GPU-accelerated Lung CT Segmentation Based on Level Sets and Texture Analysis

Overview

Journal Sci Rep

Specialty Science

Date 2024 Jan 16

PMID 38228773

Authors

Daniel Reska

Marek Kretowski

Affiliations

Soon will be listed here.

Abstract

This paper presents a novel semi-automatic method for lung segmentation in thoracic CT datasets. The fully three-dimensional algorithm is based on a level set representation of an active surface and integrates texture features to improve its robustness. The method's performance is enhanced by the graphics processing unit (GPU) acceleration. The segmentation process starts with a manual initialisation of 2D contours on a few representative slices of the analysed volume. Next, the starting regions for the active surface are generated according to the probability maps of texture features. The active surface is then evolved to give the final segmentation result. The recent implementation employs features based on grey-level co-occurrence matrices and Gabor filters. The algorithm was evaluated on real medical imaging data from the LCTCS 2017 challenge. The results were also compared with the outcomes of other segmentation methods. The proposed approach provided high segmentation accuracy while offering very competitive performance.

References

Mansoor A, Bagci U, Foster B, Xu Z, Papadakis G, Folio L . Segmentation and Image Analysis of Abnormal Lungs at CT: Current Approaches, Challenges, and Future Trends. Radiographics. 2015; 35(4):1056-76. PMC: 4521615. DOI: 10.1148/rg.2015140232. View

Smistad E, Falch T, Bozorgi M, Elster A, Lindseth F . Medical image segmentation on GPUs--a comprehensive review. Med Image Anal. 2014; 20(1):1-18. DOI: 10.1016/j.media.2014.10.012. View

Carvalho L, Sobieranski A, von Wangenheim A . 3D Segmentation Algorithms for Computerized Tomographic Imaging: a Systematic Literature Review. J Digit Imaging. 2018; 31(6):799-850. PMC: 6261188. DOI: 10.1007/s10278-018-0101-z. View

Tesar L, Shimizu A, Smutek D, Kobatake H, Nawano S . Medical image analysis of 3D CT images based on extension of Haralick texture features. Comput Med Imaging Graph. 2008; 32(6):513-20. DOI: 10.1016/j.compmedimag.2008.05.005. View

Shi F, Wang J, Shi J, Wu Z, Wang Q, Tang Z . Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation, and Diagnosis for COVID-19. IEEE Rev Biomed Eng. 2020; 14:4-15. DOI: 10.1109/RBME.2020.2987975. View

Fan D, Zhou T, Ji G, Zhou Y, Chen G, Fu H . Inf-Net: Automatic COVID-19 Lung Infection Segmentation From CT Images. IEEE Trans Med Imaging. 2020; 39(8):2626-2637. DOI: 10.1109/TMI.2020.2996645. View

Ma J, Nie Z, Wang C, Dong G, Zhu Q, He J . Active contour regularized semi-supervised learning for COVID-19 CT infection segmentation with limited annotations. Phys Med Biol. 2020; 65(22):225034. DOI: 10.1088/1361-6560/abc04e. View

Hu S, Hoffman E, Reinhardt J . Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Trans Med Imaging. 2001; 20(6):490-8. DOI: 10.1109/42.929615. View

Zhang L, Hoffman E, Reinhardt J . Atlas-driven lung lobe segmentation in volumetric X-ray CT images. IEEE Trans Med Imaging. 2006; 25(1):1-16. DOI: 10.1109/TMI.2005.859209. View

10.

Oliveira B, Queiros S, Morais P, Torres H, Gomes-Fonseca J, Fonseca J . A novel multi-atlas strategy with dense deformation field reconstruction for abdominal and thoracic multi-organ segmentation from computed tomography. Med Image Anal. 2018; 45:108-120. DOI: 10.1016/j.media.2018.02.001. View

11.

Yang J, Veeraraghavan H, Armato 3rd S, Farahani K, Kirby J, Kalpathy-Kramer J . Autosegmentation for thoracic radiation treatment planning: A grand challenge at AAPM 2017. Med Phys. 2018; 45(10):4568-4581. PMC: 6714977. DOI: 10.1002/mp.13141. View

12.

Farag A, Abd El Munim H, Graham J, Farag A . A novel approach for lung nodules segmentation in chest CT using level sets. IEEE Trans Image Process. 2013; 22(12):5202-13. DOI: 10.1109/TIP.2013.2282899. View

13.

Swierczynski P, Papiez B, Schnabel J, Macdonald C . A level-set approach to joint image segmentation and registration with application to CT lung imaging. Comput Med Imaging Graph. 2017; 65:58-68. PMC: 5885990. DOI: 10.1016/j.compmedimag.2017.06.003. View

14.

Filho P, Cortez P, da Silva Barros A, Albuquerque V, R S Tavares J . Novel and powerful 3D adaptive crisp active contour method applied in the segmentation of CT lung images. Med Image Anal. 2016; 35:503-516. DOI: 10.1016/j.media.2016.09.002. View

15.

Carmo D, Ribeiro J, Dertkigil S, Appenzeller S, Lotufo R, Rittner L . A Systematic Review of Automated Segmentation Methods and Public Datasets for the Lung and its Lobes and Findings on Computed Tomography Images. Yearb Med Inform. 2022; 31(1):277-295. PMC: 9719778. DOI: 10.1055/s-0042-1742517. View

16.

Shariaty F, Orooji M, Velichko E, Zavjalov S . Texture appearance model, a new model-based segmentation paradigm, application on the segmentation of lung nodule in the CT scan of the chest. Comput Biol Med. 2021; 140:105086. DOI: 10.1016/j.compbiomed.2021.105086. View

17.

Hoffman E, Reinhardt J, Sonka M, Simon B, Guo J, Saba O . Characterization of the interstitial lung diseases via density-based and texture-based analysis of computed tomography images of lung structure and function. Acad Radiol. 2003; 10(10):1104-18. DOI: 10.1016/s1076-6332(03)00330-1. View

18.

de Carvalho Brito V, Dos Santos P, de Sales Carvalho N, de Carvalho Filho A . COVID-index: A texture-based approach to classifying lung lesions based on CT images. Pattern Recognit. 2021; 119:108083. PMC: 8180348. DOI: 10.1016/j.patcog.2021.108083. View

19.

Clark K, Vendt B, Smith K, Freymann J, Kirby J, Koppel P . The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging. 2013; 26(6):1045-57. PMC: 3824915. DOI: 10.1007/s10278-013-9622-7. View

20.

Stone J, Gohara D, Shi G . OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems. Comput Sci Eng. 2010; 12(3):66-72. PMC: 2964860. DOI: 10.1109/MCSE.2010.69. View