Texture feature extraction of gray-level co-occurrence matrix for metastatic cancer cells using scanned laser pico-projection images
- 180 Downloads
Metastasis is responsible for 90% of all cancer-related deaths in humans, and the development of a rapid and promising solution for an early diagnosis of metastasis is required. The present study proposed a promising method combined with scanned laser pico-projection technique and typical texture feature (i.e., contrast, correlation, energy, entropy, and homogeneity) extraction of gray-level co-occurrence matrix (GLCM) image processing model to classify the low- and high-metastatic cancer cells using five common cancer adenocarcinoma cell line pairs (i.e., HeLa/HeLa-S3, CL1-0/CL1-5, OVTW59-P0/OVTW59-P4, and CE81T-FNlow/CE81T-FNhigh cell lines). Highly metastatic cancer cells essentially have the highest levels of disorder. Both contrast and entropy refer to the degree of disorder, and energy and homogeneity refer to the degree of uniformity. These four texture features can be effective evaluation indexes for disorder in cancer cells responding to metastatic ability. Texture feature extraction forms reflection images, which are recorded with scanned laser pico-projection system; they effectively bridge the gap in information derived from transmission images. The low- and high-metastatic cancer cells are statistically and effectively classified from the texture feature of GLCM through transmission and reflection images taken with scanned laser pico-projection system. In particular, it only requires several seconds after producing a confluent monolayer of cells and achieves the rapid method with a more reliable diagnostic performance for metastatic ability of cancer cells in vitro or ex vivo.
KeywordsMetastasis Cancer cell Gray-level co-occurrence matrix Scanned laser pico-projection Image analysis
The authors gratefully acknowledge the financial support provided for this study by the Ministry of Science and Technology (MOST) in Taiwan under Grant No. MOST-106-2221-E-037-004. This study is also supported by a grant from the Kaohsiung Medical University Research Foundation (KMU-Q107023).
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
Approval by Ethical Commission is not needed.
Not applicable since there are no patients involved.
- 8.CT Lam, MS Krieger, JE Gallagher, B Asma, LC Muasher, JW Schmitt, et al., "Design of a novel low cost point of care tampon (POCkeT) colposcope for use in resource limited settings," PLoS ONE, vol. 10, p. e0135869, 09/02Google Scholar
- 10.M-J Lian, C-L Huang, and T.-M. Lee, "Automation characterization for oral cancer by pathological image processing with gray-level co-occurrence matrix," presented at the 5th International Conference on Mechanics and Mechatronics Research, Tokyo, 2018Google Scholar
- 12.R Haralick, K Shanmugam, and I H. Dinstein, Texture features for image classification vol. 3, 1975Google Scholar
- 18.Aslakson CJ, Miller FR (1992) Selective events in the metastatic process defined by analysis of the sequential dissemination of subpopulations of a mouse mammary tumor. Cancer Res 52:1399–1405Google Scholar