Ensemble of Convolutional Neural Networks for the Detection of Prostate Cancer in Multi-parametric MRI Scans

  • Quang H. NguyenEmail author
  • Mengnan Gong
  • Tao Liu
  • Ou Yang Youheng
  • Binh P. Nguyen
  • Matthew Chin Heng Chua
Part of the Studies in Computational Intelligence book series (SCI, volume 899)


Prostate MP-MRI scan is a non-invasive method of detecting early stage prostate cancer which is increasing in popularity. However, this imaging modality requires highly skilled radiologists to interpret the images which incurs significant time and cost. Convolutional neural networks may alleviate the workload of radiologists by discriminating between prostate tumor positive scans and negative ones, allowing radiologists to focus their attention on a subset of scans that are neither clearly positive nor negative. The major challenges of such a system are speed and accuracy. In order to address these two challenges, a new approach using ensemble learning of convolutional neural networks (CNNs) was proposed in this paper, which leverages different imaging modalities including T2 weight, B-value, ADC and Ktrans in a multi-parametric MRI clinical dataset with 330 samples of 204 patients for training and evaluation. The results of prostate tumor identification will display benign or malignant based on extracted features by the individual CNN models in seconds. The ensemble of the four individual CNN models for different image types improves the prediction accuracy to 92% with sensitivity at 94.28% and specificity at 86.67% among given 50 test samples. The proposed framework potentially provides rapid classification in high-volume quantitative prostate tumor samples.


  1. 1.
    Cancer.Net Editorial Board. Prostate cancer: Statistics (2019).
  2. 2.
    Chung, A.G., Khalvati, F., Shafiee, M.J., Haider, M.A., Wong, A.: Prostate cancer detection via a quantitative radiomics-driven conditional random field framework. IEEE Access 3, 2531–2541 (2015)CrossRefGoogle Scholar
  3. 3.
    Sumathipala, Y., Lay, N., Turkbey, B., Smith, C., Choyke, P.L., Summers, R.M.: Prostate cancer detection from multi-institution multiparametric MRIs using deep convolutional neural networks. J. Med. Imaging 5(4), 044507 (2018)CrossRefGoogle Scholar
  4. 4.
    Lemaître, G., Martí, R., Freixenet, J., Vilanova, J.C., Walker, P.M., Meriaudeau, F.: Computer-aided detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review. Comput. Biol. Med. 60, 8–31 (2015)CrossRefGoogle Scholar
  5. 5.
    Tian, Z., Liu, L., Fei, B.: Deep convolutional neural network for prostate MR segmentation. In: Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling, vol. 10135, pp. 101351L. International Society for Optics and Photonics (2017)Google Scholar
  6. 6.
    Du, W., Wang, S., Oto, A., Peng, Y.: Graph-based prostate extraction in T2-weighted images for prostate cancer detection. In: Proceedings of the 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2015), pp. 1225–1229. IEEE (2015)Google Scholar
  7. 7.
    Chang, C., Hu, H., Tsai, Y.: Prostate cancer detection in dynamic MRIs. In: Proceedings of the IEEE International Conference on Digital Signal Processing (DSP 2015), pp. 1279–1282, July 2015Google Scholar
  8. 8.
    Cancer Imaging Archive Wiki. SPIE-AAPM-NCI PROSTATEx challenges (2019).
  9. 9.
    Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Roy. Stat. Soc. Ser. B (Methodol.) 57(1), 289–300 (1995)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Panca, V., Rustam, Z.: Application of machine learning on brain cancer multiclass classification. In: AIP Conference Proceedings, vol. 1862, pp. 030133. AIP Publishing (2017)Google Scholar
  11. 11.
    DiffusionKit. Data processing pipeline (2019).
  12. 12.
    Chen, X., Nguyen, B.P., Chui, C.-K., Ong, S.-H.: Automated brain tumor segmentation using kernel dictionary learning and superpixel-level features. In: Proceedings of the International Conference on Systems, Man, and Cybernetics (SMC 2016), Budapesh, Hungary, 9–12 Oct 2016, pp. 2547–2552. IEEE (2016)Google Scholar
  13. 13.
    Chen, X., Nguyen, B.P., Chui, C.-K., Ong, S.-H.: Reworking multilabel brain tumor segmentation - an automated framework using structured kernel sparse representation. IEEE Syst. Man Cybern. Mag. 3(2), 18–22 (2017)CrossRefGoogle Scholar
  14. 14.
    Chen, X., Nguyen, B.P., Chui, C.-K., Ong, S.-H.: An automatic framework for multi-label brain tumor segmentation based on kernel sparse representation. Acta Polytech. Hung. 14(1), 25–43 (2017)Google Scholar
  15. 15.
    Ruder, S.: An overview of gradient descent optimization algorithms, 1–14 September 2016. CoRR, abs/1609.04747Google Scholar
  16. 16.
    Yousefian, F., Nedić, A., Shanbhag, U.V.: A smoothing stochastic quasi-newton method for non-lipschitzian stochastic optimization problems. In: Proceedings of the 2017 Winter Simulation Conference, pp. 183. IEEE Press (2017)Google Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021

Authors and Affiliations

  • Quang H. Nguyen
    • 1
    Email author
  • Mengnan Gong
    • 2
  • Tao Liu
    • 2
  • Ou Yang Youheng
    • 3
  • Binh P. Nguyen
    • 4
  • Matthew Chin Heng Chua
    • 2
  1. 1.School of Information and Communication TechnologyHanoi University of Science and TechnologyHanoiVietnam
  2. 2.Institute of Systems ScienceNational University of SingaporeSingaporeSingapore
  3. 3.Department of OrthopaedicsSingapore General HospitalSingaporeSingapore
  4. 4.School of Mathematics and StatisticsVictoria University of WellingtonWellingtonNew Zealand

Personalised recommendations