MRI imaging texture features in prostate lesions classification

Conference paper
Part of the IFMBE Proceedings book series (IFMBE, volume 65)


Prostate cancer (PCa) is the most common diagnosed cancer and cause of cancer-related death among men. Computer Aided Diagnosis (CAD) systems are used to support radiologists in multiparametric Magnetic Resonance (mpMR) image-based analysis in order to avoid unnecessary biopsis and increase radiologist’s specificity. CAD systems have been reported in many papers for the last decade. The reported results have been obtained on small, private data sets and are impossible to reproduce or verify concluded remarks. PROSTATEx challenge organizers provided database that contains approximately 350 MRI cases, each from a distinct patient, allowing benchmarking of various CAD systems. This paper describes novel, deep learning based PCa CAD system that uses statistical central moments and Haralick features extracted from MR images, integrated with anamnestic data. Developed system has been trained on the dataset consisting of 330 lesions and evaluated on the challenge dataset using area under curve (AUC) related to estimated receiver operating characteristic (ROC). Two configurations of our method, based on statistical and Haralick features, scored 0.63 and 0.73 of AUC values. We draw conclusions from the challenge participation and discussed further improvements that could be made to the model to improve prostate classification.


magnetic resonance imaging computer aided diagnosis prostate cancer image texture analysis and recognition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Carroll Peter R., Parsons J. Kellogg, Andriole Gerald, et al. NCCN Guidelines Insights: Prostate Cancer Early Detection, Version 2.2016 Journal of the National Comprehensive Cancer Network. 2016;14:509-519Google Scholar
  2. 2.
    Weinreb Jeffrey C., Barentsz Jelle O., Choyke Peter L., et al. PI-RADS Prostate Imaging - Reporting and Data System: 2015, Version 2 European Urology. 2016;69:16–40Google Scholar
  3. 3.
    Shijun, Wang, Karen, Burtt, Baris, Turkbey, Peter, Choyke: Summers Ronald M. Computer Aided-Diagnosis of Prostate Cancer on Multiparametric MRI: A Technical Review of Current Research BioMed Research International. 2014, 789561 (2014)Google Scholar
  4. 4.
    Lemaitre Guillaume, Marti Robert, Freixenet Jordi, Vilanova Joan C., Walker Paul M., Meriaudeau Fabrice. Computer-Aided Detection and Diagnosis for prostate cancer based on mono and multi-parametric MRI: A Review Computers in Biology and Medicine. 2015Google Scholar
  5. 5.
    Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N., Huisman, H.: Computer-Aided Detection of Prostate Cancer in MRI IEEE Transactions on Medical Imaging. 33, 1083–1092 (2014)Google Scholar
  6. 6.
    Yahui, Peng, Yulei, Jiang, Cheng, Yang, et al.: Quantitative Analysis of Multiparametric Prostate MR Images: Differentiation between Prostate Cancer and Normal Tissue and Correlation with Gleason Score–A Computer-aided Diagnosis Development Study. Radiology. 267, 787–796 (2013)Google Scholar
  7. 7.
    Rampun Andrik, Chen Zhili, Malcolm Paul, Tiddeman Bernie, Zwiggelaar Reyer. Computer-aided diagnosis: detection and localization of prostate cancer within the peripheral zone International Journal for Numerical Methods in Biomedical Engineering. 2016;32:e02745–n/a. e02745 cnm.2745Google Scholar
  8. 8.
    Duc, Fehr, Harini, Veeraraghavan, Andreas, Wibmer, et al.: Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images Proceedings of the National Academy of Sciences. 112, E6265–E6273 (2015)Google Scholar
  9. 9.
    Andreas, Wibmer, Hedvig, Hricak, Tatsuo, Gondo, 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 European radiology. 25, 2840–2850 (2015)Google Scholar
  10. 10.
    Haralick R. M., Shanmugam K., Dinstein I.. Textural Features for Image Classification IEEE Transactions on Systems, Man, and Cybernetics. 1973;SMC-3:610-621Google Scholar
  11. 11.
    Arora Anisha, Candel Arno, Lanford Jessica, LeDell Erin, Parmar Viraj. Deep Learning with H2O H2O. ai. 2015Google Scholar
  12. 12.
    Alqahtani Khaled S, Srinivasan Shankar, Mital Dinesh P. Artificial neural network as classification method for prostate cancer incidence International Journal of Medical Engineering and Informatics. 2017;9:61–72Google Scholar
  13. 13.
    Lemaitre Guillaume, Rastgoo Mojdeh, Massich Joan, et al. Normalization of T2W-MRI prostate images using Rician a priori in SPIE Medical ImagingSPIE 2016Google Scholar
  14. 14.
    Anant, Madabhushi: Udupa Jayaram K., Souza Andre. Generalized scale: Theory, algorithms, and application to image inhomogeneity correction. Computer Vision and Image Understanding. 101, 100–121 (2006)Google Scholar
  15. 15.
    Styner, M., Brechbuhler, C., Szckely, G., Gerig, G.: Parametric estimate of intensity inhomogeneities applied to MRI IEEE Transactions on Medical Imaging. 19, 153–165 (2000)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Faculty of Mathematics and Information ScienceWarsaw University of TechnologyWarsawPoland
  2. 2.Information Processing CentrePolish Research InstituteWarsawPoland
  3. 3.Department of RadiologyCentral Clinical Hospital of the Ministry of the Interior and AdministrationWarsawPoland

Personalised recommendations