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).

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.

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.

Assessment of Post-Dilatation Strategies for Optimal Stent Expansion in Calcified Coronary Lesions: Ex Vivo Analysis With Optical Coherence Tomography.

INTRODUCTION: Interventional cardiologists make adjustments in the presence of coronary calcifications known to limit stent expansion, but proper balloon sizing, plaque-modification approaches, and high-pressure regimens are not well established. Intravascular optical coherence tomography (IVOCT) provides high-resolution images of coronary tissues, including detailed imaging of calcifications, and accurate measurements of stent deployment, providing a means for detailed study of stent deployment. OBJECTIVE: Evaluate stent expansion in an ex vivo model of calcified coronary arteries as a function of balloon size and high-pressure, post-dilatation strategies. METHODS: We conducted experiments on cadaver hearts with calcified coronary lesions. We assessed stent expansion as a function of size and pressure of non-compliant (NC) balloons (i.e., nominal, 0.5, 1.0, and 1.5 mm balloons at 10, 20 and 30 atm). IVOCT images were acquired pre-stent, post-stent, and at all post-dilatations. Stent expansion was calculated using minimum expansion index (MEI). RESULTS: We analyzed 134 IVOCT pullbacks from ten ex-vivo experiments. The mean distal and proximal reference lumen diameters were 2.2 ± 0.5 mm and 2.5 ± 0.7 mm, respectively, 80% of times using a 3.0 mm diameter stent. Overall, based on stent sizing, a good expansion (MEI ≥ 80%) was reached using the 1:1 NC balloon at 20 atm, and expansion > 100% was reached using the 1:1 NC balloon at 30 atm. In the subgroup analysis, comparing low-calcified and high-calcified lesions, good expansion (MEI ≥ 80%) was reached using the 1:1 NC balloon at nominal pressure (10 atm) versus using 1:1 NC balloon at 30 atm, respectively. Significant vessel rupture was identified in all the vessels mainly upon post-dilatation with larger balloons, and 60% of the experiments (6 vessels, 3 in each calcium subgroup) presented rupture with the +1.0 mm NC balloon at 20 atm. CONCLUSION: When treating calcified lesions, good stent expansion was reached using smaller balloons at higher pressures without coronary injuries, whereas bigger balloons yielded unpredictable expansion even at lower pressures and demonstrated potential harmful damages to the vessels. As these findings could help physicians with appropriate planning of stent post-dilatation for calcified lesions, it will be important to clinically evaluate the recommended protocol.

Hemodynamic alternations following stent deployment and post-dilation in a heavily calcified coronary artery: In silico and ex-vivo approaches.

In this work, hemodynamic alterations in a patient-specific, heavily calcified coronary artery following stent deployment and post-dilations are quantified using in silico and ex-vivo approaches. Three-dimensional artery models were reconstructed from OCT images. Stent deployment and post-dilation with various inflation pressures were performed through both the finite element method (FEM) and ex vivo experiments. Results from FEM agreed very well with the ex-vivo measurements, interms of lumen areas, stent underexpansion, and strut malapposition. In addition, computational fluid dynamics (CFD) simulations were performed to delineate the hemodynamic alterations after stent deployment and post-dilations. A pressure time history at the inlet and a lumped parameter model (LPM) at the outlet were adopted to mimic the aortic pressure and the distal arterial tree, respectively. The pressure drop across the lesion, pertaining to the clinical measure of instantaneous wave-free flow ratio (iFR), was investigated. Results have shown that post-dilations are necessary for the lumen gain as well as the hemodynamic restoration towards hemostasis. Malapposed struts induced much higher shear rate, flow disturbances and lower time-averaged wall shear stress (TAWSS) around struts. Post-dilations mitigated the strut malapposition, and thus the shear rate. Moreover, stenting induced larger area of low TAWSS (<0.4 Pa) and lager volume of high shear rate (>2000 s-1), indicating higher risks of in-stent restenosis (ISR) and stent thrombosis (ST), respectively. Oscillatory shear index (OSI) and relative residence time (RRT) indicated the wall regions more prone to ISR are located near the malapposed stent struts.

Mechanical performances of balloon post-dilation for improving stent expansion in calcified coronary artery: Computational and experimental investigations.

Stent deployment in a calcified coronary artery is often associated with suboptimal outcomes such as stent underexpansion and malapposition. Post-dilation after stent deployment is commonly used for optimal stent implantation. There is no guideline for choosing the post-dilation balloon diameter and inflation pressure. In this work, ex-vivo/in-silico experiments were performed to investigate the efficacy of post-dilation balloon diameter and inflation pressure in improving the stent expansion in a calcified lesion. Post-dilations with three balloon diameters (3 mm, 3.5 mm, and 4 mm) were performed. For each balloon diameter, three inflation pressures (10 atm, 20 atm, and 30 atm) were sequentially applied. In ex-vivo experiments, optical coherence tomography images were acquired during the stenting procedure, i.e., pre- and post-deployment of 3 mm diameter stent, as well as after each post-dilation. The results from in-silico experiments were compared with ex-vivo experiments in terms of lumen area. In addition, stretch ratio analysis was developed to predict the stent-induced lumen area, along with the strain analysis and the in-silico experiments. Results have shown that target lumen area could be achieved with an oversized nominal balloon diameter of +0.5 mm (i.e., 0.5 mm greater than reference lumen diameter) at an inflation pressure of 20 atm. After each post-dilation, fibrotic tissue demonstrated a larger strain, contributing to improved lumen gain. However, minimal changes were observed in calcification. Moreover, a strong correlation (R2 = 0.95) between the stretch ratio of fibrotic tissue and lumen area after each post-dilation was observed. This indicated that the morphology of the fibrotic tissue could be a potential marker to predict the lumen gain. The detailed mechanistic quantifications of a single lesion cannot be generalized to all clinical cases. However, this work could be used to provide a fundamental understanding of the post-dilations, to develop experimental protocols for producing generalized guidelines, and to exploit their potential for optimal pre- and post-stent strategies.

Learning With Fewer Images via Image Clustering: Application to Intravascular OCT Image Segmentation.

Deep learning based methods are routinely used to segment various structures of interest in varied medical imaging modalities. Acquiring annotations for a large number of images requires a skilled analyst, and the process is both time consuming and challenging. Our approach to reduce effort is to reduce the number of images needing detailed annotation. For intravascular optical coherence tomography (IVOCT) image pullbacks, we tested 10% to 100% of training images derived from two schemes: equally-spaced image subsampling and deep-learning- based image clustering. The first strategy involves selecting images at equally spaced intervals from the volume, accounting for the high spatial correlation between neighboring images. In clustering, we used an autoencoder to create a deep feature space representation, performed k-medoids clustering, and then used the cluster medians for training. For coronary calcifications, a baseline U-net model was trained on all images from volumes of interest (VOIs) and compared with fewer images from the sub-sampling strategies. For a given sampling ratio, the clustering based method performed better or similar as compared to the equally spaced sampling approach (e.g., with 10% of images, mean F1 score for calcific class increased from 0.52 to 0.63, with equal spacing and with clustering, respectively). Additionally, for a fixed number of training images, sampling images from more VOIs performed better than otherwise. In conclusion, we recommend the clustering based approach to annotate a small fraction of images, creating a baseline model, which potentially can be improved further by annotating images selected using methods described in active learning research.

Fully automated plaque characterization in intravascular OCT images using hybrid convolutional and lumen morphology features.

For intravascular OCT (IVOCT) images, we developed an automated atherosclerotic plaque characterization method that used a hybrid learning approach, which combined deep-learning convolutional and hand-crafted, lumen morphological features. Processing was done on innate A-line units with labels fibrolipidic (fibrous tissue followed by lipidous tissue), fibrocalcific (fibrous tissue followed by calcification), or other. We trained/tested on an expansive data set (6,556 images), and performed an active learning, relabeling step to improve noisy ground truth labels. Conditional random field was an important post-processing step to reduce classification errors. Sensitivities/specificities were 84.8%/97.8% and 91.4%/95.7% for fibrolipidic and fibrocalcific plaques, respectively. Over lesions, en face classification maps showed automated results that agreed favorably to manually labeled counterparts. Adding lumen morphological features gave statistically significant improvement (p < 0.05), as compared to classification with convolutional features alone. Automated assessments of clinically relevant plaque attributes (arc angle and length), compared favorably to those from manual labels. Our hybrid approach gave statistically improved results as compared to previous A-line classification methods using deep learning or hand-crafted features alone. This plaque characterization approach is fully automated, robust, and promising for live-time treatment planning and research applications.

Degradation modeling of poly-l-lactide acid (PLLA) bioresorbable vascular scaffold within a coronary artery.

In this work, a strain-based degradation model was implemented and validated to better understand the dynamic interactions between the bioresorbable vascular scaffold (BVS) and the artery during the degradation process. Integrating the strain-modulated degradation equation into commercial finite element codes allows a better control and visualization of local mechanical parameters. Both strut thinning and discontinuity of the stent struts within an artery were captured and visualized. The predicted results in terms of mass loss and fracture locations were validated by the documented experimental observations. In addition, results suggested that the heterogeneous degradation of the stent depends on its strain distribution following deployment. Degradation is faster at the locations with higher strains and resulted in the strut thinning and discontinuity, which contributes to the continuous mass loss, and the reduced contact force between the BVS and artery. A nonlinear relationship between the maximum principal strain of the stent and the fracture time was obtained, which could be transformed to predict the degradation process of the BVS in different mechanical environments. The developed computational model provided more insights into the degradation process, which could complement the discrete experimental data for improving the design and clinical management of the BVS.

Automatic A-line coronary plaque classification using combined deep learning and textural features in intravascular OCT images.

We developed a fully automated method for classifying A-line coronary plaques in intravascular optical coherence tomography images using combined deep learning and textural features. The proposed method was trained on 4,292 images from 48 pullbacks giving 80 manually labeled, volumes of interest. Preprocessing steps including guidewire/shadow removal, lumen boundary detection, pixel shifting, and noise reduction were employed. We built a convolutional neural network to extract the deep learning features from the preprocessed image. Traditional textural features were also extracted and combined with deep learning features. Feature selection was performed using the minimum redundancy maximum relevance method. Combined features were utilized as inputs for a random forest classifier. After classification, conditional random field (CRF) method was used for classification noise cleaning. We determined a sub-feature set with the most predictive power. With CRF noise cleaning, sensitivities/specificities were 82.2%/90.8% and 82.4%/89.2% for fibrolipidic and fibrocalcific classes, respectively, with good Dice coefficients. The classification noise cleaning step improved performance metrics by nearly 10-15%. The predicted en face classification maps of entire pullbacks agreed favorably to the manually labeled counterparts. Both assessments suggested that our automated measurements gave clinically relevant results. The proposed method is very promising with regards to both clinical treatment planning and research applications.

Co-registration of pre- and post-stent intravascular OCT images for validation of finite element model simulation of stent expansion.

Intravascular optical coherence tomography (IVOCT) provides high-resolution images of coronary calcifications and detailed measurements of acute stent deployment following stent implantation. Since pre- and post-stent IVOCT image "pull-back" acquisitions start from different locations, registration of corresponding pullbacks is needed for assessing treatment outcomes. In particular, we are interested in assessing finite element model (FEM) prediction of lumen gain following stenting, requiring registration. We used deep learning to segment calcifications in corresponding pre- and post-stent IVOCT pullbacks. We created 1D representations of calcium thickness as a function of the angle of the helical IVOCT scans. Registration of two scans was done by maximizing the cross correlation of these two 1D representations. Registration was accurate, as determined by visual comparisons of 2D image frames. We used our pre-stent calcification segmentations to create a lesion-specific FEM, which took into account balloon size, balloon pressure, and stent measurements. We then compared simulated lumen gain from FEM analysis to actual stent deployment results. Actual lumen gain across ~200 registered pre and post-stent images was 1.52 ± 0.51, while FEM prediction was 1.43 ± 0.41. Comparison between actual and FEM results showed no significant difference (p < 0.001), suggesting accurate prediction of FEM modeling. Registered image data showed good visual agreement regarding lumen gain and stent strut malapposition. Hence, we have developed a platform for evaluation of FEM prediction of lumen gain. This platform can be used to guide development of FEM prediction software, which could ultimately help physicians with stent treatment planning of calcified lesions.

Segmentation of Coronary Calcified Plaque in Intravascular OCT Images Using a Two-Step Deep Learning Approach.

We developed a fully automated, two-step deep learning approach for characterizing coronary calcified plaque in intravascular optical coherence tomography (IVOCT) images. First, major calcification lesions were detected from an entire pullback using a 3D convolutional neural network (CNN). Second, a SegNet deep learning model with the Tversky loss function was used to segment calcified plaques in the major calcification lesions. The fully connected conditional random field and the frame interpolation of the missing calcification frames were used to reduce classification errors. We trained/tested the networks on a large dataset comprising 8,231 clinical images from 68 patients with 68 vessels and 4,320 ex vivo cadaveric images from 4 hearts with 4 vessels. The 3D CNN model detected major calcifications with high sensitivity (97.7%), specificity (87.7%), and F1 score (0.922). Compared to the standard one-step approach, our two-step deep learning approach significantly improved sensitivity (from 77.5% to 86.2%), precision (from 73.5% to 75.8%), and F1 score (from 0.749 to 0.781). We investigated segmentation performance for varying numbers of training samples; at least 3,900 images were required to obtain stable segmentation results. We also found very small differences in calcification attributes (e.g., angle, thickness, and depth) and identical calcium scores on repetitive pullbacks, indicating excellent reproducibility. Applied to new clinical pullbacks, our method has implications for real-time treatment planning and imaging research.

Automated plaque characterization using deep learning on coronary intravascular optical coherence tomographic images.

Accurate identification of coronary plaque is very important for cardiologists when treating patients with advanced atherosclerosis. We developed fully-automated semantic segmentation of plaque in intravascular OCT images. We trained/tested a deep learning model on a folded, large, manually annotated clinical dataset. The sensitivities/specificities were 87.4%/89.5% and 85.1%/94.2% for pixel-wise classification of lipidous and calcified plaque, respectively. Automated clinical lesion metrics, potentially useful for treatment planning and research, compared favorably (<4%) with those derived from ground-truth labels. When we converted the results to A-line classification, they were significantly better (p < 0.05) than those obtained previously by using deep learning classifications of A-lines.

Automated A-line coronary plaque classification of intravascular optical coherence tomography images using handcrafted features and large datasets.

We developed machine learning methods to identify fibrolipidic and fibrocalcific A-lines in intravascular optical coherence tomography (IVOCT) images using a comprehensive set of handcrafted features. We incorporated features developed in previous studies (e.g., optical attenuation and A-line peaks). In addition, we included vascular lumen morphology and three-dimensional (3-D) digital edge and texture features. Classification methods were developed using expansive datasets (∼7000 images), consisting of both clinical in-vivo images and an ex-vivo dataset, which was validated using 3-D cryo-imaging/histology. Conditional random field was used to perform 3-D classification noise cleaning of classification results. We tested various multiclass approaches, classifiers, and feature selection schemes and found that a three-class support vector machine with minimal-redundancy-maximal-relevance feature selection gave the best performance. We found that inclusion of our morphological and 3-D features improved overall classification accuracy. On a held-out test set consisting of >1700 images, we obtained an overall accuracy of 81.58%, with the following (sensitivity/specificity) for each class: other (81.43/89.59), fibrolipidic (94.48/87.32), and fibrocalcific (74.82/95.28). The en-face views of classification results showed that automated classification easily captured the preponderance of a disease segment (e.g., a calcified segment had large regions of fibrocalcific classifications). Finally, we demonstrated proof-of-concept for streamlining A-line classification output with existing fibrolipidic and fibrocalcific boundary segmentation methods, to enable fully automated plaque quantification. The results suggest that our classification approach is a viable step toward fully automated IVOCT plaque classification and segmentation for live-time treatment planning and for offline assessment of drug and biologic therapeutics.

Coronary calcification segmentation in intravascular OCT images using deep learning: application to calcification scoring.

Major calcifications are of great concern when performing percutaneous coronary interventions because they inhibit proper stent deployment. We created a comprehensive software to segment calcifications in intravascular optical coherence tomography (IVOCT) images and to calculate their impact using the stent-deployment calcification score, as reported by Fujino et al. We segmented the vascular lumen and calcifications using the pretrained SegNet, convolutional neural network, which was refined for our task. We cleaned segmentation results using conditional random field processing. We evaluated the method on manually annotated IVOCT volumes of interest (VOIs) without lesions and with calcifications, lipidous, or mixed lesions. The dataset included 48 VOIs taken from 34 clinical pullbacks, giving a total of 2640 in vivo images. Annotations were determined from consensus between two expert analysts. Keeping VOIs intact, we performed 10-fold cross-validation over all data. Following segmentation noise cleaning, we obtained sensitivities of 0.85 ± 0.04 , 0.99 ± 0.01 , and 0.97 ± 0.01 for calcified, lumen, and other tissue classes, respectively. From segmented regions, we automatically determined calcification depth, angle, and thickness attributes. Bland-Altman analysis suggested strong correlation between manually and automatically obtained lumen and calcification attributes. Agreement between manually and automatically obtained stent-deployment calcification scores was good (four of five lesions gave exact agreement). Results are encouraging and suggest our classification approach could be applied clinically for assessment and treatment planning of coronary calcification lesions.

Deep learning segmentation of coronary calcified plaque from intravascular optical coherence tomography (IVOCT) images with application to finite element modeling of stent deployment.

Because coronary artery calcified plaques can hinder or eliminate stent deployment, interventional cardiologists need a better way to plan interventions, which might include one of the many methods for calcification modification (e.g., atherectomy). We are imaging calcifications with intravascular optical coherence tomography (IVOCT), which is the lone intravascular imaging technique with the ability to image the extent of a calcification, and using results to build vessel-specific finite element models for stent deployment. We applied methods to a large set of image data (>45 lesions and > 2,600 image frames) of calcified plaques, manually segmented by experts into calcified, lumen and "other" tissue classes. In optimization experiments, we evaluated anatomical (x, y) versus acquisition (r,θ) views, augmentation methods, and classification noise cleaning. Noisy semantic segmentations are cleaned by applying a conditional random field (CRF). We achieve an accuracy of 0.85 ± 0.04, 0.99 ± 0.01, and 0.97 ± 0.01, and F-score of 0.88 ± 0.07, 0.97 ± 0.01, and 0.91 ± 0.04 for calcified, lumen, and other tissues classes respectively across all folds following CRF noise cleaning. As a proof of concept, we applied our methods to cadaver heart experiments on highly calcified plaques. Following limited manual correction, we used our calcification segmentations to create a lesion-specific finite element model (FEM) and used it to predict direct stenting deployment at multiple pressure steps. FEM modeling of stent deployment captured many features found in the actual stent deployment (e.g., lumen shape, lumen area, and location and number of apposed stent struts).

Deep neural networks for A-line-based plaque classification in coronary intravascular optical coherence tomography images.

We develop neural-network-based methods for classifying plaque types in clinical intravascular optical coherence tomography (IVOCT) images of coronary arteries. A single IVOCT pullback can consist of > 500 microscopic-resolution images, creating both a challenge for physician interpretation during an interventional procedure and an opportunity for automated analysis. In the proposed method, we classify each A-line, a datum element that better captures physics and pathophysiology than a voxel, as a fibrous layer followed by calcification (fibrocalcific), a fibrous layer followed by a lipidous deposit (fibrolipidic), or other. For A-line classification, the usefulness of a convolutional neural network (CNN) is compared with that of a fully connected artificial neural network (ANN). A total of 4469 image frames across 48 pullbacks that are manually labeled using consensus labeling from two experts are used for training, evaluation, and testing. A 10-fold cross-validation using held-out pullbacks is applied to assess classifier performance. Noisy A-line classifications are cleaned by applying a conditional random field (CRF) and morphological processing to pullbacks in the en-face view. With CNN (ANN) approaches, we achieve an accuracy of 77.7 % ± 4.1 % ( 79.4 % ± 2.9 % ) for fibrocalcific, 86.5 % ± 2.3 % ( 83.4 % ± 2.6 % ) for fibrolipidic, and 85.3 % ± 2.5 % ( 82.4 % ± 2.2 % ) for other, across all folds following CRF noise cleaning. The results without CRF cleaning are typically reduced by 10% to 15%. The enhanced performance of the CNN was likely due to spatial invariance of the convolution operation over the input A-line. The predicted en-face classification maps of entire pullbacks agree favorably to the annotated counterparts. In some instances, small error regions are actually hard to call when re-examined by human experts. Even in worst-case pullbacks, it can be argued that the results will not negatively impact usage by physicians, as there is a preponderance of correct calls.