Multi-layer cube sampling for liver boundary detection in PET–CT images
- 51 Downloads
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.
KeywordsBoundary detection Multi-layer PET–CT Feature extraction Classification
We are very grateful to Dr. Li Huo from the Peking Union Medical College Hospital for providing the datasets used in this paper.
This work was supported by the National Key R&D Program of China (2017YFC0112000), and the National Science Foundation Program of China (61672099, 81627803, 61501030, 61527827).
Compliance with Ethical Standards
Conflict of interest
The authors declare that they have no competing interests.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study.
- 2.Akkasaligar PT, Biradar S (2014) Classification of medical ultrasound images of kidney. Int J Comput Appl 3:24–28Google Scholar
- 3.Li GZ, Yang J, Liu GP, Xue L (2004) Feature selection for multi-class problems using support vector machines. In Pacific Rim International Conference on Artificial Intelligence, vol 3157. Springer, Berlin, pp 292–300Google Scholar
- 4.Adegoke BO (2014) Review of feature selection methods in medical image processing. Iosrjen Org 4(1):01–05Google Scholar
- 6.Gadkari D (2004) Image quality analysis using GLCM. University of Central Florida, OrlandoGoogle Scholar
- 8.Zulpe NS, Pawar VP (2012) GLCM textural features for brain tumor classification. Int J Comput Sci Issues 9(3), 354–359Google Scholar
- 11.Nosrati M, Karimi R, Hariri M, Malekian K (2013) Edge detection techniques in processing digital images: investigation of canny algorithm and gabor method. World Appl Program 3(3):116–121.Google Scholar
- 16.Yang X, Rossi PJ, Jani AB, Mao H, Curran WJ, Liu T (2016) 3D Transrectal Ultrasound (TRUS) prostate segmentation based on optimal feature learning framework. In: Medical Imaging 2016: Image Processing. International Society for Optics and Photonics, p 97842FGoogle Scholar
- 20.Zhang Z, Lyons M, Schuster M, Akamatsu S (1998) Comparison between geometry-based and gabor-wavelets-based facial expression recognition using multi-layer perceptron. In: Proceedings of IEEE international conference on automatic face and gesture recognition, pp 454–459, 1998Google Scholar
- 21.Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:14091556Google Scholar