An identification methods of under-segmented regions in segmented lung mask

Haiyan Wei; Changli Feng; Xin Li; Zhaogui Ma; Deyun Yang

doi:10.1117/12.2557234

Translator Disclaimer

3 January 2020 An identification methods of under-segmented regions in segmented lung mask

Haiyan Wei, Changli Feng, Xin Li, Zhaogui Ma, Deyun Yang

Author Affiliations +

Proceedings Volume 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019); 1137309 (2020) https://doi.org/10.1117/12.2557234
Event: Eleventh International Conference on Graphics and Image Processing, 2019, Hangzhou, China

Abstract

The Juxtapleural nodule regions are often missed in the result of lung segmentation algorithms. To tackle this problem, an identification method basing on the SIFT information and elliptic Fourier descriptor is proposed. Firstly, the SIFT information is used to locate the position of key points in the lung mask. Then with the help of distance relationship, the support borderlines of key points are calculated. Thirdly, the elliptic Fourier descriptor is introduced to describe a support line. Finally, an adaptive threshold is designed to decide whether the current support line is corresponding to an under-segmented region. Experiments on real CT images demonstrate that the proposed model provides an efficient way to perform under-segmented region identification task.

Citation Download Citation

Haiyan Wei, Changli Feng, Xin Li, Zhaogui Ma, and Deyun Yang "An identification methods of under-segmented regions in segmented lung mask", Proc. SPIE 11373, Eleventh International Conference on Graphics and Image Processing (ICGIP 2019), 1137309 (3 January 2020); https://doi.org/10.1117/12.2557234

ACCESS THE FULL ARTICLE