Display options
Cite
Liu X, Yang J, Song S, et al. Multi-layer cube sampling for liver boundary detection in PET-CT images. Australas Phys Eng Sci Med. 2018;41(2):495-505doi: 10.1007/s13246-018-0650-y.
Liu, X., Yang, J., Song, S., Song, H., Ai, D., Zhu, J., Jiang, Y., & Wang, Y. (2018). Multi-layer cube sampling for liver boundary detection in PET-CT images. Australasian physical & engineering sciences in medicine, 41(2), 495-505. https://doi.org/10.1007/s13246-018-0650-y
Liu, Xinxin, et al. "Multi-layer cube sampling for liver boundary detection in PET-CT images." Australasian physical & engineering sciences in medicine vol. 41,2 (2018): 495-505. doi: https://doi.org/10.1007/s13246-018-0650-y
Liu X, Yang J, Song S, Song H, Ai D, Zhu J, Jiang Y, Wang Y. Multi-layer cube sampling for liver boundary detection in PET-CT images. Australas Phys Eng Sci Med. 2018 Jun;41(2):495-505. doi: 10.1007/s13246-018-0650-y. Epub 2018 May 17. PMID: 29774460.
Copy Download .nbib Format: NLM
Share it on

Australas Phys Eng Sci Med. 2018 Jun;41(2):495-505. doi: 10.1007/s13246-018-0650-y. Epub 2018 May 17.

Multi-layer cube sampling for liver boundary detection in PET-CT images.

Australasian physical & engineering sciences in medicine

Xinxin Liu, Jian Yang, Shuang Song, Hong Song, Danni Ai, Jianjun Zhu, Yurong Jiang, Yongtian Wang

Affiliations

  1. Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Electronics, Beijing Institute of Technology, Beijing, 100081, China.
  2. Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Electronics, Beijing Institute of Technology, Beijing, 100081, China. [email protected].
  3. School of Software, Beijing Institute of Technology, Beijing, 100081, China.
  4. Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Electronics, Beijing Institute of Technology, Beijing, 100081, China. [email protected].

PMID: 29774460 DOI: 10.1007/s13246-018-0650-y

Abstract

Liver metabolic information is considered as a crucial diagnostic marker for the diagnosis of fever of unknown origin, and liver recognition is the basis of automatic diagnosis of metabolic information extraction. However, the poor quality of PET and CT images is a challenge for information extraction and target recognition in PET-CT images. The existing detection method cannot meet the requirement of liver recognition in PET-CT images, which is the key problem in the big data analysis of PET-CT images. A novel texture feature descriptor called multi-layer cube sampling (MLCS) is developed for liver boundary detection in low-dose CT and PET images. The cube sampling feature is proposed for extracting more texture information, which uses a bi-centric voxel strategy. Neighbour voxels are divided into three regions by the centre voxel and the reference voxel in the histogram, and the voxel distribution information is statistically classified as texture feature. Multi-layer texture features are also used to improve the ability and adaptability of target recognition in volume data. The proposed feature is tested on the PET and CT images for liver boundary detection. For the liver in the volume data, mean detection rate (DR) and mean error rate (ER) reached 95.15 and 7.81% in low-quality PET images, and 83.10 and 21.08% in low-contrast CT images. The experimental results demonstrated that the proposed method is effective and robust for liver boundary detection.

Keywords: Boundary detection; Classification; Feature extraction; Multi-layer; PET–CT

MeSH terms

Publication Types

Grant support