Diagnosis of focal liver lesions with deep learning-based multi-channel analysis of hepatocyte-specific contrast-enhanced magnetic resonance imaging.

Journal: World journal of gastroenterology
Published Date:

Abstract

BACKGROUND: The nature of input data is an essential factor when training neural networks. Research concerning magnetic resonance imaging (MRI)-based diagnosis of liver tumors using deep learning has been rapidly advancing. Still, evidence to support the utilization of multi-dimensional and multi-parametric image data is lacking. Due to higher information content, three-dimensional input should presumably result in higher classification precision. Also, the differentiation between focal liver lesions (FLLs) can only be plausible with simultaneous analysis of multi-sequence MRI images.

Authors

  • Róbert Stollmayer
    Department of Radiology, Medical Imaging Centre, Faculty of Medicine, Semmelweis University, Budapest 1083, Hungary.
  • Bettina K Budai
    Department of Radiology, Medical Imaging Centre, Faculty of Medicine, Semmelweis University, Budapest 1083, Hungary. budai.bettina@med.semmelweis-univ.hu.
  • Ambrus Tóth
    Department of Radiology, Medical Imaging Centre, Faculty of Medicine, Semmelweis University, Budapest 1083, Hungary.
  • Ildikó Kalina
    Department of Radiology, Medical Imaging Centre, Faculty of Medicine, Semmelweis University, Budapest 1083, Hungary.
  • Erika Hartmann
    Department of Transplantation and Surgery, Faculty of Medicine, Semmelweis University, Budapest 1082, Hungary.
  • Péter Szoldán
    1 MedInnoScan Kutatás-fejlesztési Kft., Budapest.
  • Viktor Bérczi
    Radiológiai Klinika, Semmelweis Egyetem, Általános Orvostudományi Kar Budapest.
  • Pál Maurovich-Horvat
    Philips Medical Systems Technologies Ltd., Advanced Technologies Center, Haifa, 3100202, Israel.
  • Pál N Kaposi
    Department of Radiology, Medical Imaging Centre, Faculty of Medicine, Semmelweis University, Budapest 1083, Hungary.