Domain knowledge driven 3D dose prediction using moment-based loss function
- 14 September 2022
- journal article
- research article
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 67 (18) , 185017
Abstract
Objective. To propose a novel moment-based loss function for predicting 3D dose distribution for the challenging conventional lung intensity modulated radiation therapy plans. The moment-based loss function is convex and differentiable and can easily incorporate clinical dose volume histogram (DVH) domain knowledge in any deep learning (DL) framework without computational overhead. Approach. We used a large dataset of 360 (240 for training, 50 for validation and 70 for testing) conventional lung patients with 2 Gy × 30 fractions to train the DL model using clinically treated plans at our institution. We trained a UNet like convolutional neural network architecture using computed tomography, planning target volume and organ-at-risk contours as input to infer corresponding voxel-wise 3D dose distribution. We evaluated three different loss functions: (1) the popular mean absolute error (MAE) loss, (2) the recently developed MAE + DVH loss, and (3) the proposed MAE + moments loss. The quality of the predictions was compared using different DVH metrics as well as dose-score and DVH-score, recently introduced by the AAPM knowledge-based planning grand challenge. Main results. Model with (MAE + moment) loss function outperformed the model with MAE loss by significantly improving the DVH-score (11%, p < 0.01) while having similar computational cost. It also outperformed the model trained with (MAE + DVH) by significantly improving the computational cost (48%) and the DVH-score (8%, p < 0.01). Significance. DVH metrics are widely accepted evaluation criteria in the clinic. However, incorporating them into the 3D dose prediction model is challenging due to their non-convexity and non-differentiability. Moments provide a mathematically rigorous and computationally efficient way to incorporate DVH information in any DL architecture. The code, pretrained models, docker container, and Google Colab project along with a sample dataset are available on our DoseRTX GitHub ( https://github.com/nadeemlab/DoseRTX )Keywords
All Related Versions
Funding Information
- MSK Cancer Center Support Grant/Core Grant (P30 CA008748)
This publication has 27 references indexed in Scilit:
- Evaluation of a Knowledge-Based Planning Solution for Head and Neck CancerInternational Journal of Radiation Oncology - Biology - Physics (IJROBP), 2015
- A DVH-guided IMRT optimization algorithm for automatic treatment planning and adaptive radiotherapy replanningMedical Physics, 2014
- A moment-based approach for DVH-guided radiotherapy treatment plan optimizationPhysics in Medicine & Biology, 2013
- Predicting dose‐volume histograms for organs‐at‐risk in IMRT planningMedical Physics, 2012
- Variation in external beam treatment plan quality: An inter-institutional study of planners and planning systemsPractical Radiation Oncology, 2012
- Der ICRU-Report 83: Verordnung, Dokumentation und Kommunikation der fluenzmodulierten Photonenstrahlentherapie (IMRT)Strahlentherapie und Onkologie, 2012
- The equivalence of multi-criteria methods for radiotherapy plan optimizationPhysics in Medicine & Biology, 2009
- Analysis of Treatment Planning Time Among Systems and Planners for Intensity-Modulated Radiation TherapyJournal of the American College of Radiology, 2009
- Controlling the dose distribution with gEUD-type constraints within the convex radiotherapy optimization frameworkPhysics in Medicine & Biology, 2008
- How many plans are needed in an IMRT multi-objective plan database?Physics in Medicine & Biology, 2008