Focal Liver Lesion Classification Based on Tensor Sparse Representations of Multi-phase CT Images
The bag-of-visual-words (BoVW) method has been proved to be an effective method for classification tasks in both natural imaging and medical imaging. In this paper, we propose a multilinear extension of the traditional BoVW method for classification of focal liver lesions using multi-phase CT images. In our approach, we form new volumes from the corresponding slices of multi-phase CT images and extract cubes from the volumes as local structures. Regard the high dimensional local structures as tensors, we propose a K-CP (CANDECOMP/PARAFAC) algorithm to learn a tensor dictionary in an iterative way. With the learned tensor dictionary, we can calculate sparse representations of each group of multi-phase CT images. The proposed tensor was evaluated in classification of focal liver lesions and achieved better results than conventional BoVW method.
KeywordsMulti-phase CT Tensor analysis Sparse coding Image classification Focal liver lesion
This research was supported in part by the Grant-in Aid for Scientific Research from the Japanese Ministry for Education, Science, Culture and Sports (MEXT) under the Grant No. 18H03267, and No. 18H04747, in part by the Key Science and Technology Innovation Support Program of Hangzhou under the Grant No.20172011A038, and in part by the National Key Basic Research Program of China under the Grant No. 2015CB352400.
- 2.Yu, M., Lu, Z., Feng, Q., Chen, W.: Liver CT image retrieval based on non-tensor product wavelet. In: International Conference on Medical Image Analysis and Clinical Applications (MIACA), pp. 67–70 (2010)Google Scholar
- 3.Duda, D., Kretowski, M., Bezy-Wendling, J.: Texture characterization for hepatic tumor recognition in multiphase CT. Biocybern. Biomed. Eng. 26(4), 15–24 (2006)Google Scholar
- 5.Xu, Y., et al.: Combined density, texture and shape features of multi-phase contrast-enhanced CT images for CBIR of focal liver lesions: a preliminary study. In: Chen, Y.-W., Toro, C., Tanaka, S., Howlett, R.J., Jain, L.C. (eds.) Innovation in Medicine and Healthcare 2015. SIST, vol. 45, pp. 215–224. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-23024-5_20CrossRefGoogle Scholar
- 9.Xu, Y., et al.: Bag of temporal co-occurrence words for retrieval of focal liver lesions using 3D multiphase contrast-enhanced CT images. In: 2016 23rd International Conference on Pattern Recognition (ICPR 2016) (2016)Google Scholar
- 12.Wang, J., et al.: Sparse codebook model of local structures for retrieval of focal liver lesions using multi-phase medical images. Int. J. Biomed. Imaging. vol. 2017, Article ID 1413297, 13 pages (2017)Google Scholar