Using machine learning and texture analysis to predict significant and nonsignificant prostate lesions

Abdullah S. Mirza, Yazeed Alsulaiman, Metab A. Alkubeyyer

Abstract


Introduction: Prostate cancer is a well-recognized medical problem accounting for the most diagnosed type of cancer in men. The importance of early detection and its improved survival rate have motivated research on the best cancer detection method. Consequently, computer-aided diagnosis was introduced; however, more datasets are needed, and more testing and trials are required to reach a feasible and reliable diagnostic method. In this study, we use MRI T2 WI and ADC-map sequences to build a classifier to differentiate between clinically significant and insignificant prostate lesions. Material and Methods: Haralick’s first and second order statistical features were extracted from pathologically proven prostate lesions found in The Cancer Imaging Archive open data source. We used the WEKA platform for data analysis, including 152 lesions divided into 70% training set and 30% testing set. Results: The proposed classifier showed sensitivity, specificity, F-measure, and AUROC of 82.6%, 87%, 84.4%, and 92.6%, respectively. Conclusions: The proposed classifier does not require a high-end computer, outperforms many previous classifiers, and has the potential to discriminate clinically significant from insignificant prostate lesions.


Keywords


prostate; machine learning; AI; cancer; prediction

Full Text:

PDF

References


Canadian Cancer Statistics Advisory Committee 2020. Prostate cancer statistics. [online] Canadian Cancer Society. Available at: .

American Cancer Society. Cancer Facts & Figures 2020. Atlanta: American Cancer Society; 2020.

Giger ML, Chan HP, Boone J. Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM. Med Phys. 2008;35(12):5799–5820. doi:10.1118/1.3013555.

Wang S, Burtt K, Turkbey B, Choyke P, Summers RM. Computer aided-diagnosis of prostate cancer on multiparametric MRI: a technical review of current research. Biomed Res Int. 2014;2014:789561. doi:10.1155/2014/789561

Lemaître G, Martí R, Freixenet J, Vilanova JC, Walker PM, Meriaudeau F. Computer-Aided Detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review. Comput Biol Med. 2015;60:8–31. doi:10.1016/j.compbiomed.2015.02.009

Wibmer A, Hricak H, Gondo T, et al. Haralick texture analysis of prostate MRI: utility for differentiating non-cancerous prostate from prostate cancer and differentiating prostate cancers with different Gleason scores. Eur Radiol. 2015;25(10):2840–2850. doi:10.1007/s00330-015-3701-8

Niaf E, Rouvière O, Mège-Lechevallier F, Bratan F, Lartizien C. Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI. Phys Med Biol. 2012;57(12):3833–3851. doi:10.1088/0031-9155/57/12/3833

3. Haralick R. Statistical and structural approaches to texture. Proceedings of the IEEE. 1979;67(5):786–804. doi:10.1109/proc.1979.11328

Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging. 2013;26(6):1045–1057. doi:10.1007/s10278-013-9622-7

Geert Litjens, Oscar Debats, Jelle Barentsz, Nico Karssemeijer, and Henkjan Huisman. "ProstateX Challenge data", The Cancer Imaging Archive (2017). DOI: 10.7937/K9TCIA.2017.MURS5CL

Litjens G, Debats O, Barentsz J, Karssemeijer N, Huisman H. Computer-aided detection of prostate cancer in MRI. IEEE Trans Med Imaging. 2014;33(5):1083–1092. doi:10.1109/TMI.2014.2303821

Haralick R, Shanmugam K, Dinstein I. Textural Features for Image Classification. IEEE Trans Syst Man Cybern. 1973;SMC-3(6):610–621. doi:10.1109/tsmc.1973.4309314

Schindelin J, Arganda-Carreras I, Frise E, et al. Fiji: an open-source platform for biological-image analysis. Nat Methods. 2012;9(7):676–682. Published 2012 Jun 28. doi:10.1038/nmeth.2019.

Schneider CA, Rasband WS, Eliceiri KW. NIH Image to ImageJ: 25 years of image analysis. Nat Methods. 2012;9(7):671–675. doi:10.1038/nmeth.2089.

Hall M, et al. Correlation-based feature selection for machine learning, PhD Thesis, 1999 New Zealand Department of Computer Science, Waikato University.

Eibe Witten, I. H., Frank, E., Hall, M. A., Pal, C. J., & DATA, M. (2005, June). Practical machine learning tools and techniques. In Data Mining (Vol. 2, No. 4).

Armato SG 3rd, Huisman H, Drukker K, et al. PROSTATEx Challenges for computerized classification of prostate lesions from multiparametric magnetic resonance images. J Med Imaging (Bellingham). 2018;5(4):044501. doi:10.1117/1.JMI.5.4.044501.




DOI: https://doi.org/10.15408/avicenna.v4i1.31560 Abstract - 0 PDF - 0

Refbacks



Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

 

View My Stats

 

Â