Deep learning kidney segmentation with very limited training data using a cascaded convolution neural network.

Journal: PloS one
Published Date:

Abstract

BACKGROUND: Deep learning segmentation requires large datasets with ground truth. Image annotation is time consuming and leads to shortages of ground truth data for clinical imaging. This study is to investigate the feasibility of kidney segmentation using deep learning convolution neural network (CNN) models trained with MR images from only a few subjects.

Authors

  • Junyu Guo
    Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas, United States of America.
  • Ayobami Odu
    Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas, United States of America.
  • Iván Pedrosa
    Chief of MRI. Professor of Radiology, Urology, Advanced Imaging Research Center and Biomedical Engineering. University of Texas Southwestern Medical Center, Dallas, TX, United States. Electronic address: ivan.pedrosa@utsouthwestern.edu.