Deep learning method for prediction of patient-specific dose distribution in breast cancer

Abstract

Background Patient-specific dose prediction improves the efficiency and quality of radiation treatment planning and reduces the time required to find the optimal plan. In this study, a patient-specific dose prediction model was developed for a left-sided breast clinical case using deep learning, and its performance was compared with that of conventional knowledge-based planning using RapidPlan™. Methods Patient-specific dose prediction was performed using a contour image of the planning target volume (PTV) and organs at risk (OARs) with a U-net-based modified dose prediction neural network. A database of 50 volumetric modulated arc therapy (VMAT) plans for left-sided breast cancer patients was utilized to produce training and validation datasets. The dose prediction deep neural network (DpNet) feature weights of the previously learned convolution layers were applied to the test on a cohort of 10 test sets. With the same patient data set, dose prediction was performed for the 10 test sets after training in RapidPlan. The 3D dose distribution, absolute dose difference error, dose-volume histogram, 2D gamma index, and iso-dose dice similarity coefficient were used for quantitative evaluation of the dose prediction. Results The mean absolute error (MAE) and one standard deviation (SD) between the clinical and deep learning dose prediction models were 0.02 ± 0.04%, 0.01 ± 0.83%, 0.16 ± 0.82%, 0.52 ± 0.97, − 0.88 ± 1.83%, − 1.16 ± 2.58%, and − 0.97 ± 1.73% for D95%, Dmean in the PTV, and the OARs of the body, left breast, heart, left lung, and right lung, respectively, and those measured between the clinical and RapidPlan dose prediction models were 0.02 ± 0.14%, 0.87 ± 0.63%, − 0.29 ± 0.98%, 1.30 ± 0.86%, − 0.32 ± 1.10%, 0.12 ± 2.13%, and − 1.74 ± 1.79, respectively. Conclusions In this study, a deep learning method for dose prediction was developed and was demonstrated to accurately predict patient-specific doses for left-sided breast cancer. Using the deep learning framework, the efficiency and accuracy of the dose prediction were compared to those of RapidPlan. The doses predicted by deep learning were superior to the results of the RapidPlan-generated VMAT plan.

Dose prediction for cervical cancer VMAT patients with a full-scale 3D-cGAN-based model and the comparison of different input data on the prediction results

“…Recently, there are related studies for head and neck, breast, abdomen or pelvis, in which the treatment techniques include 3D-CRT, IMRT, VMAT and PBS, and the U-Net is basically adopted as architecture [ 47 – 50 ]. The evaluation indicators for performance analysis are similar in almost all related works and Ahn et al used gamma analysis as a metric [ 47 ]. Our models use cGAN as the basic architecture, which exporting satisfactory prediction results.…”

Artificial intelligence based treatment planning of radiotherapy for locally advanced breast cancer

“…To our knowledge, this is the first CNN based model for locally advanced breast cancer patients which makes it hard to compare this study with other literature. Besides that, most CNN based breast planning models, in particular for node-negative patients, are only focusing on dose predictions and are not generating clinically applicable plans [9] , [10] , [11] , [16] . This model was based on the HD U-net from Dan Nguyen et al, which was originally used for head and neck cancer patients.…”

“…There are several studies focusing on specific hard-coded algorithms which can automate the planning process [6] , [7] , [8] . Other types of studies are focusing on methods that are using previously obtained treatment plans in order to predict dose volume histograms (DVHs) [9] , dose distributions [10] , [11] or even generate clinically deliverable plans [12] . Many of these studies are using artificial intelligence (AI) involving convolutional neural networks (CNNs) to generate these predictions.…”

Organ‐at‐risk dose prediction using a machine learning algorithm: Clinical validation and treatment planning benefit for lung SBRT

“…This showed promising results when compared with the clinically delivered dose distributions for 10 test cases, with some larger uncertainty seen for the max dose to the lungs and heart. 20 It is important to note that in addition to average estimates of prediction performance, comparing estimates for individual patients is key to understanding prediction performance, since average doses can agree well even if there are considerable under‐ or overestimates for a given patient.…”