Cross-modality (CT-MRI) prior augmented deep learning for robust lung tumor segmentation from small MR datasets.

Journal: Medical physics
Published Date:

Abstract

PURPOSE: Accurate tumor segmentation is a requirement for magnetic resonance (MR)-based radiotherapy. Lack of large expert annotated MR datasets makes training deep learning models difficult. Therefore, a cross-modality (MR-CT) deep learning segmentation approach that augments training data using pseudo MR images produced by transforming expert-segmented CT images was developed.

Authors

  • Jue Jiang
    Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, NY, 10065, USA.
  • Yu-Chi Hu
    Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, USA; Department of Radiation Oncology, Memorial Sloan-Kettering Cancer Center, New York, USA.
  • Neelam Tyagi
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Pengpeng Zhang
    Department of Medical Physics, Memorial Sloan-Kettering Cancer Center, New York, USA; Department of Radiation Oncology, Memorial Sloan-Kettering Cancer Center, New York, USA. Electronic address: zhangp@mskcc.org.
  • Andreas Rimner
    Memorial Sloan Kettering Cancer Center, New York, New York.
  • Joseph O Deasy
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Harini Veeraraghavan
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY; veerarah@mskcc.org.