Domain Knowledge Driven 3D Dose Prediction Using Moment-Based Loss Function

by   Gourav Jhanwar, et al.
Memorial Sloan Kettering Cancer Center

Dose volume histogram (DVH) metrics are widely accepted evaluation criteria in the clinic. However, incorporating these metrics into deep learning dose prediction models is challenging due to their non-convexity and non-differentiability. We propose a novel moment-based loss function for predicting 3D dose distribution for the challenging conventional lung intensity modulated radiation therapy (IMRT) plans. The moment-based loss function is convex and differentiable and can easily incorporate DVH metrics in any deep learning framework without computational overhead. The moments can also be customized to reflect the clinical priorities in 3D dose prediction. For instance, using high-order moments allows better prediction in high-dose areas for serial structures. We used a large dataset of 360 (240 for training, 50 for validation and 70 for testing) conventional lung patients with 2Gy × 30 fractions to train the deep learning (DL) model using clinically treated plans at our institution. We trained a UNet like CNN architecture using computed tomography (CT), planning target volume (PTV) and organ-at-risk contours (OAR) 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. Model with (MAE + Moment) loss function outperformed the model with MAE loss by significantly improving the DVH-score (11 outperformed the model trained with (MAE+DVH) by significantly improving the computational cost (48


page 10

page 12


Deep Learning 3D Dose Prediction for Conventional Lung IMRT Using Consistent/Unbiased Automated Plans

Deep learning (DL) 3D dose prediction has recently gained a lot of atten...

DeepDoseNet: A Deep Learning model for 3D Dose Prediction in Radiation Therapy

The DeepDoseNet 3D dose prediction model based on ResNet and Dilated Den...

OpenKBP: The open-access knowledge-based planning grand challenge

The purpose of this work is to advance fair and consistent comparisons o...

Personalized Two-sided Dose Interval

In many clinical practices, the goal of medical interventions or therapi...

Surrogate-free machine learning-based organ dose reconstruction for pediatric abdominal radiotherapy

To study radiotherapy-related adverse effects, detailed dose information...

Measuring breathing induced oesophageal motion and its dosimetric impact

Stereotactic body radiation therapy allows for a precise and accurate do...

Please sign up or login with your details

Forgot password? Click here to reset