multimodars: A Rust-powered toolkit for multi-modality cardiac image fusion and registration

2025-10-03

AI Summary

Existing tools lack open, deterministic, and integrable multimodal fusion and registration capabilities for cardiac imaging across multiple physiological states (e.g., rest/stress, pre-/post-stent implantation). This paper introduces the first open-source toolkit specifically designed for coronary artery analysis across such states, enabling high-fidelity whole-vessel 3D reconstruction by fusing intravascular ultrasound (IVUS) and coronary computed tomography angiography (CCTA). Methodologically, we propose a deterministic registration algorithm and a lightweight data model; the high-performance backend is implemented in Rust, with NumPy serving as the standard interface and native support for CSV and AIVUS-CAA—among other prevalent output formats. Our contributions address three critical gaps: (1) multi-state geometric modeling, (2) system-level workflow integration, and (3) reproducible research infrastructure. Empirical evaluation demonstrates high-accuracy, low-latency fusion, significantly improving clinical modeling fidelity and reproducibility.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Combining complementary imaging modalities is critical to build reliable 3D coronary models: intravascular imaging gives sub-millimetre resolution but limited whole-vessel context, while CCTA supplies 3D geometry but suffers from limited spatial resolution and artefacts (e.g., blooming). Prior work demonstrated intravascular/CCTA fusion, yet no open, flexible toolkit is tailored for multi-state analysis (rest/stress, pre-/post-stenting) while offering deterministic behaviour, high performance, and easy pipeline integration. multimodars addresses this gap with deterministic alignment algorithms, a compact NumPy-centred data model, and an optimised Rust backend suitable for scalable, reproducible experiments. The package accepts CSV/NumPy inputs including data formats produced by the AIVUS-CAA software

Problem

• Fusing intravascular and CCTA imaging for 3D coronary models
• Addressing lack of open toolkit for multi-state cardiac analysis
• Providing deterministic alignment and high-performance registration algorithms

Innovation

• Rust-powered toolkit for cardiac image fusion
• Deterministic alignment algorithms for multi-state analysis
• NumPy-centered data model with optimized backend