Automatic Contouring Project

Project aim

Accurate contouring is a critical aspect of safe and effective treatment delivery in radiotherapy (RT). Current limitations in clinical practice include large intra and inter-observer variances (IOV), as well as time delays in both contour generation and correction. This study designed and evaluated a 2D U-Net architecture with two primary aims:

  1. Automate a time consuming aspect of canine radiotherapy. Specifically, vacuum bag segmentation has been reported to take approximately 30 minutes to contour manually.
  2. Evaluate the ability of a 2D U-Net model to achieve expert level performance as defined by Nikolov et al.’s surface dice similarity coefficient [1] with respect to IOV.

The intent for this research is to act as a template for future work extending to other organs.

Video Demonstrating Usage

Best viewed at 720p+ resolution.

Details

The Masters thesis developed during this software project has been publicly released to provide a detailed description of the work. It provides details of the model architecture, and examines performance under multiple loss functions. In addition, this work discusses the development of a second model designed to fulfil the need for contouring to become part of regular quality assurance testing.

Consider joining the PyMedPhys mailing list to be notified of future progress on this topic.

Basic Implementation

Details on how to implement the project into your own workflow will be provided once the code migrates from the experimental division of PyMedPhys into the main code base. Watch this space.

References

[1]Nikolov et al. “Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy.” (2018): https://arxiv.org/pdf/1809.04430.pdf