Transfer learning on fused multiparametric MR images for classifying histopathological subtypes of rhabdomyosarcoma

Comput Med Imaging Graph. 2018 Apr;65:167-175. doi: 10.1016/j.compmedimag.2017.05.002. Epub 2017 May 5.

Abstract

This paper presents a deep-learning-based CADx for the differential diagnosis of embryonal (ERMS) and alveolar (ARMS) subtypes of rhabdomysarcoma (RMS) solely by analyzing multiparametric MR images. We formulated an automated pipeline that creates a comprehensive representation of tumor by performing a fusion of diffusion-weighted MR scans (DWI) and gadolinium chelate-enhanced T1-weighted MR scans (MRI). Finally, we adapted transfer learning approach where a pre-trained deep convolutional neural network has been fine-tuned based on the fused images for performing classification of the two RMS subtypes. We achieved 85% cross validation prediction accuracy from the fine-tuned deep CNN model. Our system can be exploited to provide a fast, efficient and reproducible diagnosis of RMS subtypes with less human interaction. The framework offers an efficient integration between advanced image processing methods and cutting-edge deep learning techniques which can be extended to deal with other clinical domains that involve multimodal imaging for disease diagnosis.

Keywords: Computer aided diagnosis; Deep neural networks; Image fusion; Rhabdomyosarcoma; Transfer learning.

Publication types

  • Research Support, N.I.H., Extramural

MeSH terms

  • Adolescent
  • Child
  • Child, Preschool
  • Deep Learning*
  • Diagnosis, Differential
  • Humans
  • Image Interpretation, Computer-Assisted / methods*
  • Infant
  • Magnetic Resonance Imaging*
  • Retrospective Studies
  • Rhabdomyosarcoma / classification*
  • Rhabdomyosarcoma / diagnostic imaging*
  • Young Adult