Development and evaluation of radiotherapy deep learning dose prediction models for breast cancer

Treatment planning of radiotherapy is a time-consuming and planner dependent process that can be automated by dose prediction models. The purpose of this study was to evaluate the performance of two machine learning models for breast cancer radiotherapy before possible clinical implementation. An in...

Full description

Saved in:
Bibliographic Details
Published in:Physics and imaging in radiation oncology Vol. 17; pp. 65 - 70
Main Authors: Bakx, Nienke, Bluemink, Hanneke, Hagelaar, Els, van der Sangen, Maurice, Theuws, Jacqueline, Hurkmans, Coen
Format: Journal Article
Language:English
Published: Netherlands Elsevier B.V 01.01.2021
Elsevier
Subjects:
Breast cancer
Convolutional neural networks
Dose prediction
Intensity-modulated radiotherapy
Machine learning
Original
Dose prediction
Breast cancer
Intensity-modulated radiotherapy
Convolutional neural networks
Machine learning
ISSN:2405-6316, 2405-6316
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Treatment planning of radiotherapy is a time-consuming and planner dependent process that can be automated by dose prediction models. The purpose of this study was to evaluate the performance of two machine learning models for breast cancer radiotherapy before possible clinical implementation. An in-house developed model, based on U-net architecture, and a contextual atlas regression forest (cARF) model integrated in the treatment planning software were trained. Obtained dose distributions were mimicked to create clinically deliverable plans. For training and validation, 90 patients were used, 15 patients were used for testing. Treatment plans were scored on predefined evaluation criteria and percent errors with respect to clinical dose were calculated for doses to planning target volume (PTV) and organs at risk (OARs). The U-net plans before mimicking met all criteria for all patients, both models failed one evaluation criterion in three patients after mimicking. No significant differences (p < 0.05) were found between clinical and predicted U-net plans before mimicking. Doses to OARs in plans of both models differed significantly from clinical plans, but no clinically relevant differences were found. After mimicking, both models had a mean percent error within 1.5% for the average dose to PTV and OARs. The mean errors for maximum doses were higher, within 6.6%. Differences between predicted doses to OARs of the models were small when compared to clinical plans, and not found to be clinically relevant. Both models show potential in automated treatment planning for breast cancer.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2405-6316
2405-6316
DOI:10.1016/j.phro.2021.01.006