IntraCross: Cross-modality graph matching for intravascular sequence registration

Computers in Biology and Medicine, vol. 205, pp. 111566

Abstract

Intravascular ultrasound (IVUS) and optical coherence tomography (OCT) are complementary imaging modalities to assess atherosclerosis in vivo. Combining both modalities in a single imaging system has been shown to improve the characterization of vulnerable plaques that are likely to cause acute coronary events. However, fundamental differences in tissue sensitivities and acquisition protocols make the registration of sequences challenging. Anatomical landmarks used to align IVUS and OCT sequences can be masked or lack visual similarity between modalities which renders manual alignment time-consuming and prone to observer variability, limiting its clinical use. Existing methods impose strict frame-level correspondences leading to instability in low information regions, and rely on a two-step registration process that compounds alignment errors. We propose IntraCross, a novel graph matching framework that learns partial assignments between landmarks rather than enforcing rigid frame-by-frame matching, enabling flexible correspondences while rejecting unmatchable landmarks. This is the first method to perform both temporal and rotational registration simultaneously, aligning with clinical workflows. We extend existing partial matching techniques from 2D to 3D sequences and incorporate a temporal prior to regularize the matching process. Testing in 77 vessels from 22 patients showed a high agreement with expert analysts (Williams Index=1.1; p=0.62, 0.89, 0.07) and our approach outperforms existing methods reported in the literature for circumferential registration (p=0.01, 0.04). • A novel graph matching method for Intravascular sequence registration that learns partial correspondence between anatomical landmarks in different modalities, addressing error caused by forced frame-by-frame matching of prior work. • We extend existing graph matching techniques from single modality to multi modality and from 2D image to 3D video sequence. • IntraCross represents the consensus better than individual experts and offers statistically significant improvements against prior work.

Authors 13

1. Kit Mills Bransby

   Queen Mary University of London

   Affiliation as printed

   School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK; Digital Environment Research Institute, Queen Mary University of London, London, UK

2. Xingwei He

   Queen Mary University of London · Barts Health NHS Trust · William Harvey Research Institute · Tongji Hospital · Huazhong University of Science and Technology

   Affiliation as printed

   Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University of London, London, UK; Department of Cardiology, Barts Health NHS Trust, London, UK; Division of Cardiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology Wuhan, Wuhan, China

3. Christos V. Bourantas

   Queen Mary University of London · Barts Health NHS Trust · William Harvey Research Institute

   Affiliation as printed

   Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University of London, London, UK; Department of Cardiology, Barts Health NHS Trust, London, UK

4. Ahmet Emir Ulutaş

   Queen Mary University of London · Barts Health NHS Trust · William Harvey Research Institute

   Affiliation as printed

   Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University of London, London, UK; Department of Cardiology, Barts Health NHS Trust, London, UK

5. Nathan Angelo Lecaros Yap

   Queen Mary University of London · Barts Health NHS Trust · William Harvey Research Institute

   Affiliation as printed

   Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University of London, London, UK; Department of Cardiology, Barts Health NHS Trust, London, UK

6. Ryota Kakizaki

   University Hospital of Bern

   Affiliation as printed

   Department of Cardiology, Bern University Hospital, Bern, Switzerland

7. Yasushi Ueki

   University Hospital of Bern

   Affiliation as printed

   Department of Cardiology, Bern University Hospital, Bern, Switzerland

8. Jonas Häner

   University Hospital of Bern

   Affiliation as printed

   Department of Cardiology, Bern University Hospital, Bern, Switzerland

9. Konstantinos C. Koskinas

   University Hospital of Bern

   Affiliation as printed

   Department of Cardiology, Bern University Hospital, Bern, Switzerland

10. Jouke Dijkstra Aachen

    Leiden University Medical Center

    Affiliation as printed

    Leiden University Medical Center, Leiden, the Netherlands

11. Greg Slabaugh

    Queen Mary University of London

    Affiliation as printed

    School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK; Digital Environment Research Institute, Queen Mary University of London, London, UK

12. Lorenz Räber

    University Hospital of Bern

    Affiliation as printed

    Department of Cardiology, Bern University Hospital, Bern, Switzerland

13. Qianni Zhang corresponding

    Queen Mary University of London

    Affiliation as printed

    School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK; Digital Environment Research Institute, Queen Mary University of London, London, UK. Electronic address: qianni.zhang@qmul.ac.uk