Advertisement

Prostate cancer detection using residual networks

  • Helen Xu
  • John S. H. Baxter
  • Oguz Akin
  • Diego Cantor-RiveraEmail author
Short communication
  • 29 Downloads

Abstract

Purpose

To automatically identify regions where prostate cancer is suspected on multi-parametric magnetic resonance images (mp-MRI).

Methods

A residual network was implemented based on segmentations from an expert radiologist on T2-weighted, apparent diffusion coefficient map, and high b-value diffusion-weighted images. Mp-MRIs from 346 patients were used in this study.

Results

The residual network achieved a hit or miss accuracy of 93% for lesion detection, with an average Jaccard score of 71% that compared the agreement between network and radiologist segmentations.

Conclusion

This paper demonstrated the ability for residual networks to learn features for prostate lesion segmentation.

Keywords

Prostate cancer Multi-parametric MRI Lesion segmentation Deep learning 

Notes

Acknowledgements

We would like to thank Dr. Fuad Nurili and Dr. Ismail Caymaz for their work in prostate segmentation.

Compliance with ethical standards

Conflict of interest

Dr. Oguz Akin receives support from Memorial Sloan Kettering Cancer Center Support Grant/Core Grant (P30 CA008748). Dr. Oguz Akin, Dr. Helen Xu and Dr. Diego Cantor-Rivera hold stock options and serve as scientific advisors for Ezra AI Inc., which is developing artificial intelligence algorithms related to the research being reported in this paper.

References

  1. 1.
    Siegel RL, Miller KD, Jemal A (2018) Cancer statistics 2018. CA Cancer J Clin 68:7–10CrossRefGoogle Scholar
  2. 2.
    Liu S, Zheng H, Feng Y, Li W (2017) Prostate cancer diagnosis using deep learning with 3D multiparametric MRI. SPIE Med Imaging Comput Aided Diagn 10134:1013428CrossRefGoogle Scholar
  3. 3.
    Song Y, Zhang YD, Yan X, Liu H, Zhou M, Hu B, Yang G (2018) Computer-aided diagnosis of prostate cancer using a deep convolutional neural network from multiparametric MRI. J Magn Reson Imaging 48(6):1570–1577CrossRefGoogle Scholar
  4. 4.
    Yang X, Wang Z, Lin C, Le HM, Chen J, Cheng KT, Wang L (2017) Joint detection of diagnosis of prostate cancer in multi-parametric MRI based on multimodal convolutional neural networks. MICCAI 2017, Part III LNCS 10435:426–434Google Scholar
  5. 5.
    Wang Z, Liu C, Cheng D, Wang L, Yang X, Cheng KT (2018) Automated detection of clinically significant prostate cancer in mp-MRI images based on an end-to-end deep neural network. IEEE Trans Med Imaging 37(5):1127–1139CrossRefGoogle Scholar
  6. 6.
    Tsehay Y, Lay N, Wang X, Kwak JT, Turkbey B, Choyke P, Pinto P, Wood B, Summers R (2017) Biopsy-guided learning with deep convolutional neural networks for prostate cancer detection on multiparametric MRI. In: IEEE 14th international symposium on biomedical imaging, pp 642–645Google Scholar
  7. 7.
    Kohl S, Bonekamp D, Schlemmer HP, Yaqubi K, Hohenfellner M, Hadaschik B, Radtke JP, Maier-Hein K (2017) Adversarial networks for the detection of aggressive prostate cancer. arXiv preprint: arXiv:1702.08014
  8. 8.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778Google Scholar
  9. 9.
    Litjens G, Debats O, Barentsz J, Karssemeijer N, Huisman,H (2017) ProstateX challenge data. Cancer Imaging Arch.  https://doi.org/10.7937/K9TCIA.2017.MURS5CL Google Scholar
  10. 10.
    Long J, Shelhamer E, Darrel T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440Google Scholar
  11. 11.
    Chen L-C, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. CoRR, arXiv:1706.05587
  12. 12.
    Ploussard Guillaume, Epstein Jonathan I, Montironi Rodolfo, Carroll Peter R, Wirth Manfred, Grimm Marc-Oliver, Bjartell Anders S, Montorsi Francesco, Freedland Stephen J, Erbersdobler Andreas et al (2011) The contemporary concept of significant versus insignificant prostate cancer. Eur Urol 60(2):291–303CrossRefGoogle Scholar

Copyright information

© CARS 2019

Authors and Affiliations

  1. 1.Ezra AI CanadaTorontoCanada
  2. 2.Université de Rennes 1RennesFrance
  3. 3.Memorial Sloan Kettering Cancer CenterNew YorkUSA

Personalised recommendations