the most important steps in any disease classification process. A combination of 132 texture features with three shape-based features has been extracted. Then the normalization step has been done using min–max method followed by the feature reduction step based on the wrap...

[1]  Yasser M. Kadah,et al.  Robust Computer-Aided Detection of Pulmonary Nodules from Chest Computed Tomography , 2016 .

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

[3]  Aimin Hao,et al.  A CADe system for nodule detection in thoracic CT images based on artificial neural network , 2017, Science China Information Sciences.

[4]  Pawel Badura,et al.  Soft computing approach to 3D lung nodule segmentation in CT , 2014, Comput. Biol. Medicine.

[5]  David A Clausi.  An analysis of co-occurrence texture statistics as a function of grey level quantization , 2002 .

[6]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[7]  Ayman El-Baz,et al.  Computer-Aided Diagnosis Systems for Lung Cancer: Challenges and Methodologies , 2013, Int. J. Biomed. Imaging.

[8]  Xiaoou Tang,et al.  Texture information in run-length matrices , 1998, IEEE Trans. Image Process..

[9]  Leen-Kiat Soh,et al.  Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices , 1999, IEEE Trans. Geosci. Remote. Sens..

[10]  Tae-Sun Choi,et al.  Automated pulmonary nodule detection based on three-dimensional shape-based feature descriptor , 2014, Comput. Methods Programs Biomed..

[11]  M. Masotti,et al.  Computer-aided detection of lung nodules via 3D fast radial transform, scale space representation, and Zernike MIP classification. , 2011, Medical physics.

[12]  Anselmo Cardoso de Paiva,et al.  Automatic detection of small lung nodules in 3D CT data using Gaussian mixture models, Tsallis entropy and SVM , 2014, Eng. Appl. Artif. Intell..

[13]  Edwin Arnold,et al.  Chronic suprapubic catheterization in the management of patients with spinal cord injuries: analysis of upper and lower urinary tract complications , 2008, BJU International.

[14]  Hamid Soltanian-Zadeh,et al.  Fast opposite weight learning rules with application in breast cancer diagnosis , 2013, Comput. Biol. Medicine.

[15]  F. Agakov,et al.  Application of high-dimensional feature selection: evaluation for genomic prediction in man , 2015, Scientific Reports.

[16]  João Manuel R. S. Tavares,et al.  Automatic 3D pulmonary nodule detection in CT images: A survey , 2016, Comput. Methods Programs Biomed..

[17]  Shahriar B. Shokouhi,et al.  Classification of benign and malignant masses based on Zernike moments , 2011, Comput. Biol. Medicine.