OCT-Guided versus Angiography-Guided Coronary Stent Implantation in Complex Lesions: An ILUMIEN IV Substudy.

BACKGROUND: ILUMIEN IV was the first large-scale, multicenter, randomized trial comparing optical coherence tomography (OCT)-guided versus angiography-guided stent implantation in patients with high-risk clinical characteristics and/or complex angiographic lesions. OBJECTIVE: Here, we aimed to specifically examine outcomes in the complex angiographic lesions subgroup. METHODS: From the original trial population (n=2487), high-risk patients without complex angiographic lesions were excluded (n=514). Complex angiographic lesion characteristics included 1) long or multiple lesions with intended total stent length ≥28 mm; 2) bifurcation lesion with intended two-stent strategy; 3) severely calcified lesion; 4) chronic total occlusion; or 5) in-stent restenosis. The study endpoints were 1) final minimal stent area (MSA); 2) 2-year composite of serious major adverse cardiovascular events (MACE; cardiac death, target-vessel myocardial infarction (MI), or stent thrombosis); and 3) 2-year effectiveness, defined as target-vessel failure (TVF), a composite of cardiac death, target-vessel MI, or ischemia-driven target-vessel revascularization. RESULTS: The post-PCI MSA was larger in the OCT- (n=992) versus angiography-guided (n=981) group (5.56±1.95 versus 5.26±1.81mm2; difference, 0.30; 95% confidence interval [CI], 0.14-0.47; P<0.001). Compared with angiography-guided PCI, OCT-guided PCI resulted in a lower risk of serious MACE (3.1% versus 4.9%; hazard ratio [HR], 0.63; 95% CI, 0.40-0.99; P=0.04). TVF was not significantly different between groups (7.3% versus 8.8%; HR, 0.82; 95% CI, 0.59-1.12; P=0.20). CONCLUSIONS: In complex angiographic lesions, OCT-guided PCI led to a larger MSA and reduced the serious MACE composite of cardiac death, target-vessel MI, or stent thrombosis compared with angiography-guided PCI at 2 years, but did not significantly improve TVF.

Use and performance of the evolut FX transcatheter aortic valve system.

BACKGROUND: The next generation supra-annular, self-expanding Evolut FX transcatheter aortic valve (TAV) system was designed to improve catheter deliverability, provide stable and symmetric valve deployment, and assess commissural alignment during the procedure. The impact of these modifications has not been clinically evaluated. METHODS: Procedural information was collected by survey in 2 Stages: Stage I comprised 23 centers with extensive experience with Evolut TAV systems, and Stage II comprised an additional 46 centers with a broad range of balloon- and self-expanding system experience. Operators were to compare the experience with the Evolut FX to the predicate Evolut PRO+ system. RESULTS: There were 285 cases during Stage I from June 24 to August 12, 2022, and 254 cases during Stage II from August 15 to September 11, 2022. Overall, the cusp overlap technique was used in 88.6 %, and commissural alignment was achieved in 96.1 % of these cases. Compared to implanter's previous experience with the Evolut PRO+ system, less resistance was noted with the Evolut FX system: in 83.0 % of cases during vascular insertion, in 84.7 % of cases while tracking through the vasculature, in 84.4 % of cases while traversing over the arch, and 76.1 % of cases in advancing across the valve. Better symmetry of valve depth was observed in 423 of 525 cases (80.6 %). CONCLUSION: Evolut FX system design modifications translated into improvements in catheter deliverability, deployment symmetry and stability, and commissural alignment as assessed by experienced self-expanding and balloon expandable operators.

Optical Coherence Tomography-Based Functional Stenosis Assessment: FUSION-A Prospective Multicenter Trial.

BACKGROUND: Intravascular imaging and intracoronary physiology may both be used to guide and optimize percutaneous coronary intervention; however, they are rarely used together. The virtual flow reserve (VFR) is an optical coherence tomography (OCT)-based model of fractional flow reserve (FFR) facilitating the assessment of the physiological significance of coronary lesions. We aimed to validate the VFR assessment of intermediate coronary artery stenoses. METHODS: FUSION (Validation of OCT-Based Functional Diagnosis of Coronary Stenosis) was a multicenter, prospective, observational study comparing OCT-derived VFR to invasive FFR. VFR was mathematically derived from a lumped parameter flow model based on 3-dimensional lumen morphology. Patients undergoing coronary angiography with intermediate angiographic stenosis (40%-90%) requiring physiological assessment were enrolled. Investigational sites were blinded to the VFR analysis, and all OCT and FFR data were reviewed by an independent core laboratory. The coprimary end points were the sensitivity and specificity of VFR against FFR as the reference standard, each of which was tested against prespecified performance goals. RESULTS: After core laboratory review, 266 vessels in 224 patients from 25 US centers were included in the analysis. The mean angiographic diameter stenosis was 65.5%±14.9%, and the mean FFR was 0.83±0.11. Overall accuracy, sensitivity, and specificity of VFR versus FFR using a binary cutoff point of 0.80 were 82.0%, 80.4%, and 82.9%, respectively. The 97.5% lower confidence bound met the prespecified performance goal for sensitivity (71.6% versus 70%; P=0.01) and specificity (76.6% versus 75%; P=0.01). The area under the curve was 0.88 (95% CI, 0.84-0.92; P<0.0001). CONCLUSIONS: OCT-derived VFR demonstrates high sensitivity and specificity for predicting invasive FFR. Integrating high-resolution intravascular imaging with imaging-derived physiology may provide synergistic benefits as an adjunct to percutaneous coronary intervention. REGISTRATION: URL: https://clinicaltrials.gov; Unique identifier: NCT04356027.

Deep learning segmentation of fibrous cap in intravascular optical coherence tomography images.

Thin-cap fibroatheroma (TCFA) is a prominent risk factor for plaque rupture. Intravascular optical coherence tomography (IVOCT) enables identification of fibrous cap (FC), measurement of FC thicknesses, and assessment of plaque vulnerability. We developed a fully-automated deep learning method for FC segmentation. This study included 32,531 images across 227 pullbacks from two registries (TRANSFORM-OCT and UHCMC). Images were semi-automatically labeled using our OCTOPUS with expert editing using established guidelines. We employed preprocessing including guidewire shadow detection, lumen segmentation, pixel-shifting, and Gaussian filtering on raw IVOCT (r,θ) images. Data were augmented in a natural way by changing θ in spiral acquisitions and by changing intensity and noise values. We used a modified SegResNet and comparison networks to segment FCs. We employed transfer learning from our existing much larger, fully-labeled calcification IVOCT dataset to reduce deep-learning training. Postprocessing with a morphological operation enhanced segmentation performance. Overall, our method consistently delivered better FC segmentation results (Dice: 0.837 ± 0.012) than other deep-learning methods. Transfer learning reduced training time by 84% and reduced the need for more training samples. Our method showed a high level of generalizability, evidenced by highly-consistent segmentations across five-fold cross-validation (sensitivity: 85.0 ± 0.3%, Dice: 0.846 ± 0.011) and the held-out test (sensitivity: 84.9%, Dice: 0.816) sets. In addition, we found excellent agreement of FC thickness with ground truth (2.95 ± 20.73 µm), giving clinically insignificant bias. There was excellent reproducibility in pre- and post-stenting pullbacks (average FC angle: 200.9 ± 128.0°/202.0 ± 121.1°). Our fully automated, deep-learning FC segmentation method demonstrated excellent performance, generalizability, and reproducibility on multi-center datasets. It will be useful for multiple research purposes and potentially for planning stent deployments that avoid placing a stent edge over an FC.

Early use of intrapartum intra-aortic balloon pump support for haemodynamic stabilization of peripartum and anthracycline-induced cardiomyopathy: a case report.

Background: Prior exposure to cardiotoxic cancer therapies has been associated with an increased risk of peripartum cardiomyopathy (PPCM). The management of PPCM in this population remains a clinical challenge. Few studies have explored the use of mechanical circulatory support in PPCM. We present a case of early implementation of intra-aortic balloon pump (IABP) therapy for acute stabilization and intrapartum support of PPCM. Case summary: A 36-year-old G4P2103 (4th pregnancy, two full-term, one premature birth, 0 abortions, and three living children) woman at 26 weeks and 5 days gestation with history of combined peripartum and anthracycline-induced cardiomyopathy [previously left ventricular ejection fraction (LVEF) 10-15% and recently 40-45%] presented with acute decompensated heart failure. Her clinical status deteriorated with a drop in LVEF to 15-20% with a significant increase in pulmonary pressures and worsening mitral regurgitation. A multidisciplinary decision with the cardio-obstetrics team was made to place a pulmonary artery catheter for invasive haemodynamic monitoring and IABP insertion prior to delivery. Intra-aortic balloon pump support had a profound immediate decrease in her systemic and pulmonary vascular resistance allowing for a successful repeat caesarean delivery. Her haemodynamics remained stable after IABP removal and pulmonary pressures improved. She was discharged one week following her delivery on guideline-directed medical therapy. Discussion: Our case highlights the use of prophylactic intrapartum IABP in combined anthracycline-induced and PPCM and begins to explore its safety and efficacy in this high-risk patient population.

Correction: Referral for Cardiac Amyloidosis in Patients Who Underwent Transcatheter Aortic Valve Replacement: Results of the Quality Outcome Project.

[This corrects the article DOI: 10.7759/cureus.45024.].

Referral for Cardiac Amyloidosis in Patients Who Underwent Transcatheter Aortic Valve Replacement: Results of the Quality Outcome Project.

Background Transthyretin cardiac amyloidosis (ATTR) is an important comorbidity present in severe aortic stenosis (AS). The purpose of this study was to raise awareness of ATTR in patients who underwent transcatheter aortic valve replacement (TAVR) for severe AS among healthcare providers and patients. Methodology We reviewed 197 consecutive TAVR cases performed from 2019 to 2020. Adapting predefined high-risk features for ATTR based on prior literature, we contacted the patients to discuss our clinical suspicion of ATTR and offered a referral to a cardiac amyloid specialist. Results We identified 125 (69.4%) patients who had high-risk features of ATTR. Of the 105 patients contacted, 44 patients agreed to referral, 46 patients were not able to be contacted after several attempts, and 15 patients declined referral. Of the 44 patients who agreed to the referral, 20 patients completed the evaluation for cardiac amyloidosis, all of whom were negative for transthyretin and light-chain cardiac amyloidosis. Conclusions Our attempt to detect ATTR in prior TAVR patients was unsuccessful two to three years post-TAVR. We believe that early detection of cardiac amyloidosis close to the timing of TAVR is important and the most effective means.

Load-sharing characteristics of stenting and post-dilation in heavily calcified coronary artery.

In this work, stenting in non-calcified and heavily calcified coronary arteries was quantified in terms of diameter-pressure relationships and load transfer from the balloon to the artery. The efficacy of post-dilation in non-calcified and heavily calcified coronary arteries was also characterized in terms of load sharing and the changes in tissue mechanics. Our results have shown that stent expansion exhibits a cylindrical shape in non-calcified lesions, while it exhibits a dog bone shape in heavily calcified lesions. Load-sharing analysis has shown that only a small portion of the pressure load (1.4 N, 0.8% of total pressure load) was transferred to the non-calcified lesion, while a large amount of the pressure load (19 N, 12%) was transferred to the heavily calcified lesion. In addition, the increasing inflation pressure (from 10 to 20 atm) can effectively increase the minimal lumen diameter (from 1.48 to 2.82 mm) of the heavily calcified lesion, the stress (from 1.5 to 8.4 MPa) and the strain energy in the calcification (1.77 mJ to 26.5 mJ), which are associated with the potential of calcification fracture. Results indicated that increasing inflation pressure can be an effective way to improve the stent expansion if a dog bone shape of the stenting profile is observed. Considering the risk of a balloon burst, our results support the design and application of the high-pressure balloon for post-dilation. This work also sheds some light on the stent design and choice of stent materials for improving the stent expansion at the dog bone region and mitigating stresses on arterial tissues.

Prediction of stent under-expansion in calcified coronary arteries using machine learning on intravascular optical coherence tomography images.

It can be difficult/impossible to fully expand a coronary artery stent in a heavily calcified coronary artery lesion. Under-expanded stents are linked to later complications. Here we used machine/deep learning to analyze calcifications in pre-stent intravascular optical coherence tomography (IVOCT) images and predicted the success of vessel expansion. Pre- and post-stent IVOCT image data were obtained from 110 coronary lesions. Lumen and calcifications in pre-stent images were segmented using deep learning, and lesion features were extracted. We analyzed stent expansion along the lesion, enabling frame, segmental, and whole-lesion analyses. We trained regression models to predict the post-stent lumen area and then computed the stent expansion index (SEI). Best performance (root-mean-square-error = 0.04 ± 0.02 mm2, r = 0.94 ± 0.04, p < 0.0001) was achieved when we used features from both lumen and calcification to train a Gaussian regression model for segmental analysis of 31 frames in length. Stents with minimum SEI > 80% were classified as "well-expanded;" others were "under-expanded." Under-expansion classification results (e.g., AUC = 0.85 ± 0.02) were significantly improved over a previous, simple calculation, as well as other machine learning solutions. Promising results suggest that such methods can identify lesions at risk of under-expansion that would be candidates for intervention lesion preparation (e.g., atherectomy).

Optical Coherence Tomography-Guided versus Angiography-Guided PCI.

BACKGROUND: Data regarding clinical outcomes after optical coherence tomography (OCT)-guided percutaneous coronary intervention (PCI) as compared with angiography-guided PCI are limited. METHODS: In this prospective, randomized, single-blind trial, we randomly assigned patients with medication-treated diabetes or complex coronary-artery lesions to undergo OCT-guided PCI or angiography-guided PCI. A final blinded OCT procedure was performed in patients in the angiography group. The two primary efficacy end points were the minimum stent area after PCI as assessed with OCT and target-vessel failure at 2 years, defined as a composite of death from cardiac causes, target-vessel myocardial infarction, or ischemia-driven target-vessel revascularization. Safety was also assessed. RESULTS: The trial was conducted at 80 sites in 18 countries. A total of 2487 patients underwent randomization: 1233 patients were assigned to undergo OCT-guided PCI, and 1254 to undergo angiography-guided PCI. The minimum stent area after PCI was 5.72±2.04 mm2 in the OCT group and 5.36±1.87 mm2 in the angiography group (mean difference, 0.36 mm2; 95% confidence interval [CI], 0.21 to 0.51; P<0.001). Target-vessel failure within 2 years occurred in 88 patients in the OCT group and in 99 patients in the angiography group (Kaplan-Meier estimates, 7.4% and 8.2%, respectively; hazard ratio, 0.90; 95% CI, 0.67 to 1.19; P = 0.45). OCT-related adverse events occurred in 1 patient in the OCT group and in 2 patients in the angiography group. Stent thrombosis within 2 years occurred in 6 patients (0.5%) in the OCT group and in 17 patients (1.4%) in the angiography group. CONCLUSIONS: Among patients undergoing PCI, OCT guidance resulted in a larger minimum stent area than angiography guidance, but there was no apparent between-group difference in the percentage of patients with target-vessel failure at 2 years. (Funded by Abbott; ILUMIEN IV: OPTIMAL PCI ClinicalTrials.gov number, NCT03507777.).

Load-sharing characteristics of stenting and post-dilation in heavily calcified coronary artery.

In this work, stenting in non-calcified and heavily calcified coronary arteries was quantified in terms of diameter-pressure relationships and load transfer from the balloon to the artery. The efficacy of post-dilation in non-calcified and heavily calcified coronary arteries was also characterized in terms of load sharing and the changes in tissue mechanics. Our results have shown that stent expansion exhibits a cylindrical shape in non-calcified lesions, while it exhibits a dog bone shape in heavily calcified lesions. Load-sharing analysis has shown that only a small portion of the pressure load (1.4 N, 0.8% of total pressure load) was transferred to the non-calcified lesion, while a large amount of the pressure load (19 N, 12%) was transferred to the heavily calcified lesion. In addition, the increasing inflation pressure (from 10 to 20 atm) can effectively increase the minimal lumen diameter (from 1.48 mm to 2.82 mm) of the heavily calcified lesion, the stress (from 1.5 MPa to 8.4 MPa) the strain energy in the calcification (1.77 mJ to 26.5 mJ), which associated with the potential of calcification fracture. Results indicated that increasing inflation pressure can be an effective way to improve the stent expansion if a dog bone shape of the stenting profile is observed. Considering the risk of a balloon burst, our results support the design and application of the high-pressure balloon for post-dilation.

Randomized comparison of 9-month stent strut coverage of biolimus and everolimus drug-eluting stents assessed by optical coherence tomography in patients with ST-segment elevation myocardial infarction. Long-term (5-years) clinical follow-up (ROBUST trial).

BACKGROUND: The aim of the study was to compare healing (assessed by optical coherence tomography [OCT]) of biolimus A9 (BES) and everolimus drug-eluting stents (EES) at 9-month follow-up in patients with ST-segment elevation myocardial infarction (STEMI) treated by primary percutaneous coronary intervention (pPCI). Nine-month clinical and angiographic data were also compared in both groups as well as clinical data at 5 years of follow-up. METHODS: A total of 201 patients with STEMI were enrolled in the study and randomized either to pPCI with BES or EES implantation. All patients were scheduled for 9 months of angiographic and OCT follow-up. RESULTS: The rate of major adverse cardiovascular events (MACE) was comparable at 9 months in both groups (5% in BES vs. 6% in the EES group; p = 0.87). Angiographic data were also comparable between both groups. The main finding at 9-month OCT analysis was the greatly reduced extent of mean neointimal area at the cost of a higher proportion of uncovered struts in the BES group (1.3 mm² vs. 0.9 mm²; p = 0.0001 and 15.9% vs. 7.0%; p = 0.0001, respectively). At 5 years of clinical follow-up the rate of MACE was comparable between both groups (16.8% vs. 14.0%, p = 0.74). CONCLUSIONS: The study demonstrates a very low rate of MACE and good 9-month stent strut coverage of second-generation BES and EES in patients with STEMI. BES showed greatly reduced extent of mean neointimal hyperplasia area at the cost of a higher proportion of uncovered struts when compared to EES. The rate of MACE was low and comparable in both groups at 5 years.

OCTOPUS - Optical coherence tomography plaque and stent analysis software.

Background and objective: Compared with other imaging modalities, intravascular optical coherence tomography (IVOCT) has significant advantages for guiding percutaneous coronary interventions, assessing their outcomes, and characterizing plaque components. To aid IVOCT research studies, we developed the Optical Coherence TOmography PlaqUe and Stent (OCTOPUS) analysis software, which provides highly automated, comprehensive analysis of coronary plaques and stents in IVOCT images. Methods: User specifications for OCTOPUS were obtained from detailed, iterative discussions with IVOCT analysts in the Cardiovascular Imaging Core Laboratory at University Hospitals Cleveland Medical Center, a leading laboratory for IVOCT image analysis. To automate image analysis results, the software includes several important algorithmic steps: pre-processing, deep learning plaque segmentation, machine learning identification of stent struts, and registration of pullbacks for sequential comparisons. Intuitive, interactive visualization and manual editing of segmentations were included in the software. Quantifications include stent deployment characteristics (e.g., stent area and stent strut malapposition), strut level analysis, calcium angle, and calcium thickness measurements. Interactive visualizations include (x,y) anatomical, en face, and longitudinal views with optional overlays (e.g., segmented calcifications). To compare images over time, linked visualizations were enabled to display up to four registered vessel segments at a time. Results: OCTOPUS has been deployed for nearly 1 year and is currently being used in multiple IVOCT studies. Underlying plaque segmentation algorithm yielded excellent pixel-wise results (86.2% sensitivity and 0.781 F1 score). Using OCTOPUS on 34 new pullbacks, we determined that following automated segmentation, only 13% and 23% of frames needed any manual touch up for detailed lumen and calcification labeling, respectively. Only up to 3.8% of plaque pixels were modified, leading to an average editing time of only 7.5 s/frame, an approximately 80% reduction compared to manual analysis. Regarding stent analysis, sensitivity and precision were both greater than 90%, and each strut was successfully classified as either covered or uncovered with high sensitivity (94%) and specificity (90%). We demonstrated use cases for sequential analysis. To analyze plaque progression, we loaded multiple pullbacks acquired at different points (e.g., pre-stent, 3-month follow-up, and 18-month follow-up) and evaluated frame-level development of in-stent neo-atherosclerosis. In ex vivo cadaver experiments, the OCTOPUS software enabled visualization and quantitative evaluation of irregular stent deployment in the presence of calcifications identified in pre-stent images. Conclusions: We introduced and evaluated the clinical application of a highly automated software package, OCTOPUS, for quantitative plaque and stent analysis in IVOCT images. The software is currently used as an offline tool for research purposes; however, the software's embedded algorithms may also be useful for real-time treatment planning.

Use of a Pressure Wire for Automatically Correcting Artifacts in Phasic Pressure Tracings From a Fluid-Filled Catheter.

BACKGROUND/PURPOSE: Matching phasic pressure tracings between a fluid-filled catheter and high-fidelity pressure wire has received limited attention, although each part contributes half of the information to clinical decisions. We aimed to study the impact of a novel and automated method for improving the phasic calibration of a fluid-filled catheter by accounting for its oscillatory behavior. METHODS/MATERIALS: Retrospective analysis of drift check tracings was performed using our algorithm that corrects for mean difference (offset), temporal delays (timing), differential sensitivity of the manifold transducer and pressure wire sensor (gain), and the oscillatory behavior of the fluid-filled catheter described by its resonant frequency and damping factor (how quickly oscillations disappear after a change in pressure). RESULTS: Among 2886 cases, correcting for oscillations showed a large improvement in 28 % and a medium improvement in 41 % (decrease in root mean square error >0.5 mmHg to <1 or 1-2 mmHg, respectively). 96 % of oscillators were underdamped with median damping factor 0.27 and frequency 10.6 Hz. Fractional flow reserve or baseline Pd/Pa demonstrated no clinically important bias when ignoring oscillations. However, uncorrected subcycle non-hyperemic pressure ratios (NHPR) displayed both bias and scatter. CONCLUSIONS: By automatically accounting for the oscillatory behavior of a fluid-filled catheter system, phasic matching against a high-fidelity pressure wire can be improved compared to standard equalization methods. The majority of tracings contain artifacts, mainly due to underdamped oscillations, and neglecting them leads to biased estimates of equalization parameters. No clinically important bias exists for whole-cycle metrics, in contrast to significant effects on subcycle NHPR.

Automatic microchannel detection using deep learning in intravascular optical coherence tomography images.

Microchannel formation is known to be a significant marker of plaque vulnerability, plaque rupture, and intraplaque hemorrhage, which are responsible for plaque progression. We developed a fully-automated method for detecting microchannels in intravascular optical coherence tomography (IVOCT) images using deep learning. A total of 3,075 IVOCT image frames across 41 patients having 62 microchannel segments were analyzed. Microchannel was manually annotated by expert cardiologists, according to previously established criteria. In order to improve segmentation performance, pre-processing including guidewire detection/removal, lumen segmentation, pixel-shifting, and noise filtering was applied to the raw (r,θ) IVOCT image. We used the DeepLab-v3 plus deep learning model with the Xception backbone network for identifying microchannel candidates. After microchannel candidate detection, each candidate was classified as either microchannel or no-microchannel using a convolutional neural network (CNN) classification model. Our method provided excellent segmentation of microchannel with a Dice coefficient of 0.811, sensitivity of 92.4%, and specificity of 99.9%. We found that pre-processing and data augmentation were very important to improve results. In addition, a CNN classification step was also helpful to rule out false positives. Furthermore, automated analysis missed only 3% of frames having microchannels and showed no false positives. Our method has great potential to enable highly automated, objective, repeatable, and comprehensive evaluations of vulnerable plaques and treatments. We believe that this method is promising for both research and clinical applications.

Automated analysis of fibrous cap in intravascular optical coherence tomography images of coronary arteries.

Thin-cap fibroatheroma (TCFA) and plaque rupture have been recognized as the most frequent risk factor for thrombosis and acute coronary syndrome. Intravascular optical coherence tomography (IVOCT) can identify TCFA and assess cap thickness, which provides an opportunity to assess plaque vulnerability. We developed an automated method that can detect lipidous plaque and assess fibrous cap thickness in IVOCT images. This study analyzed a total of 4360 IVOCT image frames of 77 lesions among 41 patients. Expert cardiologists manually labeled lipidous plaque based on established criteria. To improve segmentation performance, preprocessing included lumen segmentation, pixel-shifting, and noise filtering on the raw polar (r, θ) IVOCT images. We used the DeepLab-v3 plus deep learning model to classify lipidous plaque pixels. After lipid detection, we automatically detected the outer border of the fibrous cap using a special dynamic programming algorithm and assessed the cap thickness. Our method provided excellent discriminability of lipid plaque with a sensitivity of 85.8% and A-line Dice coefficient of 0.837. By comparing lipid angle measurements between two analysts following editing of our automated software, we found good agreement by Bland-Altman analysis (difference 6.7° ± 17°; mean ~ 196°). Our method accurately detected the fibrous cap from the detected lipid plaque. Automated analysis required a significant modification for only 5.5% frames. Furthermore, our method showed a good agreement of fibrous cap thickness between two analysts with Bland-Altman analysis (4.2 ± 14.6 µm; mean ~ 175 µm), indicating little bias between users and good reproducibility of the measurement. We developed a fully automated method for fibrous cap quantification in IVOCT images, resulting in good agreement with determinations by analysts. The method has great potential to enable highly automated, repeatable, and comprehensive evaluations of TCFAs.

Automated Segmentation of Microvessels in Intravascular OCT Images Using Deep Learning.

Microvessels in vascular plaque are associated with plaque progression and are found in plaque rupture and intra-plaque hemorrhage. To analyze this characteristic of vulnerability, we developed an automated deep learning method for detecting microvessels in intravascular optical coherence tomography (IVOCT) images. A total of 8403 IVOCT image frames from 85 lesions and 37 normal segments were analyzed. Manual annotation was performed using a dedicated software (OCTOPUS) previously developed by our group. Data augmentation in the polar (r,θ) domain was applied to raw IVOCT images to ensure that microvessels appear at all possible angles. Pre-processing methods included guidewire/shadow detection, lumen segmentation, pixel shifting, and noise reduction. DeepLab v3+ was used to segment microvessel candidates. A bounding box on each candidate was classified as either microvessel or non-microvessel using a shallow convolutional neural network. For better classification, we used data augmentation (i.e., angle rotation) on bounding boxes with a microvessel during network training. Data augmentation and pre-processing steps improved microvessel segmentation performance significantly, yielding a method with Dice of 0.71 ± 0.10 and pixel-wise sensitivity/specificity of 87.7 ± 6.6%/99.8 ± 0.1%. The network for classifying microvessels from candidates performed exceptionally well, with sensitivity of 99.5 ± 0.3%, specificity of 98.8 ± 1.0%, and accuracy of 99.1 ± 0.5%. The classification step eliminated the majority of residual false positives and the Dice coefficient increased from 0.71 to 0.73. In addition, our method produced 698 image frames with microvessels present, compared with 730 from manual analysis, representing a 4.4% difference. When compared with the manual method, the automated method improved microvessel continuity, implying improved segmentation performance. The method will be useful for research purposes as well as potential future treatment planning.

Fractional Flow Reserve (FFR) Estimation from OCT-Based CFD Simulations: Role of Side Branches.

The computational fluid dynamic method has been widely used to quantify the hemodynamic alterations in a diseased artery and investigate surgery outcomes. The artery model reconstructed based on optical coherence tomography (OCT) images generally does not include the side branches. However, the side branches may significantly affect the hemodynamic assessment in a clinical setting, i.e., the fractional flow reserve (FFR), defined as the ratio of mean distal coronary pressure to mean aortic pressure. In this work, the effect of the side branches on FFR estimation was inspected with both idealized and optical coherence tomography (OCT)-reconstructed coronary artery models. The electrical analogy of blood flow was further used to understand the impact of the side branches (diameter and location) on FFR estimation. Results have shown that the side branches decrease the total resistance of the vessel tree, resulting in a higher inlet flowrate. The side branches located at the downstream of the stenosis led to a lower FFR value, while the ones at the upstream had a minimal impact on the FFR estimation. Side branches with a diameter larger than one third of the main vessel diameter are suggested to be considered for a proper FFR estimation. The findings in this study could be extended to other coronary artery imaging modalities and facilitate treatment planning.