CNN based heuristics for optimizing the shape of MLC apertures

Betreuer/in:            Stefan Gerlach           
Dekanat/Institut:   E-1 - Institute of Medical Technology and Intelligent Systems           

E-Mail:   stefan.gerlach@tuhh.de

Background: In robotic radiation therapy, ionizing radiation is delivered by a linear accelerator that is
mounted on a robotic arm. This allows to deliver dose from practically arbitrary many directions.
Additionally, multi-Leaf-Collimators (MLCs) offer a great flexibility in shaping beams. However, find-
ing optimal treatment beams is a computationally challenging task. However, similarities be-
tween patients exist and convolutional neural networks (CNNs) offer a method to identify beneficial
beams. Once trained CNNs show comparatively fast inference. Hence, they can be used to speed up treatment planning times and improve treatment plan quality.

Taks: The current approach for generating MLC-beams should be evaluated and training data
should be generated. The existing framework should be extended to generate image features for
MLC-beams. Using these features, a CNNs should be trained to predict each beam’s quality. Infer-
ence on the trained network for treatment plan generation should be implemented in the existing
Java framework and the performance evaluated.

Specific steps include:

  1. Familiarize with the treatment planning framework.
  2. Evaluate conventional MLC-beam generation.
  3. Generate training data.
  4. Implement a pipeline to train a CNN.
  5. Integrate inference into the treatment planning framework.
  6. Evaluate the CNN-based approach with respect to computation time and treatment plan
    quality.

Requirements: Good programming skills (ideally in Python+Java), ability to work independently, ideally experience with machine learning

Not required is experience in medicine or radiation therapy.

References: Gerlach, S., Fürweger, C., Hofmann, T. and Schlaefer, A. (2020), Feasibility and analysis
of CNN‐based candidate beam generation for robotic radiosurgery. Med. Phys., 47: 3806-3815.
doi:10.1002/mp.14331

Please contact me if you want to know more about the topic.

Schreibe einen Kommentar

Deine E-Mail-Adresse wird nicht veröffentlicht. Erforderliche Felder sind mit * markiert.