Automatic detection and segmentation of blood vessels and pulmonary nodules based on a line tracking method and generalized linear regression model
- 125 Downloads
Initial candidate segmentation is an important task in lung nodule detection. If an accurate segmentation is used, the false positives (FPs) can be decreased in subsequent stages and the desired region of each candidate can be distinguished. In this paper, a new hybrid method for nodule candidate segmentation and FPs reduction is proposed. First, the images are transferred to the neutrosophic domain. Then, three filters, named blob-like structure enhancement (BSE), line structure enhancement (LSE), and central adaptive medialness (CAM) filters, are used for filtering the output of the last step. Afterward, the outputs of BSE, LSE, and CAM filters are used for initial candidate detection and candidate segmentation, respectively. Also, line tracking method is proposed for extending the candidate voxels, and then, it is used for candidate segmentation. After feature extraction, the sparse coding is used for learning feature vector. In the last step, the generalized linear regression model (GLRM) is used for classification. The output of classifier for sensitivity and FP/scan is 98.32% and 2.8, respectively. AUC values of different link functions in GLRM, before and after feature learning, were also calculated, and the best value of AUC was obtained with probit link function after using the sparse coding method. The experimental results demonstrate the power of the proposed algorithm in nodules detection and false positive reduction.
KeywordsImage processing Nodule segmentation Blood vessels segmentation Pulmonary nodule detection Line tracking Generalized linear regression model
This work was supported by the Shahid Chamran University of Ahvaz under Grant Number 97/3/02/26247.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
This article does not contain patient data.
- 1.Siegel, R., Jemal, A.: Cancer Facts and Figures 2017. American Cancer Society, Atlanta (2017)Google Scholar
- 3.Taghavi Namin, S., Abrishami Moghaddam, H., Jafari, R., Esmaeil-Zadeh, M., Gity, M.: Automated detection and classification of pulmonary nodules in 3D thoracic CT images. In: 2010 IEEE International Conference on Systems Man and Cybernetics (SMC), 2010, pp. 3774–3779. IEEEGoogle Scholar
- 6.Chen, B., Kitasaka, T., Honma, H., Takabatake, H., Mori, M., Natori, H., Mori, K.: Automatic segmentation of pulmonary blood vessels and nodules based on local intensity structure analysis and surface propagation in 3D chest CT images. Int. J. Comput. Assist. Radiol. Surg. 7(3), 465–482 (2012)CrossRefGoogle Scholar
- 11.Huidrom, R., Chanu, Y.J., Singh, K.M.: Pulmonary nodule detection on computed tomography using neuro-evolutionary scheme. Signal Image Video Process. 1–8 (2018). https://doi.org/10.1007/s11760-018-1327-4
- 16.Armato, S.G., McLennan, G., Bidaut, L., McNitt-Gray, M.F., Meyer, C.R., Reeves, A.P., Zhao, B., Aberle, D.R., Henschke, C.I., Hoffman, E.A.: The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med. Phys. 38(2), 915–931 (2011)CrossRefGoogle Scholar
- 19.Tahmasbi, A., Saki, F., Aghapanah, H., Shokouhi, S.B.: A novel breast mass diagnosis system based on Zernike moments as shape and density descriptors. In: 2011 18th Iranian Conference of Biomedical Engineering (ICBME), 2011, pp. 100–104. IEEEGoogle Scholar
- 22.Nelder, J.A., Baker, R.J.: Generalized Linear Models. Wiley Online Library (1972)Google Scholar
- 24.Horeweg, N., van Rosmalen, J., Heuvelmans, M.A., van der Aalst, C.M., Vliegenthart, R., Scholten, E.T., Groen, H.J.: Lung cancer probability in patients with CT-detected pulmonary nodules: a prespecified analysis of data from the NELSON trial of low-dose CT screening. Lancet Oncol. 15(12), 1332–1341 (2014)CrossRefGoogle Scholar