Ilkay Oksuz

Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography

Though conventional coronary angiography (CCA) has been the standard of reference for diagnosing coronary artery disease in the past decades, computed tomography angiography (CTA) has rapidly emerged, and is nowadays widely used in clinical practice. Here, we introduce a standardized evaluation framework to reliably evaluate and compare the performance of the algorithms devised to detect and quantify the coronary artery stenoses, and to segment the coronary artery lumen in CTA data. The objective of this evaluation framework is to demonstrate the feasibility of dedicated algorithms to: (1) (semi-)automatically detect and quantify stenosis on CTA, in comparison with quantitative coronary angiography (QCA) and CTA consensus reading, and (2) (semi-)automatically segment the coronary lumen on CTA, in comparison with experts manual annotation. A database consisting of 48 multicenter multivendor cardiac CTA datasets with corresponding reference standards are described and made available. The algorithms from 11 research groups were quantitatively evaluated and compared. The results show that (1) some of the current stenosis detection/quantification algorithms may be used for triage or as a second-reader in clinical practice, and that (2) automatic lumen segmentation is possible with a precision similar to that obtained by experts. The framework is open for new submissions through the website, at http://coronary.bigr.nl/stenoses/.

Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the VESSEL12 study

The VESSEL12 (VESsel SEgmentation in the Lung) challenge objectively compares the performance of different algorithms to identify vessels in thoracic computed tomography (CT) scans. Vessel segmentation is fundamental in computer aided processing of data generated by 3D imaging modalities. As manual vessel segmentation is prohibitively time consuming, any real world application requires some form of automation. Several approaches exist for automated vessel segmentation, but judging their relative merits is difficult due to a lack of standardized evaluation. We present an annotated reference dataset containing 20 CT scans and propose nine categories to perform a comprehensive evaluation of vessel segmentation algorithms from both academia and industry. Twenty algorithms participated in the VESSEL12 challenge, held at International Symposium on Biomedical Imaging (ISBI) 2012. All results have been published at the VESSEL12 website http://vessel12.grand-challenge.org. The challenge remains ongoing and open to new participants. Our three contributions are: (1) an annotated reference dataset available online for evaluation of new algorithms; (2) a quantitative scoring system for objective comparison of algorithms; and (3) performance analysis of the strengths and weaknesses of the various vessel segmentation methods in the presence of various lung diseases.

Statistical Shape Modeling of the Left Ventricle: Myocardial Infarct Classification Challenge

Statistical shape modeling is a powerful tool for visualizing and quantifying geometric and functional patterns of the heart. After myocardial infarction (MI), the left ventricle typically remodels in response to physiological challenges. Several methods have been proposed in the literature to describe statistical shape changes. Which method best characterizes the left ventricular remodeling after MI is an open research question. A better descriptor of remodeling is expected to provide a more accurate evaluation of disease status in MI patients. We therefore designed a challenge to test shape characterization in MI given a set of three-dimensional left ventricular surface points. The training set comprised 100 MI patients, and 100 asymptomatic volunteers (AV). The challenge was initiated in 2015 at the Statistical Atlases and Computational Models of the Heart workshop, in conjunction with the MICCAI conference. The training set with labels was provided to participants, who were asked to submit the likelihood of MI from a different (validation) set of 200 cases (100 AV and 100 MI). Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve were used as the outcome measures. The goals of this challenge were to 1) establish a common dataset for evaluating statistical shape modeling algorithms in MI, and 2) test whether statistical shape modeling provides additional information characterizing MI patients over standard clinical measures. Eleven groups with a wide variety of classification and feature extraction approaches participated in this challenge. All methods achieved excellent classification results with accuracy ranges from 0.83 to 0.98. The areas under the receiver operating characteristic curves were all above 0.90. Four methods showed significantly higher performance than standard clinical measures. The dataset and software for evaluation are available from the Cardiac Atlas Project website.11 http://www.cardiacatlas.org.

Data-driven feature learning for myocardial segmentation of CP-BOLD MRI

Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP-BOLD) MR is capable of diagnosing an ongoing ischemia by detecting changes in myocardial intensity patterns at rest without any contrast and stress agents. Visualizing and detecting these changes require significant post-processing, including myocardial segmentation for isolating the myocardium. But, changes in myocardial intensity pattern and myocardial shape due to the heart’s motion challenge automated standard CINE MR myocardial segmentation techniques resulting in a significant drop of segmentation accuracy. We hypothesize that the main reason behind this phenomenon is the lack of discernible features. In this paper, a multi scale discriminative dictionary learning approach is proposed for supervised learning and sparse representation of the myocardium, to improve the myocardial feature selection. The technique is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canine subjects. The proposed method significantly outperforms standard cardiac segmentation techniques, including segmentation via registration, level sets and supervised methods for myocardial segmentation.

Unsupervised Myocardial Segmentation for Cardiac MRI

Though unsupervised segmentation was a de-facto standard for cardiac MRI segmentation early on, recently cardiac MRI segmentation literature has favored fully supervised techniques such as Dictionary Learning and Atlas-based techniques. But, the benefits of unsupervised techniques e.g., no need for large amount of training data and better potential of handling variability in anatomy and image contrast, is more evident with emerging cardiac MR modalities. For example, CP-BOLD is a new MRI technique that has been shown to detect ischemia without any contrast at stress but also at rest conditions. Although CP-BOLD looks similar to standard CINE, changes in myocardial intensity patterns and shape across cardiac phases, due to the heart’s motion, BOLD effect and artifacts affect the underlying mechanisms of fully supervised segmentation techniques resulting in a significant drop in segmentation accuracy. In this paper, we present a fully unsupervised technique for segmenting myocardium from the background in both standard CINE MR and CP-BOLD MR. We combine appearance with motion information (obtained via Optical Flow) in a dictionary learning framework to sparsely represent important features in a low dimensional space and separate myocardium from background accordingly. Our fully automated method learns background-only models and one class classifier provides myocardial segmentation. The advantages of the proposed technique are demonstrated on a dataset containing CP-BOLD MR and standard CINE MR image sequences acquired in baseline and ischemic condition across 10 canine subjects, where our method outperforms state-of-the-art supervised segmentation techniques in CP-BOLD MR and performs at-par for standard CINE MR.

Dictionary Learning Based Image Descriptor for Myocardial Registration of CP-BOLD MR

Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP-BOLD) MRI is a new contrast agent- and stress-free imaging technique for the assessment of myocardial ischemia at rest. The precise registration among the cardiac phases in this cine type acquisition is essential for automating the analysis of images of this technique, since it can potentially lead to better specificity of ischemia detection. However, inconsistency in myocardial intensity patterns and the changes in myocardial shape due to the heart’s motion lead to low registration performance for state-of-the-art methods. This low accuracy can be explained by the lack of distinguishable features in CP-BOLD and inappropriate metric definitions in current intensity-based registration frameworks. In this paper, the sparse representations, which are defined by a discriminative dictionary learning approach for source and target images, are used to improve myocardial registration. This method combines appearance with Gabor and HOG features in a dictionary learning framework to sparsely represent features in a low dimensional space. The sum of absolute differences of these distinctive sparse representations are used to define a similarity term in the registration framework. The proposed approach is validated on a dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canines.

MRI-TRUS Image Synthesis with Application to Image-Guided Prostate Intervention

Accurate and robust fusion of pre-procedure magnetic resonance imaging (MRI) to intra-procedure trans-rectal ultrasound (TRUS) imaging is necessary for image-guided prostate cancer biopsy procedures. The current clinical standard for image fusion relies on non-rigid surface-based registration between semi-automatically segmented prostate surfaces in both the MRI and TRUS. This surface-based registration method does not take advantage of internal anatomical prostate structures, which have the potential to provide useful information for image registration. However, non-rigid, multi-modal intensity-based MRI-TRUS registration is challenging due to highly non-linear intensities relationships between MRI and TRUS. In this paper, we present preliminary work using image synthesis to cast this problem into a mono-modal registration task by using a large database of over 100 clinical MRI-TRUS image pairs to learn a joint model of MR-TRUS appearance. Thus, given an MRI, we use this learned joint appearance model to synthesize the patient’s corresponding TRUS image appearance with which we could potentially perform mono-modal intensity-based registration. We present preliminary results of this approach.

Region growing on frangi vesselness values in 3-D CTA data

In cardiac related diagnostic methods, the shape and curvature of coronary arteries is essential. Consequently, one of the most important requirements for Computer Aided Diagnosis (CAD) Systems is automated segmentation of vasculature. In this paper, we propose a new hybrid algorithm, which segment the coronary arterial tree in CTA images by merging methodologies-, namely, Region Growing and Frangi Approach. The algorithm first runs a region growing on Frangi vesselness values and subsequently optimizes the results with several threshold values. Comparison of the present results with optimal results of existing segmentation algorithms reveals that the proposed approach outperforms its predecessors. The diagnostic accuracy of the algorithm will next be validated on the segmentation of coronary arteries from real CT data.

Deep Learning Using K-Space Based Data Augmentation for Automated Cardiac MR Motion Artefact Detection

Quality assessment of medical images is essential for complete automation of image processing pipelines. For large population studies such as the UK Biobank, artefacts such as those caused by heart motion are problematic and manual identification is tedious and time-consuming. Therefore, there is an urgent need for automatic image quality assessment techniques. In this paper, we propose a method to automatically detect the presence of motion-related artefacts in cardiac magnetic resonance (CMR) images. As this is a highly imbalanced classification problem (due to the high number of good quality images compared to the low number of images with motion artefacts), we propose a novel k-space based training data augmentation approach in order to address this problem. Our method is based on 3D spatio-temporal Convolutional Neural Networks, and is able to detect 2D+time short axis images with motion artefacts in less than 1 ms. We test our algorithm on a subset of the UK Biobank dataset consisting of 3465 CMR images and achieve not only high accuracy in detection of motion artefacts, but also high precision and recall. We compare our approach to a range of state-of-the-art quality assessment methods.

Joint Myocardial Registration and Segmentation of Cardiac BOLD MRI

Registration and segmentation of anatomical structures are two well studied problems in medical imaging. Optimizing segmentation and registration jointly has been proven to improve results for both challenges. In this work, we propose a joint optimization scheme for registration and segmentation using dictionary learning based descriptors. Our joint registration and segmentation aims to solve an optimization function, which enables better performance for both of these ill-posed processes. We build two dictionaries for background and myocardium for square patches extracted from training images. Based on dictionary learning residuals and sparse representations defined on these pre-trained dictionaries, a Markov Random Field (MRF) based joint optimization scheme is built. The algorithm proceeds iteratively updating the dictionaries in an online fashion. The accuracy of the proposed method is illustrated on Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP-BOLD) MRI and standard cine Cardiac MRI data from MICCAI 2013 SATA Segmentation Challenge. The proposed joint segmentation and registration method achieves higher dice accuracy for myocardium segmentation compared to its variants.