Maysa M. G. Macedo

Three-dimensional synthetic blood vessel generation using stochastic L-systems

Segmentation of blood vessels from magnetic resonance angiography (MRA) or computed tomography angiography (CTA) images is a complex process that usually takes a lot of computational resources. Also, most vascular segmentation and detection algorithms do not work properly due to the wide architectural variability of the blood vessels. Thus, the construction of convincing synthetic vascular trees makes it possible to validate new segmentation methodologies. In this work, an extension to the traditional Lindenmayer system (L-system) that generates synthetic 3D blood vessels by adding stochastic rules and parameters to the grammar is proposed. Towards this aim, we implement a parser and a generator of L-systems whose grammars simulate natural features of real vessels such as the bifurcation angle, average length and diameter, as well as vascular anomalies, such as aneurysms and stenoses. The resulting expressions are then used to create synthetic vessel images that mimic MRA and CTA images. In addition, this methodology allows for vessel growth to be limited by arbitrary 3D surfaces, and the vessel intensity profille can be tailored to match real angiographic intensities.

Vessel centerline tracking in CTA and MRA images using hough transform

Vascular disease is characterized by any condition that affects the circulatory system. Recently, a demand for sophisticated software tools that can characterize the integrity and functional state of vascular networks from different vascular imaging modalities has appeared. Such tools face significant challenges such as: large datasets, similarity in intensity distributions of other organs and structures, and the presence of complex vessel geometry and branching patterns. Towards that goal, this paper presents a new approach to automatically track vascular networks from CTA and MRA images. Our methodology is based on the Hough transform to dynamically estimate the centerline and vessel diameter along the vessel trajectory. Furthermore, the vessel architecture and orientation is determined by the analysis of the Hessian matrix of the CTA or MRA intensity distribution. Results are shown using both synthetic vessel datasets and real human CTA and MRA images. The tracking algorithm yielded high reproducibility rates, robustness to different noise levels, associated with simplicity of execution, which demonstrates the feasibility of our approach.

A robust fully automatic lumen segmentation method for in vivo intracoronary optical coherence tomography

Introduction: Intravascular optical coherence tomography (IVOCT) is an in-vivo imaging modality based on the introduction of a catheter in a blood vessel for viewing its inner wall using electromagnetic radiation. One of the most developed automatic applications for this modality is the lumen area segmentation, however on the evaluation of these methods, the slices inside bifurcation regions, or with the presence of complex atherosclerotic plaques and dissections are usually discarded. This paper describes a fully-automatic method for computing the lumen area in IVOCT images where the set of slices includes complex atherosclerotic plaques and dissections. Methods The proposed lumen segmentation method is divided into two steps: preprocessing, including the removal of artifacts and the second step comprises a lumen detection using morphological operations. In addition, it is proposed an approach to delimit the lumen area for slices inside bifurcation region, considering only the main branch. Results Evaluation of the automatic lumen segmentation used manual segmentations as a reference, it was performed on 1328 human IVOCT images, presenting a mean difference in lumen area and Dice metrics of 0.19 mm2 and 97% for slices outside the bifurcation, 1.2 mm2 and 88% in the regions with bifurcation without automatic contour correction and 0.52 mm2 and 90% inside bifurcation region with automatic contour correction. Conclusion This present study shows a robust lumen segmentation method for vessel cross-sections with dissections and complex plaque and bifurcation avoiding the exclusion of such regions from the dataset analysis.

A centerline-based estimator of vessel bifurcations in angiography images

The analysis of vascular structure based on vessel diameters, density and distance between bifurcations is an important step towards the diagnosis of vascular anomalies. Moreover, vascular network extraction allows the study of angiogenesis. This work describes a technique that detects bifurcations in vascular networks in magnetic resonance angiography and computed tomography angiography images. Initially, a vessel tracking technique that uses the Hough transform and a matrix composed of second order partial derivatives of image intensity is used to estimate the scale and vessel direction, respectively. This semi-automatic technique is capable of connecting isolated tracked vessel segments and extracting a full tree from a vascular network with minimal user intervention. Vessel shape descriptors such as curvature are then used to identify bifurcations during tracking and to estimate the next branch direction. We have initially applied this technique on synthetic datasets and then on real images.

A bifurcation identifier for IV-OCT using orthogonal least squares and supervised machine learning

Intravascular optical coherence tomography (IV-OCT) is an in-vivo imaging modality based on the intravascular introduction of a catheter which provides a view of the inner wall of blood vessels with a spatial resolution of 10-20 μm. Recent studies in IV-OCT have demonstrated the importance of the bifurcation regions. Therefore, the development of an automated tool to classify hundreds of coronary OCT frames as bifurcation or nonbifurcation can be an important step to improve automated methods for atherosclerotic plaques quantification, stent analysis and co-registration between different modalities. This paper describes a fully automated method to identify IV-OCT frames in bifurcation regions. The method is divided into lumen detection; feature extraction; and classification, providing a lumen area quantification, geometrical features of the cross-sectional lumen and labeled slices. This classification method is a combination of supervised machine learning algorithms and feature selection using orthogonal least squares methods. Training and tests were performed in sets with a maximum of 1460 human coronary OCT frames. The lumen segmentation achieved a mean difference of lumen area of 0.11 mm(2) compared with manual segmentation, and the AdaBoost classifier presented the best result reaching a F-measure score of 97.5% using 104 features.

An automatic labeling bifurcation method for intracoronary optical coherence tomography images

Vessel branchings are critical vascular locations from the clinical point of view. In these sites, the arterial hemodynamic plays a relevant role in the progression of atherosclerosis, an important vascular pathology. In this paper, a fully automatic approach for the bifurcation classification in human Intravascular Optical Coherence Tomography (IV-OCT) sequences is introduced. Given the lumen contours, the method is capable of labeling the bifurcation slices. A geometric feature extraction was performed and the Forward Regression Orthogonal Least Squares method (FROLS) was applied to analyze the best features and to determine the appropriated weights in a binary classifier. A cross-validation scheme is applied in order to evaluate the performance of the classification approach and the results have shown a sensitivity of 86% and specificity of 92% to FROLS.

Coronary calcification identification in optical coherence tomography using convolutional neural networks

Intravascular optical coherence tomography (IOCT) is a modality that provides sufficient resolution for very accurate visualization of localized cardiovascular conditions, such as coronary artery calcification (CAC). CAC quantification in IOCT images is still performed mostly manually, which is time consuming, considering that each IOCT exam has more than two hundred 2D slices. An automated method for CAC detection in IOCT would add valuable information for clinicians when treating patients with coronary atherosclerosis. In this context, we propose an approach that uses a fully connected neural network (FCNN) for CAC detection in IOCT images using a small training dataset. In our approach, we transform the input image to polar coordinate transformation using as reference the centroid from the lumen segmentation, that restricts the variability in CAC spatial position, which we proved to be beneficial for the CNN training with few training data. We analyzed 51 slices from in-vivo human coronaries and the method achieved 63.6% sensitivity and 99.8% specificity for segmenting CAC. Our results demonstrate that it is possible to successfully detect and segment calcific plaques in IOCT images using FCNNs.

Classification of bifurcations regions in IVOCT images using support vector machine and artificial neural network models

Studies in intravascular optical coherence tomography (IV-OCT) have demonstrated the importance of coronary bifurcation regions in intravascular medical imaging analysis, as plaques are more likely to accumulate in this region leading to coronary disease. A typical IV-OCT pullback acquires hundreds of frames, thus developing an automated tool to classify the OCT frames as bifurcation or non-bifurcation can be an important step to speed up OCT pullbacks analysis and assist automated methods for atherosclerotic plaque quantification. In this work, we evaluate the performance of two state-of-the-art classifiers, SVM and Neural Networks in the bifurcation classification task. The study included IV-OCT frames from 9 patients. In order to improve classification performance, we trained and tested the SVM with different parameters by means of a grid search and different stop criteria were applied to the Neural Network classifier: mean square error, early stop and regularization. Different sets of features were tested, using feature selection techniques: PCA, LDA and scalar feature selection with correlation. Training and test were performed in sets with a maximum of 1460 OCT frames. We quantified our results in terms of false positive rate, true positive rate, accuracy, specificity, precision, false alarm, f-measure and area under ROC curve. Neural networks obtained the best classification accuracy, 98.83%, overcoming the results found in literature. Our methods appear to offer a robust and reliable automated classification of OCT frames that might assist physicians indicating potential frames to analyze. Methods for improving neural networks generalization have increased the classification performance.