Towards optimal deep fusion of imaging and clinical data via a model-based description of fusion quality.

Journal: Medical physics
Published Date:

Abstract

BACKGROUND: Due to intrinsic differences in data formatting, data structure, and underlying semantic information, the integration of imaging data with clinical data can be non-trivial. Optimal integration requires robust data fusion, that is, the process of integrating multiple data sources to produce more useful information than captured by individual data sources. Here, we introduce the concept of fusion quality for deep learning problems involving imaging and clinical data. We first provide a general theoretical framework and numerical validation of our technique. To demonstrate real-world applicability, we then apply our technique to optimize the fusion of CT imaging and hepatic blood markers to estimate portal venous hypertension, which is linked to prognosis in patients with cirrhosis of the liver.

Authors

  • Yuqi Wang
    Graduate School at Shenzhen, Tsinghua University, Shenzhen, Guangdong, P.R. China.
  • Xiang Li
    Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, United States.
  • Meghana Konanur
    Department of Radiology, Duke University, Durham, North Carolina, USA.
  • Brandon Konkel
    Department of Radiology, Duke University Medical Center, Durham, North Carolina.
  • Elisabeth Seyferth
    Department of Radiology, Duke University, Durham, North Carolina, USA.
  • Nathan Brajer
    Duke Institute for Health Innovation, Durham, North Carolina.
  • Jian-Guo Liu
  • Mustafa R Bashir
    Department of Radiology, Duke University, Durham, North Carolina, USA.
  • Kyle J Lafata
    Department of Radiology, Duke University School of Medicine, Durham, NC, USA. kyle.lafata@duke.edu.