EUVIMEDDescobrir EUVIMED
Open access · CC BY 4.0

Deep‐learning‐based joint rigid and deformable contour propagation for magnetic resonance imaging‐guided prostate radiotherapy

Iris D Kolenbrander, Matteo Maspero, Allard A Hendriksen, Ryan Pollitt, Jochem R N van der Voort van Zyp, Cornelis A T van den Berg, Josien P W Pluim, Maureen A J M van Eijnatten

Medical Physics · 2024

DOI: 10.1002/mp.17000 ↗

At a glance

Journal article in Medical Physics, 2024. Written by Iris D Kolenbrander and 7 co-authors. Institution: Medical Image Analysis Group, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands. Major MEDLINE topics: Deep Learning, Prostatic Neoplasms. Cited 11 times so far (Crossref); 41 references. The full text is freely available (open access, CC BY 4.0). Funded by: The Irene Curie Fellowship program, Eindhoven Artificial Intelligence Systems Institute, Nederlandse Organisatie voor Wetenschappelijk Onderzoek.

ResumoSubjectsDados bibliográficosCiteRelated studies

Abstract (original language)

Background

Deep learning‐based unsupervised image registration has recently been proposed, promising fast registration. However, it has yet to be adopted in the online adaptive magnetic resonance imaging‐guided radiotherapy (MRgRT) workflow.

Purpose

In this paper, we design an unsupervised, joint rigid, and deformable registration framework for contour propagation in MRgRT of prostate cancer.

Methods

Three‐dimensional pelvic T2‐weighted MRIs of 143 prostate cancer patients undergoing radiotherapy were collected and divided into 110, 13, and 20 patients for training, validation, and testing. We designed a framework using convolutional neural networks (CNNs) for rigid and deformable registration. We selected the deformable registration network architecture among U‐Net, MS‐D Net, and LapIRN and optimized the training strategy (end‐to‐end vs. sequential). The framework was compared against an iterative baseline registration. We evaluated registration accuracy (the Dice and Hausdorff distance of the prostate and bladder contours), structural similarity index, and folding percentage to compare the methods. We also evaluated the framework's robustness to rigid and elastic deformations and bias field perturbations.

Results

The end‐to‐end trained framework comprising LapIRN for the deformable component achieved the best median (interquartile range) prostate and bladder Dice of 0.89 (0.85–0.91) and 0.86 (0.80–0.91), respectively. This accuracy was comparable to the iterative baseline registration: prostate and bladder Dice of 0.91 (0.88–0.93) and 0.86 (0.80–0.92). The best models complete rigid and deformable registration in 0.002 (0.0005) and 0.74 (0.43) s (Nvidia Tesla V100‐PCIe 32 GB GPU), respectively. We found that the models are robust to translations up to 52 mm, rotations up to 15, elastic deformations up to 40 mm, and bias fields.

Conclusions

Our proposed unsupervised, deep learning‐based registration framework can perform rigid and deformable registration in less than a second with contour propagation accuracy comparable with iterative registration.

Subjects

MeSH terms (MEDLINE)

Deep LearningProstatic NeoplasmsMaleHumansProstatePelvisRadiotherapy Planning, Computer-AssistedMagnetic Resonance ImagingImage Processing, Computer-AssistedAlgorithms

Author keywords

MRI‐guided radiotherapycontour propagationdeep‐learning‐based image registration

Authors and institutions

  • Medical Image Analysis Group, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
  • Eindhoven Artificial Intelligence Systems Institute, Eindhoven University of Technology, Eindhoven, The Netherlands.
  • Computational Imaging Group for MR Diagnostics & Therapy, Center for Image Sciences, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Department of Radiotherapy, University Medical Center Utrecht, Utrecht, The Netherlands.
  • Computational Imaging, Centrum Wiskunde & Informatica, Amsterdam, The Netherlands.

Funding

  • The Irene Curie Fellowship program
  • Eindhoven Artificial Intelligence Systems Institute
  • Nederlandse Organisatie voor Wetenschappelijk Onderzoek

Cite

APA

Kolenbrander, I. D., Maspero, M., Hendriksen, A. A., Pollitt, R., van der Voort van Zyp, J. R. N., van den Berg, C. A. T., Pluim, J. P. W., & van Eijnatten, M. A. J. M. (2024). Deep‐learning‐based joint rigid and deformable contour propagation for magnetic resonance imaging‐guided prostate radiotherapy. Medical Physics. https://doi.org/10.1002/mp.17000

Vancouver

Kolenbrander ID, Maspero M, Hendriksen AA, Pollitt R, van der Voort van Zyp JRN, van den Berg CAT, et al. Deep‐learning‐based joint rigid and deformable contour propagation for magnetic resonance imaging‐guided prostate radiotherapy. Medical Physics. 2024. doi:10.1002/mp.17000

BibTeX
@article{Kolenbrander2024,
  author = {Kolenbrander, Iris D and Maspero, Matteo and Hendriksen, Allard A and Pollitt, Ryan and van der Voort van Zyp, Jochem R N and van den Berg, Cornelis A T and Pluim, Josien P W and van Eijnatten, Maureen A J M},
  title = {Deep‐learning‐based joint rigid and deformable contour propagation for magnetic resonance imaging‐guided prostate radiotherapy},
  journal = {Medical Physics},
  year = {2024},
  doi = {10.1002/mp.17000}
}
Start for free →