Advertisement

Deep Learning Based Approach to Quantification of PET Tracer Uptake in Small Tumors

  • Laura Dal TosoEmail author
  • Elisabeth Pfaehler
  • Ronald Boellaard
  • Julia A. Schnabel
  • Paul K. Marsden
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11905)

Abstract

In Positron Emission Tomography (PET), quantification of tumor radiotracer uptake is mainly performed using standardised uptake value and related methods. However, the accuracy of these metrics is limited by the poor spatial resolution and noise properties of PET images. Therefore, there is a great need for new methods that allow for accurate and reproducible quantification of tumor radiotracer uptake, particularly for small regions. In this work, we propose a deep learning approach to improve quantification of PET tracer uptake in small tumors using a 3D convolutional neural network. The network was trained on simulated images that present 3D shapes with typical tumor tracer uptake distributions (‘ground truth distributions’), and the corresponding set of simulated PET images. The network was tested on unseen simulated PET images and was shown to robustly estimate the original radiotracer uptake, yielding improved images both in terms of shape and activity distribution. The same network was successful when applied to 3D tumors acquired from physical phantom PET scans.

Keywords

Convolutional neural network PET Quantification Reconstruction 

References

  1. 1.
    Bai, B., Bading, J., Conti, P.S.: Tumor quantification in clinical positron emission tomography. Theranostics (2013).  https://doi.org/10.7150/thno.5629CrossRefGoogle Scholar
  2. 2.
    Baizán, A.N., Puig, D.R., Segura, J.P.: Evolution of quantification methods in oncologic 18F-FDG PET studies. Rev. Esp. Med. Nucl. Imagen Mol. 37(4), 203–204 (2018).  https://doi.org/10.1016/j.remn.2018.06.001CrossRefGoogle Scholar
  3. 3.
    Blanc-Durand, P., Gucht, A., Schaefer, N., Itti, E., Prior, J.O.: Automatic lesion detection and segmentation of 18F-FET PET in gliomas: a full 3D U-Net convolutional neural network study. PLOS ONE 13, e0195798 (2018).  https://doi.org/10.1371/journal.pone.0195798CrossRefGoogle Scholar
  4. 4.
    Gong, K., et al.: Iterative PET image reconstruction using convolutional neural network representation. IEEE Trans. Med. Imaging 38(3), 675–685 (2019).  https://doi.org/10.1109/TMI.2018.2869871CrossRefGoogle Scholar
  5. 5.
    Gong, K., Guan, J., Liu, C.C., Qi, J.: PET image denoising using a deep neural network through fine tuning. IEEE Trans. Radiat. Plasma Med. Sci. 3(2), 153–161 (2019).  https://doi.org/10.1109/trpms.2018.2877644CrossRefGoogle Scholar
  6. 6.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, ICML 2015, vol. 37, pp. 448–456. JMLR.org (2015). http://dl.acm.org/citation.cfm?id=3045118.3045167
  7. 7.
    Kim, K., et al.: Penalized PET reconstruction using deep learning prior and local linear fitting. IEEE Trans. Med. Imaging (2018).  https://doi.org/10.1109/TMI.2018.2832613CrossRefGoogle Scholar
  8. 8.
    Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. (2017).  https://doi.org/10.1016/j.media.2017.07.005CrossRefGoogle Scholar
  9. 9.
    Loening, A., Sam Gambhir, S.: AMIDE: a free software tool for multimodality medical image analysis. Mol. Imaging 2, 131–137 (2003).  https://doi.org/10.1162/153535003322556877CrossRefGoogle Scholar
  10. 10.
    Pfaehler, E., et al.: Repeatability of 18F-FDG PET radiomic features: a phantom study to explore sensitivity to image reconstruction settings, noise, and delineation method. Med. Phys. (2019).  https://doi.org/10.1002/mp.13322CrossRefGoogle Scholar
  11. 11.
    Strauss, L.G., Conti, P.S.: The applications of PET in clinical oncology. J. Nucl. Med. 32, 623–648 (1991)Google Scholar
  12. 12.
    van der Vos, C.S., et al.: Quantification, improvement, and harmonization of small lesion detection with state-of-the-art PET. Eur. J. Nucl. Med. Mol. Imaging 44, 4–16 (2017).  https://doi.org/10.1007/s00259-017-3727-zCrossRefGoogle Scholar
  13. 13.
    Wahl, R.L., Jacene, H., Kasamon, Y., Lodge, M.A.: From RECIST to PERCIST: evolving considerations for PET response criteria in solid tumors. J. Nucl. Med. 50(Suppl. 1), 1–50 (2009).  https://doi.org/10.2967/jnumed.108.057307CrossRefGoogle Scholar
  14. 14.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 1–14 (2004).  https://doi.org/10.1109/TIP.2003.819861CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Laura Dal Toso
    • 1
    Email author
  • Elisabeth Pfaehler
    • 2
  • Ronald Boellaard
    • 2
    • 3
  • Julia A. Schnabel
    • 1
  • Paul K. Marsden
    • 1
  1. 1.School of Biomedical Engineering and Imaging SciencesKing’s College LondonLondonUK
  2. 2.Department of Nuclear Medicine and Molecular ImagingUniversity of Groningen, University Medical Center GroningenGroningenThe Netherlands
  3. 3.Department of Radiology and Nuclear MedicineAmsterdam University Medical CentersAmsterdamThe Netherlands

Personalised recommendations