Computational Fractional Flow Reserve From Coronary Computed Tomography Angiography—Optical Coherence Tomography Fusion Images in Assessing Functionally Significant Coronary Stenosis

A Physics-Integrated Deep Learning Approach for Patient-Specific Non-Newtonian Blood Viscosity Assessment using PPG

BACKGROUND AND OBJECTIVE

The aim of this study is to extract a patient-specific viscosity equation from photoplethysmography (PPG) data. An aging society has increased the need for remote, non-invasive health monitoring systems. However, the circulatory system remains beyond the scope of wearable devices. The solution might be found in the possibility of measuring blood viscosity from wearable devices. Blood viscosity information can be used to monitor and diagnose various circulatory system diseases. Therefore, if blood viscosity can be calculated from wearable photoplethysmography, the versatility of a non-invasive health monitoring system can be broadened.

METHODS

A hybrid 1D CNN-LSTM architecture incorporating physics-informed constraints was developed to integrate rheological principles into data-driven PPG analysis. The shear-viscosity equation derived from the viscometer was used as ground-truth data. The signal obtained from the wearable devices was processed with noise filtering and wandering elimination to gain stable blood pressure waves. The neural network was trained using k-fold cross-validation and weight factor optimization, with the loss function incorporating rheological constraints from the Carreau-Yasuda model.

RESULTS

The final estimation model achieved an accuracy of 81.1 %. The accuracy in the physiological shear range (50-300 s-1) was 84.0 %, outperforming other low and high shear regions. Mean absolute errors of 0.67 cP in the physiological range align with clinical viscometry tolerances (< 1 cP), demonstrating diagnostic feasibility. Statistical analysis revealed strong linear relationships between predicted and ground truth values across all shear rates (correlation coefficients: 0.619-0.742, p < 0.0001), with mean absolute errors decreasing from 7.84 cP at low shear rates to 0.67 cP in the physiological range. The accuracy and contribution of each parameter to the Carreau-Yasuda model were also analyzed. The results show that the contribution of each parameter varies based on the shear range, providing insight into weight factor optimization.

CONCLUSION

By non-invasively estimating blood viscosity from PPG, the diagnostic capabilities of wearable healthcare systems can be expanded to target various diseases related to the circulatory system. The demonstrated accuracy in physiologically relevant shear ranges supports the potential clinical application of this methodology.

Computed Tomography-Derived Fractional Flow Reserve: Developing A Gold Standard for Coronary Artery Disease Diagnostics

In recent years, a new technique called computed tomography-derived fractional flow reserve (CT-FFR) has been developed. CT-FFR overcomes many limitations in the current gold-standard fractional flow reserve (FFR) techniques while maintaining a better concordance with FFR. This technique integrates static coronary CT angiography data with hydrodynamic models, employing algorithms rather than guidewire interventions to compute the FFR. In addition to diagnosing coronary heart disease, CT-FFR has been applied in the preoperative risk assessment of major adverse cardiovascular events (MACEs) in organ transplantation and transcatheter aortic valve replacement (TAVR). Continuous advancements in CT-FFR techniques and algorithms are expanding their applicability to other methodologies. Subsequently, with robust clinical trial validation, CT-FFR can potentially supersede FFR as the primary "gatekeeper" for interventions.

Predictive value of plaque characteristics for identification of lesions causing ischemia

BACKGROUND

Functional assessment using fractional flow reserve (FFR) and anatomical assessment using optical coherence tomography (OCT) are used in clinical practice for patients with intermediate coronary stenosis. Moreover, coronary computed tomography angiography (CTA) is a common noninvasive imaging technique for evaluating suspected coronary artery disease before being referred for angiography. This study aimed to investigate the association between FFR and plaque characteristics assessed using coronary CTA and OCT for intermediate coronary stenosis.

METHODS

Based on a prospective multicenter registry, 159 patients having 339 coronary lesions with intermediate stenosis were included. All patients underwent coronary CTA before being referred for coronary angiography, and both FFR measurements and OCT examinations were performed during angiography. A stenotic lesion identified with FFR ≤0.80 was deemed diagnostic of an ischemia-causing lesion. The predictive value of plaque characteristics assessed using coronary CTA and OCT for identifying lesions causing ischemia was analyzed.

RESULTS

Stenosis severity and plaque characteristics on coronary CTA and OCT differed between lesions that caused ischemia and those that did not. In multivariate analysis, low attenuation plaque on coronary CTA (odds ratio [OR]=2.78; P=0.038), thrombus (OR=5.13; P=0.042), plaque rupture (OR=3.25; P=0.017), and intimal vasculature on OCT (OR=2.57; P=0.012) were independent predictors of ischemic lesions. Increasing the number of these plaque characteristics offered incremental improvement in predicting the lesions causing ischemia.

CONCLUSIONS

Comprehensive anatomical evaluation of coronary stenosis may provide additional supportive information for predicting the lesions causing ischemia.

Assessment of fractional flow reserve in intermediate coronary stenosis using optical coherence tomography-based machine learning

Objectives

This study aimed to evaluate and compare the diagnostic accuracy of machine learning (ML)- fractional flow reserve (FFR) based on optical coherence tomography (OCT) with wire-based FFR irrespective of the coronary territory.

Background

ML techniques for assessing hemodynamics features including FFR in coronary artery disease have been developed based on various imaging modalities. However, there is no study using OCT-based ML models for all coronary artery territories.

Methods

OCT and FFR data were obtained for 356 individual coronary lesions in 130 patients. The training and testing groups were divided in a ratio of 4:1. The ML-FFR was derived for the testing group and compared with the wire-based FFR in terms of the diagnosis of ischemia (FFR ≤ 0.80).

Results

The mean age of the subjects was 62.6 years. The numbers of the left anterior descending, left circumflex, and right coronary arteries were 130 (36.5%), 110 (30.9%), and 116 (32.6%), respectively. Using seven major features, the ML-FFR showed strong correlation (r = 0.8782, P < 0.001) with the wire-based FFR. The ML-FFR predicted wire-based FFR ≤ 0.80 in the test set with sensitivity of 98.3%, specificity of 61.5%, and overall accuracy of 91.7% (area under the curve: 0.948). External validation showed good correlation (r = 0.7884, P < 0.001) and accuracy of 83.2% (area under the curve: 0.912).

Conclusion

OCT-based ML-FFR showed good diagnostic performance in predicting FFR irrespective of the coronary territory. Because the study was a small-size study, the results should be warranted the performance in further large-scale research.