Deep learning prediction of voxel-level liver stiffness in patients with nonalcoholic fatty liver disease

Brian L. Pollack, Kayhan Batmanghelich, Stephen S. Cai, Emile Gordon, Stephen Wallace, Roberta Catania, Carlos Morillo-Hernandez, Alessandro Furlan, Amir A. Borhani*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Purpose: To reconstruct virtual MR elastography (MRE) images based on traditional MRI inputs with a machine learning algorithm. Materials and Methods: In this single-institution, retrospective study, 149 patients (mean age, 58 years ± 12 [standard deviation]; 71 men) with nonalcoholic fatty liver disease who underwent MRI and MRE between January 2016 and January 2019 were evaluated. Nine conventional MRI sequences and clinical data were used to train a convolutional neural network to reconstruct MRE images at the per-voxel level. The architecture was further modified to accept multichannel three-dimensional inputs and to allow inclusion of clinical and demographic information. Liver stiffness and fibrosis category (F0 [no fibrosis] to F4 [significant fibrosis]) of reconstructed images were assessed by using voxel-and patient-level agreement by correlation, sensitivity, and specificity calculations; in addition, classification by receiver operator characteristic analyses was performed, and Dice score was used to evaluate hepatic stiffness locality. Results: The model for predicting liver stiffness incorporated four image sequences (precontrast T1-weighted liver acquisition with volume acquisition [LAVA] water and LAVA fat, 120-second–delay T1-weighted LAVA water, and single-shot fast spin-echo T2 weighted) and clinical data. The model had a patient-level and voxel-level correlation of 0.50 ± 0.05 and 0.34 ± 0.03, respectively. By using a stiffness threshold of 3.54 kPa to make a binary classification into no fibrosis or mild fibrosis (F0–F1) versus clinically significant fibro-sis (F2–F4), the model had sensitivity of 80% ± 4, specificity of 75% ± 5, accuracy of 78% ± 3, area under the receiver operating characteristic curve of 84 ± 0.04, and a Dice score of 0.74. Conclusion: The generation of virtual elastography images is feasible by using conventional MRI and clinical data with a machine learning algorithm.

Original languageEnglish (US)
Article numbere200274
JournalRadiology: Artificial Intelligence
Issue number6
StatePublished - Nov 2021

ASJC Scopus subject areas

  • Artificial Intelligence
  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Deep learning prediction of voxel-level liver stiffness in patients with nonalcoholic fatty liver disease'. Together they form a unique fingerprint.

Cite this