Site-agnostic 3D dose distribution prediction with deep learning neural networks.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: Typically, the current dose prediction models are limited to small amounts of data and require retraining for a specific site, often leading to suboptimal performance. We propose a site-agnostic, three-dimensional dose distribution prediction model using deep learning that can leverage data from any treatment site, thus increasing the total data available to train the model. Applying our proposed model to a new target treatment site requires only a brief fine-tuning of the model to the new data and involves no modifications to the model input channels or its parameters. Thus, it can be efficiently adapted to a different treatment site, even with a small training dataset.

Authors

  • Maryam Mashayekhi
    Medical Artificial Intelligence and Automation Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
  • Itzel Ramirez Tapia
    Medical Artificial Intelligence and Automation Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas, USA.
  • Anjali Balagopal
    Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, UT Southwestern Medical Center, United States of America.
  • Xinran Zhong
  • Azar Sadeghnejad Barkousaraie
    Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology,University of Texas Southwestern Medical Center, Dallas, Texas, United States.
  • Rafe McBeth
    Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, UT Southwestern Medical Center, Dallas, TX, 75390, USA.
  • Mu-Han Lin
    Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, Texas.
  • Steve Jiang
  • Dan Nguyen
    University of Massachusetts Chan Medical School, Worcester, Massachusetts.