EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Deep learning‐based dose prediction for magnetic resonance‐guided prostate radiotherapy

Samuel Fransson, Robin Strand, David Tilly

Medical Physics · 2024

DOI: 10.1002/mp.17312 ↗

At a glance

Journal article in Medical Physics, 2024. Written by Samuel Fransson and 2 co-authors. Institution: Department of Medical Physics, Uppsala University Hospital, Uppsala, Sweden. Major MEDLINE topics: Deep Learning, Prostatic Neoplasms, Radiotherapy Dosage, Radiotherapy, Image-Guided. Cited 6 times so far (Crossref); 36 references. The full text is freely available (open access, CC BY 4.0). Funded by: ASSIST.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

Daily adaptive radiotherapy, as performed with the Elekta Unity MR‐Linac, requires choosing between different adaptation methods, namely ATP (Adapt to Position) and ATS (Adapt to Shape), where the latter requires daily re‐contouring to obtain a dose plan tailored to the daily anatomy. These steps are inherently resource‐intensive, and quickly predicting the dose distribution and the dosimetric evaluation criteria while the patient is on the table could facilitate a fast selection of adaptation method and decrease the treatment times.

Purpose

In this work, we aimed to develop a deep‐learning‐based dose‐prediction pipeline for prostate MR‐Linac treatments.

Methods

Two hundred twelve MR‐images, structure sets, and dose distributions from 35 prostate patients treated with 6.1 Gy for 7 or 6 fractions at our MR‐Linac were included, split into train/test partitions of 152/60 images, respectively. A deep‐learning segmentation network was trained to segment the CTV (prostate), bladder, and rectum. A second network was trained to predict the dose distribution based on manually delineated structures. At inference, the predicted segmentations acted as input to the dose prediction network, and the predicted dose was compared to the true (optimized in the treatment planning system) dose distribution.

Results

Median DSC values from the segmentation network were 0.90/0.94/0.87 for CTV/bladder/rectum. Predicted segmentations as input to the dose prediction resulted in mean differences between predicted and true doses of 0.7%/0.7%/1.7% (relative to the prescription dose) for D 98% / D 95% / D 2% for the CTV. For the bladder, the difference was 0.7%/0.3% for D mean /D 2% and for the rectum 0.1/0.2/0.2 pp (percentage points) for V 33Gy / V 38Gy / V 41Gy . In comparison, true segmentations as input resulted in differences of 1.1%/0.9%/1.6% for CTV, 0.5%/0.4% for bladder, and 0.7/0.4/0.3 pp for the rectum. Only D 2% for CTV and D mean / D 2% for bladder were found to be statistically significantly better when using true structures instead of predicted structures as input to the dose prediction.

Conclusions

Small differences in the fulfillment of clinical dose‐volume constraints are seen between utilizing deep‐learning predicted structures as input to a dose prediction network and manual structures. Overall mean differences 2%.

Subjects

MeSH terms (MEDLINE)

Deep LearningProstatic NeoplasmsRadiotherapy DosageRadiotherapy, Image-GuidedMagnetic Resonance ImagingHumansMaleRadiation DosageRadiotherapy Planning, Computer-Assisted

Author keywords

deep learningdose predictionradiotherapy

Authors and institutions

  • Department of Medical Physics, Uppsala University Hospital, Uppsala, Sweden.
  • Department of Surgical Sciences, Uppsala University, Uppsala, Sweden.
  • Department of Information Technology, Uppsala University, Uppsala, Sweden.
  • Department of Immunology, Genetics and Pathology, Uppsala University, Uppsala, Sweden.

Funding

  • ASSIST

Cite

APA

Fransson, S., Strand, R., & Tilly, D. (2024). Deep learning‐based dose prediction for magnetic resonance‐guided prostate radiotherapy. Medical Physics. https://doi.org/10.1002/mp.17312

Vancouver

Fransson S, Strand R, Tilly D. Deep learning‐based dose prediction for magnetic resonance‐guided prostate radiotherapy. Medical Physics. 2024. doi:10.1002/mp.17312

BibTeX
@article{Fransson2024,
  author = {Fransson, Samuel and Strand, Robin and Tilly, David},
  title = {Deep learning‐based dose prediction for magnetic resonance‐guided prostate radiotherapy},
  journal = {Medical Physics},
  year = {2024},
  doi = {10.1002/mp.17312}
}
Start for free →