Related Experiment Video
Updated: Jul 12, 2025
Intravascular Ultrasound Image-Based Finite Element Modeling Approach for Quantifying In Vivo Mechanical Properties of Human Coronary Artery
Published on: December 6, 2024
CARDIAN: a novel computational approach for real-time end-diastolic frame detection in intravascular ultrasound using
Xingru Huang1,2, Retesh Bajaj3,4, Weiwei Cui1
1School of Electronic Engineering and Computer Science, Queen Mary University of London, London, United Kingdom.
Insights
Accurate end-diastolic frame detection in intravascular ultrasound (IVUS) is crucial for cardiac analysis. A novel neural network approach, trained with ECG signals, outperforms human experts in identifying these critical frames.
Area of Science:
- Cardiovascular Imaging
- Medical Artificial Intelligence
- Biomedical Engineering
Background:
- Accurate quantification of coronary artery dimensions using intravascular ultrasound (IVUS) is challenged by cardiac cycle variations.
- End-diastolic (ED) frame detection is critical for reliable volumetric analysis and interventional guidance in IVUS studies.
- Manual ED-frame identification is time-consuming and prone to inter-observer variability.
Purpose of the Study:
- To develop and validate a novel, automated neural network-based method for precise end-diastolic frame detection in IVUS sequences.
- To improve the accuracy and reproducibility of volumetric analysis in IVUS studies.
- To provide a robust alternative to manual ED-frame identification by expert analysts.
Main Methods:
- A neural network framework integrating motion encoders, a bidirectional attention recurrent network (BARNet), and temporal/spatiotemporal encoders was developed.
- The model was trained using electrocardiogram (ECG) signals acquired synchronously with IVUS data.
- The system captures cardiac phase motion and catheter rotational movement for frame analysis.
Main Results:
- The proposed automated method achieved high accuracy in detecting ED frames across major coronary arteries (71.9% LAD, 67.8% LCx, 69.9% RCA) within a 66.7 ms tolerance against ECG.
- The neural network approach demonstrated superior performance compared to estimations made by two expert human analysts.
- The methodology proved to be accurate and fully reproducible in identifying ED frames.
Conclusions:
- The developed neural network methodology offers an accurate and reproducible solution for end-diastolic frame detection in IVUS imaging.
- This automated approach is recommended over manual expert identification for enhanced consistency and efficiency in IVUS analysis.
- The findings support the integration of this AI-driven tool for improved clinical decision-making and research standardization.
Introduction:
Changes in coronary artery luminal dimensions during the cardiac cycle can impact the accurate quantification of volumetric analyses in intravascular ultrasound (IVUS) image studies. Accurate ED-frame detection is pivotal for guiding interventional decisions, optimizing therapeutic interventions, and ensuring standardized volumetric analysis in research studies. Images acquired at different phases of the cardiac cycle may also lead to inaccurate quantification of atheroma volume due to the longitudinal motion of the catheter in relation to the vessel. As IVUS images are acquired throughout the cardiac cycle, end-diastolic frames are typically identified retrospectively by human analysts to minimize motion artefacts and enable more accurate and reproducible volumetric analysis.
Methods:
In this paper, a novel neural network-based approach for accurate end-diastolic frame detection in IVUS sequences is proposed, trained using electrocardiogram (ECG) signals acquired synchronously during IVUS acquisition. The framework integrates dedicated motion encoders and a bidirectional attention recurrent network (BARNet) with a temporal difference encoder to extract frame-by-frame motion features corresponding to the phases of the cardiac cycle. In addition, a spatiotemporal rotation encoder is included to capture the IVUS catheter's rotational movement with respect to the coronary artery.
Results:
With a prediction tolerance range of 66.7 ms, the proposed approach was able to find 71.9%, 67.8%, and 69.9% of end-diastolic frames in the left anterior descending, left circumflex and right coronary arteries, respectively, when tested against ECG estimations. When the result was compared with two expert analysts' estimation, the approach achieved a superior performance.
Discussion:
These findings indicate that the developed methodology is accurate and fully reproducible and therefore it should be preferred over experts for end-diastolic frame detection in IVUS sequences.
More Related Videos
09:17High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation
Published on: July 29, 2011
08:10Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022