3D fusion between fluoroscopy angiograms and SPECT myocardial perfusion images to guide percutaneous coronary intervention

Abstract

Background. Percutaneous coronary intervention (PCI) in stable coronary artery disease (CAD) is commonly triggered by abnormal myocardial perfusion imaging (MPI). However, due to the possibilities of multivessel disease, serial stenoses and variability of coronary artery perfusion distribution, opportunity exists to better align anatomic stenosis with perfusion abnormalities to improve revascularization decisions. This study aims to develop a 3-dimensional (3D) multi-modality fusion approach to assist decision-making for PCI.Methods. Coronary arteries from fluoroscopic angiography (FA) were reconstructed into 3D artery anatomy. Left ventricular (LV) epicardial surface was extracted from single-photon emission computed tomography (SPECT). The 3D fusion between artery anatomy and LV epicardial surface was completed with scaling iterative closest points (S-ICP) and vessel-surface overlay algorithms. The accuracy of the 3D fusion was evaluated via both computer simulation and real patient data. For technical validation, simulated FA and MPI were integrated and then compared with the ground truth from a digital phantom. For clinical validation, FA and SPECT images were integrated and then compared with the ground truth from computed tomography (CT) angiograms.Results. In the technical evaluation, the distance-based mismatch error between simulated fluoroscopy and phantom arteries is 1.86±1.43mm for left coronary arteries (LCA) and 2.21±2.50mm for right coronary arteries (RCA). In the clinical validation, the distance-based mismatch errors between the fluoroscopy and CT arteries were 3.84±3.15mm for LCA and 5.55±3.64mm for RCA. The presence of the corresponding fluoroscopy and CT arteries in the AHA 17-segment model agreed well with a Kappa value of 0.91(95% confidence interval (CI): 0.89-0.93) for LCA and a Kappa value of 0.80 (CI: 0.67-0.92) for RCA. Conclusions.Our fusion approach is technically accurate to assist PCI decision-making and is clinically feasible to be used in the catheterization laboratory. There is an opportunity to improve the decisionmaking and outcomes of PCI in stable CAD.

3D fusion between SPECT myocardial perfusion imaging and invasive coronary angiography to guide the treatment for patients with stable CAD

“…By utilizing various deep learning-based algorithms, we have been able to automatically extract left ventricles from myocardial perfusion images [28] and arterial segments from ICA frames [10, 11]. Our SPECT-ICA fusion can be completed within 5 minutes [7]. In addition to myocardial perfusion, our SPECT-ICA fusion has additional values by providing information about wall motion and thickening.…”

“…Image fusion between SPECT MPI and ICA was carried out using a previously published approach by a trained operator [7]. A deep learning model was utilized to extract coronary arteries automatically from ICA images, and manual corrections were made when the arteries were not accurately extracted [10, 11].…”

“…We have developed a 3D fusion approach that combined SPECT and ICA and analyzed its clinical utility based on per-vessel analysis [7]. Compared with the side-by-side analysis, our SPECT-ICA fusion approach showed a lower number of segments being qualified with equivocal coronary luminal stenosis and an improvement in the revascularization ratio of the matched group [8].…”

“…We have developed a 3D fusion approach that combined SPECT and ICA and analyzed its clinical utility based on per-vessel analysis [7]. Compared with the sideby-side analysis, our SPECT-ICA fusion approach showed a lower number of All rights reserved.…”

How AI and Robotics Will Advance Interventional Radiology: A Narrative Review and Future Perspectives

“…In contemporary cardiovascular operations, not only is precision required in the treatment, but it is also essential to incorporate basic physiological information such as perfusion, blood flow, and tissue oxygenation during intravascular interventions to make comprehensive treatment decisions. Besides its ability to complement single-photon emission computed tomography myocardial perfusion imaging in guiding PCI [105], cardiovascular magnetic resonance has the advantage of no ionizing radiation and provides good soft tissue contrast. [106] Therefore, MRI-guided interventional therapy navigation has a promising future.…”