EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-ND 4.0

Feasibility of Monte Carlo dropout‐based uncertainty maps to evaluate deep learning‐based synthetic CTs for adaptive proton therapy

Arthur Villanueva Galapon iD, Adrian Thummerer, Johannes Albertus Langendijk, Dirk Wagenaar, Stefan Both

Medical Physics · 2024-04 · 51 (4) · 2499-2509

DOI: 10.1002/mp.16838 ↗

At a glance

Journal article in Medical Physics, published online on 2023-11-13. Written by Arthur Villanueva Galapon and 4 co-authors. Institution: Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands. Major MEDLINE topics: Deep Learning, Proton Therapy. Cited 31 times so far (Crossref); 35 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: European Union's Horizon 2020 Marie Skłodowska-Curie Actions.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Deep learning has shown promising results to generate MRI‐based synthetic CTs and to enable accurate proton dose calculations on MRIs. For clinical implementation of synthetic CTs, quality assurance tools that verify their quality and reliability are required but still lacking.

Purpose

This study aims to evaluate the predictive value of uncertainty maps generated with Monte Carlo dropout (MCD) for verifying proton dose calculations on deep‐learning‐based synthetic CTs (sCTs) derived from MRIs in online adaptive proton therapy.

Methods

Two deep‐learning models (DCNN and cycleGAN) were trained for CT image synthesis using 101 paired CT‐MR images. sCT images were generated using MCD for each model by performing 10 inferences with activated dropout layers. The final sCT was obtained by averaging the inferred sCTs, while the uncertainty map was obtained from the HU variance corresponding to each voxel of 10 sCTs. The resulting uncertainty maps were compared to the observed HU‐, range‐, WET‐, and dose‐error maps between the sCT and planning CT. For range and WET errors, the generated uncertainty maps were projected along the 90‐degree angle. To evaluate the dose distribution, a mask based on the 5%‐isodose curve was applied to only include voxels along the beam paths. Pearson's correlation coefficients were calculated to determine the correlation between the uncertainty maps and HUs, range, WET, and dose errors. To evaluate the dosimetric accuracy of synthetic CTs, clinical proton treatment plans were recalculated and compared to the pCTs Results Evaluation of the correlation showed an average of r = 0.92 ± 0.03 and r = 0.92 ± 0.03 for errors between uncertainty‐HU, r = 0.66 ± 0.09 and r = 0.62 ± 0.06 between uncertainty‐range, r = 0.64 ± 0.06 and r = 0.58 ± 0.07 between uncertainty‐WET, and r = 0.65 ± 0.09 and r = 0.67 ± 0.07 between uncertainty and dose difference for DCNN and cycleGAN model, respectively. Dosimetric comparison for target volumes showed an average 3%/3 mm gamma pass rate of 99.76 ± 0.43 (DCNN) and 99.10 ± 1.27 (cycleGAN).

Conclusion

The observed correlations between uncertainty maps and the various metrics (HU, range, WET, and dose errors) demonstrated the potential of MCD‐based uncertainty maps as a reliable QA tool to evaluate the accuracy of deep learning‐based sCTs.

Subjects

MeSH terms (MEDLINE)

Deep LearningProton TherapyTomography, X-Ray ComputedProtonsFeasibility StudiesReproducibility of ResultsUncertaintyRadiotherapy Planning, Computer-AssistedMagnetic Resonance ImagingRadiotherapy DosageImage Processing, Computer-Assisted

Author keywords

MRIadaptive proton therapydeep learningquality assurancesynthetic CT

Substances

Protons

Authors and institutions

  • Department of Radiation Oncology, University Medical Center Groningen, University of Groningen, Groningen, The Netherlands.
  • Department of Radiation Oncology, LMU University Hospital, LMU Munich, Germany.

ORCID profiles: Arthur Villanueva Galapon

Funding

  • European Union's Horizon 2020 Marie Skłodowska-Curie Actions

Cite

APA

Galapon, A. V., Thummerer, A., Langendijk, J. A., Wagenaar, D., & Both, S. (2024). Feasibility of Monte Carlo dropout‐based uncertainty maps to evaluate deep learning‐based synthetic CTs for adaptive proton therapy. Medical Physics, 51(4), 2499-2509. https://doi.org/10.1002/mp.16838

Vancouver

Galapon AV, Thummerer A, Langendijk JA, Wagenaar D, Both S. Feasibility of Monte Carlo dropout‐based uncertainty maps to evaluate deep learning‐based synthetic CTs for adaptive proton therapy. Medical Physics. 2024;51(4):2499-2509. doi:10.1002/mp.16838

BibTeX
@article{Galapon2024,
  author = {Galapon, Arthur Villanueva and Thummerer, Adrian and Langendijk, Johannes Albertus and Wagenaar, Dirk and Both, Stefan},
  title = {Feasibility of Monte Carlo dropout‐based uncertainty maps to evaluate deep learning‐based synthetic CTs for adaptive proton therapy},
  journal = {Medical Physics},
  year = {2024},
  volume = {51},
  number = {4},
  pages = {2499--2509},
  doi = {10.1002/mp.16838}
}
Start for free →