abstract: Coronary computed tomography angiography (CTA) has a high negative predictive value for ruling out coronary artery disease with non-invasive evaluation of the coronary arteries. My work has attempted to provide metrics that could increase the positive predictive value of coronary CTA through the use of dual energy CTA imaging. After developing an algorithm for obtaining calcium scores from a CTA exam, a dual energy CTA exam was performed on patients at dose levels equivalent to levels for single energy CTA with a calcium scoring exam. Calcium Agatston scores obtained from the dual energy CTA exam were within ±11% of scores obtained with conventional calcium scoring exams. In the presence of highly attenuating coronary calcium plaques, the virtual non-calcium images obtained with dual energy CTA were able to successfully measure percent coronary stenosis within 5% of known stenosis values, which is not possible with single energy CTA images due to the presence of the calcium blooming artifact. After fabricating an anthropomorphic beating heart phantom with coronary plaques, characterization of soft plaque vulnerability to rupture or erosion was demonstrated with measurements of the distance from soft plaque to aortic ostium, percent stenosis, and percent lipid volume in soft plaque. A classification model was developed, with training data from the beating heart phantom and plaques, which utilized support vector machines to classify coronary soft plaque pixels as lipid or fibrous. Lipid versus fibrous classification with single energy CTA images exhibited a 17% error while dual energy CTA images in the classification model developed here only exhibited a 4% error. Combining the calcium blooming correction and the percent lipid volume methods developed in this work will provide physicians with metrics for increasing the positive predictive value of coronary CTA as well as expanding the use of coronary CTA to patients with highly attenuating calcium plaques. / Dissertation/Thesis / Ph.D. Bioengineering 2013

Atherosclerotic plaque is currently the leading cause of coronary artery disease (CAD). With the help of CT images, we can identify the size and type of plaque, which can help doctors make a correct diagnosis. To do this, we need to segment coronary plaques from CT images. However, plaque segmentation is still challenging because it takes a lot of energy and time of the radiologists. With the development of technology, some segmentation algorithms based on deep learning are applied in this field. These deep learning algorithms tend to be fully automated and have high segmentation accuracy, showing great potential. In this paper, we try to use deep learning method to segment plaques from 3D cardiac CT images. This work is implemented in two steps. The first part is to extract coronary artery from the CT image with the help of UNet. In the second part, a fully convolutional network is used to segment the plaques from the artery. In each part, the algorithm undergoes 5-fold cross validation. In the first part, we achieve a dice coefficient of 0.8954. In the second part, we achieve the AUC score of 0.9202 which is higher than auto-encoder method and is very close to state-of-the-art method. / Aterosklerotisk plack är för närvarande den främsta orsaken till kranskärlssjukdom (CAD). Med hjälp av CT-bilder kan vi identifiera storlek och typ av plack, vilket kan hjälpa läkare att ställa en korrekt diagnos. För att göra detta måste vi segmentera koronarplack från CT-bilder. Emellertid är placksegmentering fortfarande utmanande eftersom det tar mycket energi och tid av radiologerna. Med utvecklingen av teknik tillämpas vissa segmenteringsalgoritmer baserade på djupinlärning inom detta område. Dessa djupinlärningsalgoritmer tenderar att vara helt automatiserade och har hög segmenteringsnoggrannhet, vilket visar stor potential. I detta dokument försöker vi använda djupinlärningsmetoden för att segmentera plack från 3D-hjärt-CT-bilder. Detta arbete genomförs i två steg. Den första delen är att extrahera kranskärlen från CT-bilden med hjälp av UNet. I den andra delen används ett helt konvolutionerande nätverk för att segmentera placken från artären. I varje del genomgår algoritmen 5-faldig korsvalidering. I den första delen uppnår vi en tärningskoefficient på 0,8954. I den andra delen uppnår vi AUC-poängen 0,9202, vilket är högre än den automatiska kodarmetoden och är mycket nära den senaste metoden.

Les bioresorbable stents (BRS), en français intitulés tuteurs coronariens biorésorbables, sont constitués d’un polymère biorésorbable, plutôt que de métal, et ne créent pas d’artéfacts métalliques significatifs en tomodensitométrie (TDM). Cela permet une meilleure évaluation de la plaque coronarienne sous ces tuteurs en TDM qu’avec les anciens tuteurs qui sont en métal. OBJECTIF: Évaluer l’évolution de la composition de la plaque, sa fraction lipidique (FL)— marqueur de vulnérabilité de la plaque, dans les 3 zones pré-tuteur (bord proximal), intra-tuteur et post-tuteur (bord distal), et le volume de la plaque entre 1 et 12 mois post-implantation de BRS. MÉTHODOLOGIE: Il s’agit d’une étude observationnelle longitudinale réalisée chez 27 patients consécutifs (âge moyen 59,7 +/- 8,6 ans) et recrutés prospectivement pour une imagerie par TDM 256-coupes à 1 et 12 mois post-implantation de BRS (35 tuteurs total). Les objectifs primaires sont: volume de plaque totale et de FL (mm3) comparés entre 1 et 12 mois. Afin de tenir compte de la corrélation intra-patient, des analyses de variance des modèles linéaires mixtes avec ou sans spline sont utilisés avec deux facteurs répétés temps et zone/bloc (1 bloc= 5 mm en axe longitudinal). La valeur % FL= volume absolu du FL/ volume total de la plaque. RÉSULTATS: Notre analyse par bloc ou par spline n’a pas démontré une différence significative dans les volumes de plaque ou des FL dans les zones pre- intra- and post-tuteur entre 1 et 12 mois. CONCLUSION: Notre étude a réussi à démontrer la faisabilité d’une analyse non-invasive quantitative répétée de la plaque coronarienne et de la lumière intra-tuteur avec l’utilisation de TDM 256 coupes. Cette étude pilote n’a pas démontré de différence significative dans les volumes des plaques et atténuation entre 1- et 12- mois de follow-up post-implantation de BRS. Notre méthode pourrait être appliquée à l’évaluation des différents structures ou profils pharmacologiques de ces tuteurs. / Coronary bioresorbable stents (BRS) are made of a bioresorbable polymer rather than metal. Unlike metallic stents, BRS do not produce significant artifacts in computed tomography (CT) and are radiolucent in CT, making it possible to evaluate coronary plaque beneath an implanted stent. PURPOSE: The purpose of our study was to evaluate the volumes of plaque and low attenuation plaque components (LAP —a marker of plaque vulnerability) of pre-, intra- and post-stent plaque location between 1 and 12 months post-implantation. METHODS: In our prospective longitudinal study, we recruited 27 consecutive patients (mean age 59.7 +/- 8.6 years) with bioresorbable stents (n=35) for a 256-slice ECG-synchronized CT evaluation at 1 month and at 12 months post stent implantation. Total plaque volume (mm3) as well as absolute and relative (%) LAP volume per block in the pre-, intra- and post-stent zones were analyzed; comparison of 1 and 12 months post BRS implantation. Changes in these variables were assessed using mixed effects models with and without spline, which also accounted for correlation between repeated measurements with factors such as time and zone/block (1 block = 5 mm in longitudinal axis). The value % LAP= LAP absolute volume/ total plaque volume. RESULTS: Our block or spline model analysis showed no significant difference in plaque or LAP volumes in pre-, intra- and post-stent zones measured at 1 month and at 12 months. CONCLUSION: Our study demonstrates the feasibility of repeated non-invasive quantitative analysis of intrastent coronary plaque and in-stent lumen using a 256-channel CT scan. This pilot study did not show significant differences in plaque volume and attenuation between 1- and 12-month follow-up from stent implantation. The method we used could be applied to the evaluation of different stent structures or different pharmacological profiles of bioresorbable stents.