Skip to main content
Springer Nature Link
Log in

Predicting Treatment Response in Prostate Cancer Patients Based on Multimodal PET/CT for Clinical Decision Support

  • Conference paper
  • First Online:
Multimodal Learning for Clinical Decision Support (ML-CDS 2021)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 13050))

Abstract

Clinical decision support systems (CDSSs) have gained critical importance in clinical practice and research. Machine learning (ML) and deep learning methods are widely applied in CDSSs to provide diagnostic and prognostic assistance in oncological studies. Taking prostate cancer (PCa) as an example, true segmentation of pathological uptake and prediction of treatment outcome taking advantage of radiomics features extracted from prostate-specific membrane antigen-positron emission tomography/computed tomography (PSMA-PET/CT) were the main objectives of this study. Thus, we aimed at providing an automated clinical decision support tool to assist physicians. To this end, a multi-channel deep neural network inspired by U-Net architecture is trained and fit to automatically segment pathological uptake in multimodal whole-body baseline \(^{68}\)Ga-PSMA-PET/CT scans. Moreover, state-of-the-art ML methods are applied to radiomics features extracted from the predicted U-Net masks to identify responders to \(^{177}\)Lu-PSMA treatment. To investigate the performance of the methods, 2067 pathological hotspots annotated in a retrospective cohort of 100 PCa patients are applied after subdividing to train and test cohorts. For the automated segmentation task, we achieved 0.88 test precision, 0.77 recall, and 0.82 Dice. For predicting responders, we achieved 0.73 area under the curve (AUC), 0.81 sensitivity, and 0.58 specificity on the test cohort. As a result, the facilitated automated decision support tool has shown its potential to serve as an assistant for patient screening for \(^{177}\)Lu-PSMA therapy.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Data and Code Availability

Due to German regulations on medical data availability, we cannot disclose the data, however all the data would be available for review on-site. The in-house developed code is available online at https://gitlab.com/Moazemi/pet-ct-u-net.

References

  1. Ferlay, J., et al.: Global Cancer Observatory: Cancer Today. International Agency for Research on Cancer, Lyon. https://gco.iarc.fr/today. Accessed 30 June 2021

  2. Jin, S., Li, D., Wang, H., Yin, Y.: Registration of PET and CT images based on multiresolution gradient of mutual information demons algorithm for positioning esophageal cancer patients. J. Appl. Clin. Med. Phys. 14(1), 55–61 (2013). https://doi.org/10.1120/jacmp.v14i1.3931

  3. Bundschuh, R.A., et al.: Textural parameters of tumor heterogeneity in 18F-FDG PET/CT for therapy response assessment and prognosis in patients with locally advanced rectal cancer. J. Nucl. Med. 55(6), 891–897 (2014). https://doi.org/10.2967/jnumed.113.127340

  4. Bang, J.-I., et al.: Prediction of neoadjuvant radiation chemotherapy response and survival using pretreatment [18F]FDG PET/CT scans in locally advanced rectal cancer. Eur. J. Nucl. Med. Mol. Imaging 43(3), 422–431 (2015). https://doi.org/10.1007/s00259-015-3180-9

    Article  Google Scholar 

  5. Ypsilantis, P.P., et al.: Predicting response to neoadjuvant chemotherapy with PET imaging using convolutional neural networks. PLoS One 10(9) (2015). https://doi.org/10.1371/journal.pone.0137036

  6. Gorgi Zadeh, S., et al.: CNNs enable accurate and fast segmentation of Drusen in optical coherence tomography. In: Cardoso, M.J. (ed.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 65–73. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_8

    Chapter  Google Scholar 

  7. Selvaganesan, K., et al.: Robust, atlas-free, automatic segmentation of brain MRI in health and disease. Heliyon. 5(2), e01226 (2019). https://doi.org/10.1016/j.heliyon.2019.e01226

  8. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  9. Hatt, M., et al.: The first MICCAI challenge on PET tumor segmentation. Med. Image Ana. 44, 177–195 (2018). https://doi.org/10.1016/j.media.2017.12.007. ISSN 1361–8415

  10. Li, L., Zhao, X., Lu, W., Tan, S.: Deep learning for variational multimodality tumor segmentation in PET/CT. Neurocomputing 392, 277–295 (2020). https://doi.org/10.1016/j.neucom.2018.10.099. ISSN 0925–2312

  11. Liu, L., Cheng, J., Quan, Q., Wu, F.X., Wang, Y. P., Wang, J.: A survey on U-shaped networks in medical image segmentations. Neurocomputing 409, 244–258 (2020). https://doi.org/10.1016/j.neucom.2020.05.070. ISSN 0925–2312

  12. Beukinga, R.J., et al.: Predicting response to neoadjuvant chemoradiotherapy in esophageal cancer with textural features derived from pretreatment 18F-FDG PET/CT imaging. J. Nucl. Med. 58(5), 723–729 (2017). https://doi.org/10.2967/jnumed.116.180299

  13. Cheng, J.Z., et al.: Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Scientific reports, vol. 6 (2016). https://doi.org/10.1038/srep24454

  14. Moazemi, S., et al.: Decision-support for treatment with 177Lu-PSMA: machine learning predicts response with high accuracy based on PSMA-PET/CT and clinical parameters. Ann. Transl. Med. 9,9, 818 (2021). https://doi.org/10.21037/atm-20-6446

  15. Parisot, C.: The DICOM standard. Int. J. Cardiac. Imag. 11, 171–177 (1995). https://doi.org/10.1007/BF01143137

    Article  Google Scholar 

  16. Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. tensorflow.org (2015). https://doi.org/10.5281/zenodo.4724125

  17. Chollet, F.: Keras. GitHub repository (2015). https://github.com/fchollet/keras

  18. Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945). https://doi.org/10.2307/1932409

  19. van Griethuysen, J.J.M., et al.: Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77(21), e104–e107 (2017). https://doi.org/10.1158/0008-5472.CAN-17-0339

  20. Guyon, I., Weston, J., Barnhill, S., Vapnik, V.: Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389–422 (2002). https://doi.org/10.1023/A:1012487302797

    Article  MATH  Google Scholar 

  21. Official Company Website for the InterView FUSION: Software. https://www.mediso.de/Interview-fusion.html. Accessed 30 June 2021

  22. Tomar, N.K.: Polyp Segmentation using UNET in TensorFlow 2.0. https://idiotdeveloper.com/polyp-segmentation-using-unet-in-tensorflow-2/. Accessed 30 June 2021

  23. Wright, R.E.: Logistic regression. In: Grimm, L.G., Yarnold, P.R.: (eds.) Reading and Understanding Multivariate Statistics, pp. 217–244. American Psychological Association (1995)

    Google Scholar 

  24. Hearst, M.A., Dumais, S.T., Osuna, E., Platt, J., Scholkopf, B.: Support vector machines. IEEE Intell. Syst. Appl. 13(4), 18–28 (1998). https://doi.org/10.1109/5254.708428

  25. Simm, J., de Abril, I., Sugiyama, M.: Tree-based ensemble multi-task learning method for classification and regression 97(6) (2014). http://CRAN.R-project.org/package=extraTrees

  26. Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001). https://doi.org/10.1023/A:1010933404324

    Article  MATH  Google Scholar 

  27. Moazemi, S., et al.: Machine learning facilitates hotspot classification in PSMA-PET/CT with nuclear medicine specialist accuracy. Diagnostics (Basel, Switzerland) 10(9), 622 (2020). https://doi.org/10.3390/diagnostics10090622

    Article  Google Scholar 

  28. Erle, A., Moazemi, S., Lütje, S., Essler, M., Schultz, T., Bundschuh, R.A.: Evaluating a machine learning tool for the classification of pathological uptake in whole-body PSMA-PET-CT scans. Tomography 7, 301–312 (2021). https://doi.org/10.3390/tomography7030027

    Article  Google Scholar 

  29. Vallieres, M., et al.: Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci. Rep. 7(1), e10117 (2017). https://doi.org/10.1038/s41598-017-10371-5

  30. Moazemi, S., Erle, A., Lütje, S., Gaertner, F.C., Essler, M., Bundschuh, R.A.: Estimating the potential of radiomics features and radiomics signature from pretherapeutic PSMA-PET-CT scans and clinical data for prediction of overall survival when treated with 177Lu-PSMA. Diagnostics 11(2), 186 (2021). https://doi.org/10.3390/diagnostics11020186

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Bonn, 53115, Bonn, Germany

    Sobhan Moazemi & Thomas Schultz

  2. Department of Nuclear Medicine, University Hospital Bonn, 53127, Bonn, Germany

    Sobhan Moazemi, Markus Essler & Ralph A. Bundschuh

  3. Bonn-Aachen International Center for Information Technology (BIT), 53115, Bonn, Germany

    Thomas Schultz

Authors
  1. Sobhan Moazemi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Markus Essler
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Thomas Schultz
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ralph A. Bundschuh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sobhan Moazemi .

Editor information

Editors and Affiliations

  1. IBM Research - Almaden, San Jose, CA, USA

    Tanveer Syeda-Mahmood

  2. Harvard Medical School, Boston, MA, USA

    Xiang Li

  3. Case Western Reserve University, Cleveland, OH, USA

    Anant Madabhushi

  4. Tel Aviv University, Tel Aviv, Israel

    Hayit Greenspan

  5. Harvard Medical School, Boston, MA, USA

    Quanzheng Li

  6. University of Southern California, Los Angeles, CA, USA

    Richard Leahy

  7. Peking University, Beijing, China

    Bin Dong

  8. IBM Research - Almaden, San Jose, CA, USA

    Hongzhi Wang

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Moazemi, S., Essler, M., Schultz, T., Bundschuh, R.A. (2021). Predicting Treatment Response in Prostate Cancer Patients Based on Multimodal PET/CT for Clinical Decision Support. In: Syeda-Mahmood, T., et al. Multimodal Learning for Clinical Decision Support. ML-CDS 2021. Lecture Notes in Computer Science(), vol 13050. Springer, Cham. https://doi.org/10.1007/978-3-030-89847-2_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-89847-2_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-89846-5

  • Online ISBN: 978-3-030-89847-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships