Performance Analysis of Convolution Neural Network with Different Architecture for Lung Segmentation

As lung cancer is one of the significant causes of death, there is a need for the development of algorithms for early detection of these cancers. Early detection of lung cancer helps to provide appropriate treatment and reduce morbidity. Accurate segmentation of the lung is an essential step in every computer-aided diagnosis (CAD) system to provide an accurate lung CT image analysis. This study is focused on the design of the appropriate architecture of the convolution neural network (CNN) using suitable combinations of CNN blocks to improve lung segmentation efficiency. Based on the scientific intuition, three CNN architectures are proposed for effective segmentation of lung parts from CT images. These CNN architectures are varied by the depth of down sampling of images as 32 × 32, 16 × 16 and 8 × 8. The performances of these CNN are obtained as under segmentation or over-segmentation by comparing the segmented lung part with ground truth lung images. This performance analysis shows the segmentation efficiency greatly affected by appropriate selection of downsampling of these images.

[1]  Jacek M. Zurada,et al.  Lung segmentation based on Nonnegative Matrix Factorization , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[2]  Fereidoun Abtin,et al.  Automatic segmentation of lung parenchyma in the presence of diseases based on curvature of ribs. , 2008, Academic radiology.

[3]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Huichuan Duan,et al.  3D computerized segmentation of lung volume with computed tomography. , 2006, Academic radiology.

[5]  Jason Cong,et al.  An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy , 2015, Comput. Biol. Medicine.

[6]  Jacek M. Zurada,et al.  3-D Lung Segmentation by Incremental Constrained Nonnegative Matrix Factorization , 2016, IEEE Transactions on Biomedical Engineering.

[7]  J W Sayre,et al.  Knowledge-based segmentation of thoracic computed tomography images for assessment of split lung function. , 2000, Medical physics.

[8]  Andrea Vedaldi,et al.  Instance Normalization: The Missing Ingredient for Fast Stylization , 2016, ArXiv.

[9]  Jamshid Dehmeshki,et al.  Shape-Based Computer-Aided Detection of Lung Nodules in Thoracic CT Images , 2009, IEEE Transactions on Biomedical Engineering.

[10]  Geoffrey D. Rubin,et al.  Adaptive border marching algorithm: Automatic lung segmentation on chest CT images , 2008, Comput. Medical Imaging Graph..

[11]  B. van Ginneken,et al.  Automatic lung segmentation from thoracic computed tomography scans using a hybrid approach with error detection. , 2009, Medical physics.

[12]  Michael F. McNitt-Gray,et al.  Method for segmenting chest CT image data using an anatomical model: preliminary results , 1997, IEEE Transactions on Medical Imaging.