Fully automated quantitative coronary angiography versus optical coherence tomography guidance for coronary stent implantation (FLASH): Study protocol for a randomized controlled noninferiority trial.

BACKGROUND: Artificial intelligence-based quantitative coronary angiography (AI-QCA) has been developed to provide a more objective and reproducible data about the severity of coronary artery stenosis and the dimensions of the vessel for intervention in real-time, overcoming the limitations of significant inter- and intraobserver variability, and time-consuming nature of on-site QCA, without requiring extra time and effort. Compared with the subjective nature of visually estimated conventional CAG guidance, AI-QCA guidance provides a more practical and standardized angiography-based approach. Although the advantage of intravascular imaging-guided PCI is increasingly recognized, their broader adoption is limited by clinical and economic barriers in many catheterization laboratories. METHODS: The FLASH (fully automated quantitative coronary angiography versus optical coherence tomography guidance for coronary stent implantation) trial is a randomized, investigator-initiated, multicenter, open-label, noninferiority trial comparing the AI-QCA-assisted PCI strategy with optical coherence tomography-guided PCI strategy in patients with significant coronary artery disease. All operators will utilize a novel, standardized AI-QCA software and PCI protocol in the AI-QCA-assisted group. A total of 400 patients will be randomized to either group at a 1:1 ratio. The primary endpoint is the minimal stent area (mm2), determined by the final OCT run after completion of PCI. Clinical follow-up and cost-effectiveness evaluations are planned at 1 month and 6 months for all patients enrolled in the study. RESULTS: Enrollment of a total of 400 patients from the 13 participating centers in South Korea will be completed in February 2024. Follow-up of the last enrolled patients will be completed in August 2024, and primary results will be available by late 2024. CONCLUSION: The FLASH is the first clinical trial to evaluate the feasibility of AI-QCA-assisted PCI, and will provide the clinical evidence on AI-QCA assistance in the field of coronary intervention. CLINICAL TRIAL REGISTRATION: URL: https://www. CLINICALTRIALS: gov. Unique identifier: NCT05388357.

Multi-VENC acquisition of four-dimensional phase-contrast MRI to improve precision of velocity field measurement.

PURPOSE: The present study aims to improve precision of four-dimensional (4D) phase-contrast (PC) MRI technique by using multiple velocity encoding (VENC) parameters. THEORY AND METHODS: The 3D flow fields in an in vitro stenosis phantom and an in vivo ascending aorta were determined using a 4D PC-MRI sequence with multiple VENC values. The velocity field obtained for large VENC was combined with that from small VENC, unless velocity data were lost by phase aliasing and phase dispersion. Noise levels of the combined velocity fields were compared with the increasing overlapping number of VENC parameters. RESULTS: The phantom measurement showed that the multi-VENC acquisition reduced the noise levels in radial and axial velocities (> 24 cm/s at VENC = 300 cm/s) down to 0.80 ± 0.45 cm/s and 5.60 ± 2.63 cm/s, respectively. This increased the velocity-to-noise ratio (VNR) by approximately two-fold to six-fold depending on the locations. As a result, the multi-VENC measurement could visualize the low-velocity recirculating flows more clearly. CONCLUSION: The multi-VENC measurement of 4D PC-MRI sequence increased the VNR distribution by reducing velocity noise. The improved VNR can be beneficial for investigating blood flow structures in a flow field with a high velocity dynamic range.

Four-dimensional flow MRI for evaluation of post-stenotic turbulent flow in a phantom: comparison with flowmeter and computational fluid dynamics.

OBJECTIVES: To validate 4D flow MRI in a flow phantom using a flowmeter and computational fluid dynamics (CFD) as reference. METHODS: Validation of 4D flow MRI was performed using flow phantoms with 75 % and 90 % stenosis. The effect of spatial resolution on flow rate, peak velocity and flow patterns was investigated in coronal and axial scans. The accuracy of flow rate with 4D flow MRI was evaluated using a flowmeter as reference, and the peak velocity and flow patterns obtained were compared with CFD analysis results. RESULTS: 4D flow MRI accurately measured the flow rate in proximal and distal regions of the stenosis (percent error ≤3.6 % in axial scanning with 1.6-mm resolution). The peak velocity of 4D flow MRI was underestimated by more than 22.8 %, especially from the second half of the stenosis. With 1-mm isotropic resolution, the maximum thickness of the recirculating flow region was estimated within a 1-mm difference, but the turbulent velocity fluctuations mostly disappeared in the post-stenotic region. CONCLUSION: 4D flow MRI accurately measures the flow rates in the proximal and distal regions of a stenosis in axial scan but has limitations in its estimation of peak velocity and turbulent characteristics. KEY POINTS: • 4D flow MRI accurately measures the flow rate in axial scan. • The peak velocity was underestimated by 4D flow MRI. •4D flow MRI demonstrates the principal pattern of post-stenotic flow.

Optimal Minimal Stent Area and Impact of Stent Underexpansion in Left Main Up-Front 2-Stent Strategy.

BACKGROUND: We previously reported the use of minimal stent area to predict angiographic in-stent restenosis after drug-eluting stent implantation for unprotected left main (LM) disease. We aimed to evaluate the optimal minimal stent area criteria for up-front LM 2-stenting based on long-term clinical outcomes. METHODS: We identified 292 consecutive patients with LM bifurcation stenosis who were treated using the crush technique. The final minimal stent area was measured in the ostial left anterior descending artery (LAD), ostial left circumflex artery (LCX), and distal LM. The primary outcome was 5-year major adverse cardiac events, including all-cause death, myocardial infarction, and target lesion revascularization. RESULTS: The minimal stent area cutoff values that best predicted the 5-year major adverse cardiac events were 11.8 mm2 for distal LM (area under the curve, 0.57; P=0.15), 8.3 mm2 for LAD ostium (area under the curve, 0.62; P=0.02), and 5.7 mm2 for LCX ostium (area under the curve, 0.64; P=0.01). Using these criteria, the risk of 5-year major adverse cardiac events was significantly associated with stent underexpansion in the LAD ostium (hazard ratio, 3.14; [95% CI, 1.23-8.06]; P=0.02) and LCX ostium (hazard ratio, 2.60 [95% CI, 1.11-6.07]; P=0.03) but not in the distal LM (hazard ratio, 0.81 [95% CI, 0.34-1.91]; P=0.63). Patients with stent underexpansion in both ostial LAD and LCX had a significantly higher rate of 5-year major adverse cardiac events than those with no or 1 underexpanded stent of either ostium (P<0.01). CONCLUSIONS: Stent underexpansion in the LAD and LCX ostium was significantly associated with long-term outcomes in patients who underwent up-front 2-stenting for LM bifurcation stenosis.

Artificial intelligence-based quantitative coronary angiography of major vessels using deep-learning.

BACKGROUND: Quantitative coronary angiography (QCA) offers objective and reproducible measures of coronary lesions. However, significant inter- and intra-observer variability and time-consuming processes hinder the practical application of on-site QCA in the current clinical setting. This study proposes a novel method for artificial intelligence-based QCA (AI-QCA) analysis of the major vessels and evaluates its performance. METHODS: AI-QCA was developed using three deep-learning models trained on 7658 angiographic images from 3129 patients for the precise delineation of lumen boundaries. An automated quantification method, employing refined matching for accurate diameter calculation and iterative updates of diameter trend lines, was embedded in the AI-QCA. A separate dataset of 676 coronary angiography images from 370 patients was retrospectively analyzed to compare AI-QCA with manual QCA performed by expert analysts. A match was considered between manual and AI-QCA lesions when the minimum lumen diameter (MLD) location identified manually coincided with the location identified by AI-QCA. Matched lesions were evaluated in terms of diameter stenosis (DS), MLD, reference lumen diameter (RLD), and lesion length (LL). RESULTS: AI-QCA exhibited a sensitivity of 89% in lesion detection and strong correlations with manual QCA for DS, MLD, RLD, and LL. Among 995 matched lesions, most cases (892 cases, 80%) exhibited DS differences ≤10%. Multiple lesions of the major vessels were accurately identified and quantitatively analyzed without manual corrections. CONCLUSION: AI-QCA demonstrates promise as an automated tool for analysis in coronary angiography, offering potential advantages for the quantitative assessment of coronary lesions and clinical decision-making.

Deep-Learning Segmentation of Urinary Stones in Noncontrast Computed Tomography.

Background: Noncontrast CT (NCCT) relies on labor-intensive examinations of CT slices to identify urolithiasis in the urinary tract, and, despite the use of deep-learning algorithms, false positives remain. Materials and Methods: A total of 410 NCCT axial scans from patients undergoing surgical treatment for urolithiasis were used for model development. The deep learning model was customized to combine a urolithiasis segmentation with per-slice classification for screening. Prediction models of the axial, coronal, and sagittal views were trained, and an additive model with an intersection of the coronal and sagittal predictions added to the axial outcome was introduced. Automated quantification of clinical metrics was evaluated in three-dimensional models of urinary stones. Results: The axial model detected 88.92% of urinary stones and produced a dice similarity coefficient of 87.56% in the urolithiasis segmentation. For urolithiasis (>5 mm), the sensitivity of the axial model reached 95.10%. False positives were reduced to 0.34 per patient using an ensemble of individual models. The additive model improved the sensitivity to 90.97% by detecting more small urolithiasis (<5 mm). All clinical metrics of size, long-axis diameter, volume, mean stone density, stone heterogeneity index, and skin-to-stone distance showed a strong correlation of R2 > 0.964. Conclusions: The proposed system could reduce the burden on the physician for imaging diagnosis and help determine treatment strategies for urinary stones through automated quantification of clinical metrics with high accuracy and reproducibility.

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography.

BACKGROUND: Invasive coronary angiography (ICA) is a primary imaging modality that visualizes the lumen area of coronary arteries for diagnosis and interventional guidance. In the current practice of quantitative coronary analysis (QCA), semi-automatic segmentation tools require labor-intensive and time-consuming manual correction, limiting their application in the catheterization room. PURPOSE: This study aims to propose rank-based selective ensemble methods that improve the segmentation performance and reduce morphological errors that limit fully automated quantification of coronary artery using deep-learning segmentation of ICA. METHODS: Two selective ensemble methods proposed in this work integrated the weighted ensemble approach with per-image quality estimation. The segmentation outcomes from five base models with different loss functions were ranked either by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranks. The ranking criteria based on mask morphology were formulated from empirical insight to avoid frequent types of segmentation errors (MSEN), while the estimation of DSCs was performed by comparing the pseudo-ground truth generated from a meta-learner (ESEN). Five-fold cross-validation was performed with the internal dataset of 7426 coronary angiograms from 2924 patients, and prediction model was externally validated with 556 images of 226 patients. RESULTS: The selective ensemble methods improved the segmentation performance with DSCs up to 93.07% and provided a better delineation of coronary lesion with local DSCs of up to 93.93%, outperforming all individual models. Proposed methods also minimized the chances of mask disconnection in the most narrowed regions to 2.10%. The robustness of the proposed methods was also evident in the external validation. Inference time for major vessel segmentation was approximately one-sixth of a second. CONCLUSION: Proposed methods successfully reduced morphological errors in the predicted masks and were able to enhance the robustness of the automatic segmentation. The results suggest better applicability of real-time QCA-based diagnostic methods in routine clinical settings.

Automated multi-class classification for prediction of tympanic membrane changes with deep learning models.

BACKGROUNDS AND OBJECTIVE: Evaluating the tympanic membrane (TM) using an otoendoscope is the first and most important step in various clinical fields. Unfortunately, most lesions of TM have more than one diagnostic name. Therefore, we built a database of otoendoscopic images with multiple diseases and investigated the impact of concurrent diseases on the classification performance of deep learning networks. STUDY DESIGN: This retrospective study investigated the impact of concurrent diseases in the tympanic membrane on diagnostic performance using multi-class classification. A customized architecture of EfficientNet-B4 was introduced to predict the primary class (otitis media with effusion (OME), chronic otitis media (COM), and 'None' without OME and COM) and secondary classes (attic cholesteatoma, myringitis, otomycosis, and ventilating tube). RESULTS: Deep-learning classifications accurately predicted the primary class with dice similarity coefficient (DSC) of 95.19%, while misidentification between COM and OME rarely occurred. Among the secondary classes, the diagnosis of attic cholesteatoma and myringitis achieved a DSC of 88.37% and 88.28%, respectively. Although concurrent diseases hampered the prediction performance, there was only a 0.44% probability of inaccurately predicting two or more secondary classes (29/6,630). The inference time per image was 2.594 ms on average. CONCLUSION: Deep-learning classification can be used to support clinical decision-making by accurately and reproducibly predicting tympanic membrane changes in real time, even in the presence of multiple concurrent diseases.

Deep-learning segmentation of ultrasound images for automated calculation of the hydronephrosis area to renal parenchyma ratio.

PURPOSE: We investigated the feasibility of measuring the hydronephrosis area to renal parenchyma (HARP) ratio from ultrasound images using a deep-learning network. MATERIALS AND METHODS: The coronal renal ultrasound images of 195 pediatric and adolescent patients who underwent pyeloplasty to repair ureteropelvic junction obstruction were retrospectively reviewed. After excluding cases without a representative longitudinal renal image, we used a dataset of 168 images for deep-learning segmentation. Ten novel networks, such as combinations of DeepLabV3+ and UNet++, were assessed for their ability to calculate hydronephrosis and kidney areas, and the ensemble method was applied for further improvement. By dividing the image set into four, cross-validation was conducted, and the segmentation performance of the deep-learning network was evaluated using sensitivity, specificity, and dice similarity coefficients by comparison with the manually traced area. RESULTS: All 10 networks and ensemble methods showed good visual correlation with the manually traced kidney and hydronephrosis areas. The dice similarity coefficient of the 10-model ensemble was 0.9108 on average, and the best 5-model ensemble had a dice similarity coefficient of 0.9113 on average. We included patients with severe hydronephrosis who underwent renal ultrasonography at a single institution; thus, external validation of our algorithm in a heterogeneous ultrasonography examination setup with a diverse set of instruments is recommended. CONCLUSIONS: Deep-learning-based calculation of the HARP ratio is feasible and showed high accuracy for imaging of the severity of hydronephrosis using ultrasonography. This algorithm can help physicians make more accurate and reproducible diagnoses of hydronephrosis using ultrasonography.

Impact of Serial Coronary Stenoses on Various Coronary Physiologic Indices.

BACKGROUND: Determining the functional significance of each individual coronary lesion in patients with serial coronary stenoses is challenging. It has been proposed that nonhyperemic pressure ratios, such as the instantaneous wave free ratio (iFR) and the ratio of resting distal to proximal coronary pressure (Pd/Pa) are more accurate than fractional flow reserve (FFR) because autoregulation should maintain stable resting coronary flow and avoid hemodynamic interdependence (cross-talk) that occurs during hyperemia. This study aimed to measure the degree of hemodynamic interdependence of iFR, resting Pd/Pa, and FFR in a porcine model of serial coronary stenosis. METHODS: In 6 anesthetized female swine, 381 serial coronary stenoses were created in the left anterior descending artery using 2 balloon catheters. The degree of hemodynamic interdependence was calculated by measuring the absolute changes in iFR, resting Pd/Pa, and FFR across the fixed stenosis as the severity of the other stenosis varied. RESULTS: The hemodynamic interdependence of iFR, resting Pd/Pa, and FFR was 0.039±0.048, 0.021±0.026, and 0.034±0.034, respectively (all P<0.001). When the functional significance of serial stenoses was less severe (0.70-0.90 for each index), the hemodynamic interdependence was 0.009±0.020, 0.007±0.013, and 0.017±0.022 for iFR, resting Pd/Pa, and FFR, respectively (all P<0.001). However, in more severe serial coronary stenoses (<0.60 for each index), hemodynamic interdependence was 0.060±0.050, 0.037±0.030, and 0.051±0.037 for iFR, resting Pd/Pa, and FFR, respectively (all P<0.001). CONCLUSIONS: When assessing serial coronary stenoses, nonhyperemic pressure ratios are affected by hemodynamic interdependence. When the functional significance of serial coronary stenoses is severe, the effect is similar to that which is seen with FFR.