FIRE: Unsupervised bi-directional inter- And intra-modality registration using deep networks

Chengjia Wang, Guang Yang, Giorgos Papanastasiou*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Magnetic resonance imaging (MRI) benefits from the acquisition of multiple sequences (thereafter, referred to as 'modalities') under a single imaging session. Each modality offers different complementary spatial and functional information in the clinical setting. Inter- and intra (across MR sequence slices)-modality image registration is an important pre-processing step across multiple applications in routine clinical workflows, such as when visual or quantitative imaging biomarkers need to be assessed across multi-sequence/multi-slice MRI data. This paper presents an unsupervised deep learning-based registration network that can learn affine and non-rigid transformations, simultaneously. Inverse-consistency is an important property that is commonly ignored in recent deep learning-based inter-modality registration algorithms. We address this issue through our proposed multi-task, cross-domain image synthesis architecture, in which we incorporated a new comprehensive transformation network. The proposed model learns a modality-independent latent representation to perform cycle-consistent cross-modality synthesis and uses an inverse-consistency loss to learn paired transformations, to align the synthesized with the target image. We name this proposed framework as 'FIRE' due to the shape of its structure and we focus on interpreting model components to enhance model interpretability for clinical MR applications. Our method shows comparable and better performances against a well-established baseline method in experiments on multi-sequence brain MR data and intra-modality 4D cardiac Cine-MR data.

Original languageEnglish
Title of host publication34th IEEE International Symposium on Computer-Based Medical Systems 2021
PublisherIEEE
Pages510-514
Number of pages5
ISBN (Electronic)9781665441216
DOIs
Publication statusPublished - 12 Jul 2021
Event34th IEEE International Symposium on Computer-Based Medical Systems 2021 - Virtual, Online
Duration: 7 Jun 20219 Jun 2021

Conference

Conference34th IEEE International Symposium on Computer-Based Medical Systems 2021
Abbreviated titleCBMS 2021
CityVirtual, Online
Period7/06/219/06/21

Keywords

  • deep learning interpretability
  • Inter- and intra-modality registration
  • inverse-consistency loss

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'FIRE: Unsupervised bi-directional inter- And intra-modality registration using deep networks'. Together they form a unique fingerprint.

Cite this