Lung Parenchymal Segmentation Algorithm Based on Improved Marker Watershed for Lung CT Images

Watershed algorithm is the basic method of digital image processing. and the most important segmentation technology. The lung CT images of human thoracic cross-section are segmented by watershed algorithm and edge detection in this paper. 400 CT images of human lung contour will be picked from Related data set to label artificially. Then the segmentation results are compared with those randomly selected labeled images to evaluate the performance using with Jaccard Index, dice coefficients and Correlation coefficients. At the same time, by comparing the accuracy between the image of lung segmentation and lung connection, the former reached to 99% and the latter is 98%. The real details can be preserved after segmentation by this segmentation.

[1]  Song-tao Liu,et al.  The Basic Principle and Its New Advances of Image Segmentation Methods Based on Graph Cuts , 2012 .

[2]  Kenji Suzuki,et al.  Radiologic classification of small adenocarcinoma of the lung: radiologic-pathologic correlation and its prognostic impact. , 2006, The Annals of thoracic surgery.

[3]  Ahmed M. Anter,et al.  Computational intelligence optimization approach based on particle swarm optimizer and neutrosophic set for abdominal CT liver tumor segmentation , 2018, J. Comput. Sci..

[4]  Yong Li,et al.  Improved U-NET network for pulmonary nodules segmentation , 2018, Optik.

[5]  Masumi Kadoya,et al.  Small solitary pulmonary nodules (< or =1 cm) detected at population-based CT screening for lung cancer: Reliable high-resolution CT features of benign lesions. , 2003, AJR. American journal of roentgenology.

[6]  K. Awai,et al.  Pulmonary nodules at chest CT: effect of computer-aided diagnosis on radiologists' detection performance. , 2004, Radiology.

[7]  Brahim Ait Skourt,et al.  Lung CT Image Segmentation Using Deep Neural Networks , 2018 .

[8]  D. R. Lewis,et al.  Early estimates of SEER cancer incidence, 2014 , 2017, Cancer.

[9]  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.

[10]  A. Jemal,et al.  Cancer Statistics, 2010 , 2010, CA: a cancer journal for clinicians.

[11]  C. Henschke.  Early lung cancer action project , 2000, Cancer.

[12]  Oscar Castillo,et al.  An improved sobel edge detection method based on generalized type-2 fuzzy logic , 2014, Soft Computing.

[13]  Jame Abraham,et al.  Reduced lung cancer mortality with low-dose computed tomographic screening , 2011 .

[14]  Emine Doganay,et al.  A robust lung segmentation algorithm using fuzzy C-means method from HRCT scans , 2016 .