Enhancing automated right-sided early-stage breast cancer treatments via deep learning model adaptation without additional training.

Journal: Medical physics
PMID: 39966996

Abstract

BACKGROUND: Input data curation and model training are essential, but time-consuming steps in building a deep-learning (DL) auto-planning model, ensuring high-quality data and optimized performance. Ideally, one would prefer a DL model that exhibits the same high-quality performance as a trained model without the necessity of undergoing such time-consuming processes. That goal can be achieved by providing models that have been trained on a given dataset and are capable of being fine-tuned for other ones, requiring no additional training.

Authors

  • Michele Zeverino
    Institute of Radiation Physics, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
  • Silvia Fabiano
    Radiation Oncology Department, Zurich University Hospital and University of Zurich, Zurich, Switzerland.
  • Wendy Jeanneret-Sozzi
    Radiation Oncology Department, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
  • Jean Bourhis
    Radiation Oncology Department, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
  • Francois Bochud
    Institute of Radiation Physics, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland.
  • Raphaël Moeckli
    Institute of Radiation Physics, Lausanne University Hospital and Lausanne University, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals