RESUMO
BACKGROUND: Although regional wall motion abnormality (RWMA) detection is foundational to transthoracic echocardiography, current methods are prone to interobserver variability. We aimed to develop a deep learning (DL) model for RWMA assessment and compare it to expert and novice readers. METHODS: We used 15,746 transthoracic echocardiography studies-including 25,529 apical videos-which were split into training, validation, and test datasets. A convolutional neural network was trained and validated using apical 2-, 3-, and 4-chamber videos to predict the presence of RWMA in 7 regions defined by coronary perfusion territories, using the ground truth derived from clinical transthoracic echocardiography reports. Within the test cohort, DL model accuracy was compared to 6 expert and 3 novice readers using F1 score evaluation, with the ground truth of RWMA defined by expert readers. Significance between the DL model and novices was assessed using the permutation test. RESULTS: Within the test cohort, the DL model accurately identified any RWMA with an area under the curve of 0.96 (0.92-0.98). The mean F1 scores of the experts and the DL model were numerically similar for 6 of 7 regions: anterior (86 vs 84), anterolateral (80 vs 74), inferolateral (83 vs 87), inferoseptal (86 vs 86), apical (88 vs 87), inferior (79 vs 81), and any RWMA (90 vs 94), respectively, while in the anteroseptal region, the F1 score of the DL model was lower than the experts (75 vs 89). Using F1 scores, the DL model outperformed both novices 1 (P = .002) and 2 (P = .02) for the detection of any RWMA. CONCLUSIONS: Deep learning provides accurate detection of RWMA, which was comparable to experts and outperformed a majority of novices. Deep learning may improve the efficiency of RWMA assessment and serve as a teaching tool for novices.
Assuntos
Aprendizado Profundo , Ecocardiografia , Humanos , Ecocardiografia/métodos , Masculino , Feminino , Inteligência Artificial , Pessoa de Meia-Idade , Idoso , Reprodutibilidade dos Testes , Variações Dependentes do Observador , Disfunção Ventricular Esquerda/fisiopatologia , Disfunção Ventricular Esquerda/diagnóstico por imagem , Disfunção Ventricular Esquerda/diagnóstico , Interpretação de Imagem Assistida por Computador/métodosRESUMO
AIMS: While transthoracic echocardiography (TTE) assessment of left ventricular end-diastolic pressure (LVEDP) is critically important, the current paradigm is subject to error and indeterminate classification. Recently, peak left atrial strain (LAS) was found to be associated with LVEDP. We aimed to test the hypothesis that integration of the entire LAS time curve into a single parameter could improve the accuracy of peak LAS in the noninvasive assessment of LVEDP with TTE. METHODS AND RESULTS: We retrospectively identified 294 patients who underwent left heart catheterization and TTE within 24 h. LAS curves were trained using machine learning (100 patients) to detect LVEDP ≥ 15 mmHg, yielding the novel parameter LAS index (LASi). The accuracy of LASi was subsequently validated (194 patients), side by side with peak LAS and ASE/EACVI guidelines, against invasive filling pressures. Within the validation cohort, invasive LVEDP was elevated in 116 (59.8%) patients. The overall accuracy of LASi, peak LAS, and American Society of Echocardiography/European Association for Cardiovascular Imaging (ASE/EACVI) algorithm was 79, 75, and 76%, respectively (excluding 37 patients with indeterminate diastolic function by ASE/EACVI guidelines). When the number of LASi indeterminates (defined by near-zero LASi values) was matched to the ASE/EACVI guidelines (n = 37), the accuracy of LASi improved to 87%. Importantly, among the 37 patients with ASE/EACVI-indeterminate diastolic function, LASi had an accuracy of 81%, compared with 76% for peak LAS. CONCLUSION: LASi allows the detection of elevated LVEDP using invasive measurements as a reference, at least as accurately as peak LAS and current diastolic function guideline algorithm, with the advantage of no indeterminate classifications in patients with measurable LAS.
Assuntos
Disfunção Ventricular Esquerda , Função Ventricular Esquerda , Humanos , Pressão Sanguínea , Estudos Retrospectivos , Átrios do Coração/diagnóstico por imagem , Ecocardiografia , Diástole , Disfunção Ventricular Esquerda/diagnóstico por imagem , Volume Sistólico , Pressão VentricularRESUMO
PURPOSE OF REVIEW: This paper investigates present uses and future potential of artificial intelligence (AI) applied to intracoronary imaging technologies. RECENT FINDINGS: Advances in data analytics and digitized medical imaging have enabled clinical application of AI to improve patient outcomes and reduce costs through better diagnosis and enhanced workflow. Applications of AI to IVUS and IVOCT have produced improvements in image segmentation, plaque analysis, and stent evaluation. Machine learning algorithms are able to predict future coronary events through the use of imaging results, clinical evaluations, laboratory tests, and demographics. The application of AI to intracoronary imaging holds significant promise for improved understanding and treatment of coronary heart disease. Even in these early stages, AI has demonstrated the ability to improve the prediction of cardiac events. Large curated data sets and databases are needed to speed the development of AI and enable testing and comparison among algorithms.
Assuntos
Inteligência Artificial , Vasos Coronários/diagnóstico por imagem , Aprendizado de Máquina , Tomografia de Coerência Óptica/métodos , Ultrassonografia de Intervenção/métodos , Algoritmos , Aprendizado Profundo , HumanosRESUMO
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.
Assuntos
Aprendizado Profundo , Placa Aterosclerótica/diagnóstico por imagem , Tomografia de Coerência Óptica/métodos , Diagnóstico por Computador/métodos , Humanos , Processamento de Imagem Assistida por Computador/métodos , Placa Aterosclerótica/classificaçãoRESUMO
In this work, a heavily calcified coronary artery model was reconstructed from optical coherence tomography (OCT) images to investigate the impact of calcification characteristics on stenting outcomes. The calcification was quantified at various cross sections in terms of angle, maximum thickness, and area. The stent deployment procedure, including the crimping, expansion, and recoil, was implemented. The influence of calcification characteristics on stent expansion, malapposition, and lesion mechanics was characterized. Results have shown that the minimal lumen area following stenting occurred at the cross section with the greatest calcification angle. The calcification angle constricted the stretchability of the lesion and thus resulted in a small lumen area. The maximum principal strain and von Mises stress distribution patterns in both the fibrotic tissue and artery were consistent with the calcification profiles. The radially projected region of the calcification tends to have less strain and stress. The peak strain and stress of the fibrotic tissue occurred near the interface with the calcification. It is also the region with a high risk of tissue dissection and strut malapposition. In addition, the superficial calcification with a large angle aggregated the malapposition at the middle of the calcification arc. These detailed mechanistic quantifications could be used to provide a fundamental understanding of the role of calcification in stent expansions, as well as to exploit their potential for enhanced pre- and post-stenting strategies.
Assuntos
Stents , Tomografia de Coerência Óptica , Idoso , Angiografia Coronária , Vasos Coronários , Humanos , Pessoa de Meia-IdadeRESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
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 (â¼7000 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.
Assuntos
Doença da Artéria Coronariana/diagnóstico por imagem , Interpretação de Imagem Assistida por Computador/métodos , Aprendizado de Máquina , Placa Aterosclerótica/diagnóstico por imagem , Tomografia de Coerência Óptica/métodos , Algoritmos , Vasos Coronários/diagnóstico por imagem , Bases de Dados Factuais , Procedimentos Endovasculares , Humanos , Máquina de Vetores de SuporteRESUMO
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.
RESUMO
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).
RESUMO
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.
RESUMO
We created and evaluated a preclinical, multimodality imaging, and software platform to assess molecular imaging of small metastases. This included experimental methods (e.g., GFP-labeled tumor and high resolution multispectral cryo-imaging), nonrigid image registration, and interactive visualization of imaging agent targeting. We describe technological details earlier applied to GFP-labeled metastatic tumor targeting by molecular MR (CREKA-Gd) and red fluorescent (CREKA-Cy5) imaging agents. Optimized nonrigid cryo-MRI registration enabled nonambiguous association of MR signals to GFP tumors. Interactive visualization of out-of-RAM volumetric image data allowed one to zoom to a GFP-labeled micrometastasis, determine its anatomical location from color cryo-images, and establish the presence/absence of targeted CREKA-Gd and CREKA-Cy5. In a mouse with >160 GFP-labeled tumors, we determined that in the MR images every tumor in the lung >0.3 mm2 had visible signal and that some metastases as small as 0.1 mm2 were also visible. More tumors were visible in CREKA-Cy5 than in CREKA-Gd MRI. Tape transfer method and nonrigid registration allowed accurate (<11 µm error) registration of whole mouse histology to corresponding cryo-images. Histology showed inflammation and necrotic regions not labeled by imaging agents. This mouse-to-cells multiscale and multimodality platform should uniquely enable more informative and accurate studies of metastatic cancer imaging and therapy.
RESUMO
Intravascular Optical Coherence Tomography (IVOCT) is a high contrast, 3D microscopic imaging technique that can be used to assess atherosclerosis and guide stent interventions. Despite its advantages, IVOCT image interpretation is challenging and time consuming with over 500 image frames generated in a single pullback volume. We have developed a method to classify voxel plaque types in IVOCT images using machine learning. To train and test the classifier, we have used our unique database of labeled cadaver vessel IVOCT images accurately registered to gold standard cryo-images. This database currently contains 300 images and is growing. Each voxel is labeled as fibrotic, lipid-rich, calcified or other. Optical attenuation, intensity and texture features were extracted for each voxel and were used to build a decision tree classifier for multi-class classification. Five-fold cross-validation across images gave accuracies of 96 % ± 0.01 %, 90 ± 0.02% and 90 % ± 0.01 % for fibrotic, lipid-rich and calcified classes respectively. To rectify performance degradation seen in left out vessel specimens as opposed to left out images, we are adding data and reducing features to limit overfitting. Following spatial noise cleaning, important vascular regions were unambiguous in display. We developed displays that enable physicians to make rapid determination of calcified and lipid regions. This will inform treatment decisions such as the need for devices (e.g., atherectomy or scoring balloon in the case of calcifications) or extended stent lengths to ensure coverage of lipid regions prone to injury at the edge of a stent.
RESUMO
Stent deployment has been widely used to treat narrowed coronary artery. Its acute outcome in terms of stent under expansion and malapposition depends on the extent and shape of calcifications. However, no clear understanding as to how to quantify or categorize the impact of calcification. We have conducted ex vivo stenting characterized by the optical coherence tomography (OCT). The goal of this work is to capture the ex vivo stent deployment and quantify the effect of calcium morphology on the stenting. A three dimensional model of calcified plaque was reconstructed from ex vivo OCT images. The crimping, balloon expansion and recoil process of the Express stent were characterized. Three cross-sections with different calcium percentages were chosen to evaluated the effect of the calcium in terms of stress/strain, lumen gains and malapposition. Results will be used to the pre-surgical planning.
RESUMO
Evidence suggests high-resolution, high-contrast, [Formula: see text] intravascular optical coherence tomography (IVOCT) can distinguish plaque types, but further validation is needed, especially for automated plaque characterization. We developed experimental and three-dimensional (3-D) registration methods to provide validation of IVOCT pullback volumes using microscopic, color, and fluorescent cryo-image volumes with optional registered cryo-histology. A specialized registration method matched IVOCT pullback images acquired in the catheter reference frame to a true 3-D cryo-image volume. Briefly, an 11-parameter registration model including a polynomial virtual catheter was initialized within the cryo-image volume, and perpendicular images were extracted, mimicking IVOCT image acquisition. Virtual catheter parameters were optimized to maximize cryo and IVOCT lumen overlap. Multiple assessments suggested that the registration error was better than the [Formula: see text] spacing between IVOCT image frames. Tests on a digital synthetic phantom gave a registration error of only [Formula: see text] (signed distance). Visual assessment of randomly presented nearby frames suggested registration accuracy within 1 IVOCT frame interval ([Formula: see text]). This would eliminate potential misinterpretations confronted by the typical histological approaches to validation, with estimated 1-mm errors. The method can be used to create annotated datasets and automated plaque classification methods and can be extended to other intravascular imaging modalities.
RESUMO
Analysis of intravascular optical coherence tomography (IVOCT) data has potential for real-time in vivo plaque classification. We developed a processing pipeline on a three-dimensional local region of support for estimation of optical properties of atherosclerotic plaques from coronary artery, IVOCT pullbacks. Using realistic coronary artery disease phantoms, we determined insignificant differences in mean and standard deviation estimates between our pullback analyses and more conventional processing of stationary acquisitions with frame averaging. There was no effect of tissue depth or oblique imaging on pullback parameter estimates. The method's performance was assessed in comparison with observer-defined standards using clinical pullback data. Values (calcium [Formula: see text], lipid [Formula: see text], and fibrous [Formula: see text]) were consistent with previous measurements obtained by other means. Using optical parameters ([Formula: see text], [Formula: see text], [Formula: see text]), we achieved feature space separation of plaque types and classification accuracy of [Formula: see text]. Despite the rapid [Formula: see text] motion and varying incidence angle in pullbacks, the proposed computational pipeline appears to work as well as a more standard "stationary" approach.
RESUMO
High resolution, 100 frames/sec intravascular optical coherence tomography (IVOCT) can distinguish plaque types, but further validation is needed, especially for automated plaque characterization. We developed experimental and 3D registration methods, to provide validation of IVOCT pullback volumes using microscopic, brightfield and fluorescent cryo-image volumes, with optional, exactly registered cryo-histology. The innovation was a method to match an IVOCT pull-back images, acquired in the catheter reference frame, to a true 3D cryo-image volume. Briefly, an 11-parameter, polynomial virtual catheter was initialized within the cryo-image volume, and perpendicular images were extracted, mimicking IVOCT image acquisition. Virtual catheter parameters were optimized to maximize cryo and IVOCT lumen overlap. Local minima were possible, but when we started within reasonable ranges, every one of 24 digital phantom cases converged to a good solution with a registration error of only +1.34±2.65µm (signed distance). Registration was applied to 10 ex-vivo cadaver coronary arteries (LADs), resulting in 10 registered cryo and IVOCT volumes yielding a total of 421 registered 2D-image pairs. Image overlays demonstrated high continuity between vascular and plaque features. Bland-Altman analysis comparing cryo and IVOCT lumen area, showed mean and standard deviation of differences as 0.01±0.43 mm2. DICE coefficients were 0.91±0.04. Finally, visual assessment on 20 representative cases with easily identifiable features suggested registration accuracy within one frame of IVOCT (±200µm), eliminating significant misinterpretations introduced by 1mm errors in the literature. The method will provide 3D data for training of IVOCT plaque algorithms and can be used for validation of other intravascular imaging modalities.
RESUMO
The presence of extensive calcification is a primary concern when planning and implementing a vascular percutaneous intervention such as stenting. If the balloon does not expand, the interventionalist must blindly apply high balloon pressure, use an atherectomy device, or abort the procedure. As part of a project to determine the ability of Intravascular Optical Coherence Tomography (IVOCT) to aid intervention planning, we developed a method for automatic classification of calcium in coronary IVOCT images. We developed an approach where plaque texture is modeled by the joint probability distribution of a bank of filter responses where the filter bank was chosen to reflect the qualitative characteristics of the calcium. This distribution is represented by the frequency histogram of filter response cluster centers. The trained algorithm was evaluated on independent ex-vivo image data accurately labeled using registered 3D microscopic cryo-image data which was used as ground truth. In this study, regions for extraction of sub-images (SI's) were selected by experts to include calcium, fibrous, or lipid tissues. We manually optimized algorithm parameters such as choice of filter bank, size of the dictionary, etc. Splitting samples into training and testing data, we achieved 5-fold cross validation calcium classification with F1 score of 93.7±2.7% with recall of ≥89% and a precision of ≥97% in this scenario with admittedly selective data. The automated algorithm performed in close-to-real-time (2.6 seconds per frame) suggesting possible on-line use. This promising preliminary study indicates that computational IVOCT might automatically identify calcium in IVOCT coronary artery images.
RESUMO
We developed robust, three-dimensional methods, as opposed to traditional A-line analysis, for estimating the optical properties of calcified, fibrotic, and lipid atherosclerotic plaques from in vivo coronary artery intravascular optical coherence tomography clinical pullbacks. We estimated attenuation [Formula: see text] and backscattered intensity [Formula: see text] from small volumes of interest annotated by experts in 35 pullbacks. Some results were as follows: noise reduction filtering was desirable, parallel line (PL) methods outperformed individual line methods, root mean square error was the best goodness-of-fit, and [Formula: see text]-trimmed PL ([Formula: see text]-T-PL) was the best overall method. Estimates of [Formula: see text] were calcified ([Formula: see text]), fibrotic ([Formula: see text]), and lipid ([Formula: see text]), similar to those in the literature, and tissue classification from optical properties alone was promising.