Acharya U.R.,Ann Polytechnic |
Acharya U.R.,University of Malaya |
Faust O.,University of Aberdeen |
S. V.S.,Global Biomedical Technologies Inc. |
And 4 more authors.
Computer Methods and Programs in Biomedicine | Year: 2013
Characterization of carotid atherosclerosis and classification into either symptomatic or asymptomatic is crucial in terms of diagnosis and treatment planning for a range of cardiovascular diseases. This paper presents a computer-aided diagnosis (CAD) system (Atheromatic) that analyzes ultrasound images and classifies them into symptomatic and asymptomatic. The classification result is based on a combination of discrete wavelet transform, higher order spectra (HOS) and textural features. In this study, we compare support vector machine (SVM) classifiers with different kernels. The classifier with a radial basis function (RBF) kernel achieved an average accuracy of 91.7% as well as a sensitivity of 97%, and specificity of 80%. Thus, it is evident that the selected features and the classifier combination can efficiently categorize plaques into symptomatic and asymptomatic classes. Moreover, a novel symptomatic asymptomatic carotid index (SACI), which is an integrated index that is based on the significant features, has been proposed in this work. Each analyzed ultrasound image yields on SACI number. A high SACI value indicates that the image shows symptomatic and low value indicates asymptomatic plaques. We hope this SACI can support vascular surgeons during routine screening for asymptomatic plaques. © 2012 Elsevier Ireland Ltd.
PubMed | University of Rome La Sapienza, Section of Vascular Surgery, Azienda Ospedaliero Universitaria of Cagliari Polo di Monserrato, AtheroPoint LLC and Italian Institute of Technology
Type: Journal Article | Journal: Journal of neuroradiology. Journal de neuroradiologie | Year: 2016
The relation between white matter loss (WML) and diabetes is still debated. The aim of this study was to investigate the correlation between typical WML- and diabetes-related magnetic resonance imaging (MRI) findings in a cohort of patients scheduled for carotid endarterectomy (CEA).Ninety-three consecutive patients (mean age 719years; male 71) were included in a single-centre retrospective study. All the patients underwent MRI as baseline evaluation prior to CEA. A neuroradiologist blinded to the presence of risk factors calculated WML volume and number of lesions on FLAIR images using a semi-automated segmentation technique. Receiver operating characteristics analysis was performed to search for any association between WML volume and the number of WML lesions. The Mann-Whitney tests were used to determine significant WML differences between diabetic and non-diabetic patients. Logistic regression analysis was performed to evaluate the potential association of other variables.The prevalence of diabetes was 20.4% (n=19). WML volume and number of WML lesions were significantly associated with diabetes (P=0.001). A statistically significant difference in WML volume was found between diabetic and non-diabetic patients (P<0.0001). Only diabetes, among all the investigated variables (WML volume, CAD status, age, smoking status, gender, hypertension, hyperlipidemia, diabetes) was significantly associated with WML (P=0.0001).Our results demonstrate a strong statistical correlation between diabetes and WML. Future scientific challenges could include the identification of potential therapeutic targets and the creation of dedicated screening protocols for WML in diabetic patients other than the simple measurement of leukoaraiosis total burden.
Molinari F.,Polytechnic University of Turin |
Meiburger K.M.,Polytechnic University of Turin |
Saba L.,A.U.O. Cagliari |
Rajendra Acharya U.,Ngee Ann Polytechnic |
And 5 more authors.
Ultrasonics | Year: 2012
Accurate intima-media thickness (IMT) measurement of the carotid artery from minimal plaque ultrasound images is a relevant clinical need, since IMT increase is related to the progression of atherosclerosis. In this paper, we describe a novel dual snake-based model for the high-performance carotid IMT measurement, called Carotid Measurement Using Dual Snakes (CMUDS). Snakes (which are deformable contours) adapt to the lumen-intima (LI) and media-adventitia (MA) interfaces, thus enabling the IMT computation as distance between the LI and MA snakes. However, traditional snakes might be unable to maintain a correct distance and in some spatial location along the artery, it might even collapse between them or diverge. The technical improvement of this work is the definition of a dual snake-based constrained system, which prevents the LI and MA snakes from collapsing or bleeding, thus optimizing the IMT estimation. The CMUDS system consists of two parametric models automatically initialized using the far adventitia border which we automatically traced by using a previously developed multi-resolution approach. The dual snakes evolve simultaneously and are constrained by the distances between them, ensuring the regularization of LI/MA topology. We benchmarked our automated CMUDS with the previous conventional semi-automated snake system called Carotid Measurement Using Single Snake (CMUSS). Two independent readers manually traced the LIMA boundaries of a multi-institutional, multi-ethnic, and multi-scanner database of 665 CCA longitudinal 2D images. We evaluated our system performance by comparing it with the gold standard as traced by clinical readers. CMUDS and CMUSS correctly processed 100% of the 665 images. Comparing the performance with respect to the two readers, our automatically measured IMT was on average very close to that of the two readers (IMT measurement biases for CMUSS was equal to -0.011 ± 0.329 mm and -0.045 ± 0.317 mm, respectively, while for CMUDS, it was 0.030 ± 0.284 mm and -0.004 ± 0.273 mm, respectively). The Figure-of-Merit of the system was 98.5% and 94.4% for CMUSS, while 96.0% and 99.6% for CMUDS, respectively. Results showed that the dual-snake system CMUDS reduced the IMT measurement error accuracy (Wilcoxon, p < 0.02) and the IMT error variability (Fisher, p < 3 × 10 -2). We propose the CMUDS technique for use in large multi-centric studies, where the need for a standard, accurate, and automated IMT measurement technique is required. © 2012 Elsevier B.V. All rights reserved.
Araki T.,Toho University |
Ikeda N.,National Center for Global Health and Medicine |
Molinarp F.,Polytechnic University of Turin |
Dey N.,Global Biomedical Technologies Inc. |
And 5 more authors.
International Angiology | Year: 2014
Aim. Establishing relationship between coronary calcium volumes from Intravascular Ultrasound (IVUS) and automated carotid intima-media thickness (cIMT) helps in understanding the genetic nature of atherosclerosis disease. In this research, we have quantified the detected calcium from IVUS video frames and associated a relationship between coronary calcium volumes computed and automated cIMT from B-mode ultrasound. Methods: Coronary calcium volume is computed from IVUS and auto cIMTs are computed using B-mode ultrasound. An automated computer based application is developed and tested on 100 patient volumes (an average of 2549 frames per volume) to calculate lesion area and normalized coronary calcium volume. We use an integrated approach for volume computation which is based on lesion area per frame. We have measured the normalized volume from the calcium detected video frames using proposed integration method. The cIMT of 100 carotids were measured with novel and dedicated automated software analysis (AtheroEdge™ from AtheroPoint™ LLC, Roseville, CA, USA). Results. The computer-based coronary calcium volume (from IVUS) showed a correlation coefficient with respect to cIMT for left and right carotids as 9.1% and 13.9%, respectively. Conclusion. Coronary calcium volume computed from IVUS and auto cIMT are moderately correlated. The association between auto cIMT (right side) vs. computer-based coronary calcium volume (IVUS) is stronger than the association between auto cIMT (left side) vs. computer-based coronary calcium volume.
Pedro L.M.,University of Lisbon |
Sanches J.M.,University of Lisbon |
Seabra J.,University of Lisbon |
Suri J.S.,AtheroPoint LLC |
And 2 more authors.
Echocardiography | Year: 2014
Active carotid plaques are associated with atheroembolism and neurological events; its identification is crucial for stroke prevention. High-definition ultrasound (HDU) can be used to recognize plaque structure in carotid bifurcation stenosis associated with plaque vulnerability and occurrence of brain ischemic events. A new computer-assisted HDU method to study the echomorphology of the carotid plaque and to determine a risk score for developing appropriate symptoms is proposed in this study. Plaque echomorphology characteristics such as presence of ulceration at the plaque surface, juxta-luminal location of echolucent areas, echoheterogeneity were obtained from B-mode ultrasound scans using several image processing algorithms and were combined with measurement of severity of stenosis to obtain a clinical score - enhanced activity index (EAI) - which was correlated with the presence or absence of ipsilateral appropriate ischemic symptoms. An optimal cutoff value of EAI was determined to obtain the best separation between symptomatic (active) from asymptomatic (inactive) plaques and its diagnostic yield was compared to other 2 reference methods by means of receiver-operating characteristic (ROC) analysis. Classification performance was evaluated by leave-one-patient-out cross-validation applied to a cohort of 146 carotid plaques from 99 patients. The proposed method was benchmarked against (a) degree of stenosis criteria and (b) earlier proposed activity index (AI) and demonstrated that EAI yielded the highest accuracy up to an accuracy of 77% to predict asymptomatic plaques that developed symptoms in a prospective cross-sectional study. Enhanced activity index is a noninvasive, easy to obtain parameter, which provided accurate estimation of neurological risk of carotid plaques. © 2013, Wiley Periodicals, Inc.
Gupta A.,New York Medical College |
Gupta A.,Brain and Mind Research Institute |
Kesavabhotla K.,New York Medical College |
Baradaran H.,New York Medical College |
And 10 more authors.
Stroke | Year: 2015
Background and Purpose-Ultrasonographic plaque echolucency has been studied as a stroke risk marker in carotid atherosclerotic disease. We performed a systematic review and meta-analysis to summarize the association between ultrasound-determined carotid plaque echolucency and future ipsilateral stroke risk.Methods-We searched the medical literature for studies evaluating the association between carotid plaque echolucency and future stroke in asymptomatic patients. We included prospective observational studies with stroke outcome ascertainment after baseline carotid plaque echolucency assessment. We performed a meta-analysis and assessed study heterogeneity and publication bias. We also performed subgroup analyses limited to patients with stenosis 50%, studies in which plaque echolucency was determined via subjective visual interpretation, studies with a relatively lower risk of bias, and studies published after the year 2000.Results-We analyzed data from 7 studies on 7557 subjects with a mean follow-up of 37.2 months. We found a significant positive relationship between predominantly echolucent (compared with predominantly echogenic) plaques and the risk of future ipsilateral stroke across all stenosis severities (0% to 99%; relative risk, 2.31; 95% confidence interval, 1.58-3.39; P<0.001) and in subjects with 50% stenosis (relative risk, 2.61; 95% confidence interval, 1.47-4.63; P=0.001). A statistically significant increased relative risk for future stroke was preserved in all additional subgroup analyses. No statistically significant heterogeneity or publication bias was present in any of the meta-analyses.Conclusions-The presence of ultrasound-determined carotid plaque echolucency provides predictive information in asymptomatic carotid artery stenosis beyond luminal stenosis. However, the magnitude of the increased risk is not sufficient on its own to iden tify patients likely to benefit from surgical revascularization. © 2014 American Heart Association, Inc.
Molinari F.,Polytechnic University of Turin |
Meiburger K.M.,Polytechnic University of Turin |
Saba L.,University of Cagliari |
Zeng G.,Mayo Medical School |
And 5 more authors.
Journal of Ultrasound in Medicine | Year: 2012
Automated computer-aided detection systems for measurement of the carotid intimamedia thickness (IMT) are becoming popular. These systems yield lumen-intima (LI) and media-adventitia (MA) borders. In this work, we developed and validated a novel and patented completely automated IMT measurement system called carotid measurement using dual snakes (CMUDS): a class of AtheroEdge system (Global Biomedical Technologies, Inc, Roseville, CA). CMUDS is modeled as a dual parametric system corresponding to LI and MA borders with initialization from the far adventitia layer. The novelty of CMUDS is the first-order absolute moment-based external energy, which provides stable deformation. The dual snakes evolve simultaneously and are forced to maintain a regularized distance to prevent collapsing or bleeding. Two independent readers manually traced the LI/MA boundaries of a multi-institutional, multiethnic, and multi-scanner database of 665 longitudinal images for performance evaluation. CMUDS was also benchmarked against a previously developed automated technique. CMUDS correctly processed 660 images (99.2% success). The differences between the CMUDS and two manual IMT measurements (mean ± SD) were 0.013 ± 0.216 and -0.021 ± 0.197 mm, respectively. The corresponding figures of merit for CMUDS compared to reader tracings were 98.4% and 97.5%. Compared to the previous technique (IMT differences, 0.022 ± 0.276 and -0.012 ± 0.266 mm), CMUDS improved accuracy (Wilcoxon P < 0.009) and variability (Fisher P > 10 -8). Among different resolution images from original equipment manufacturer ultrasound scanners, CMUDS performed best with high-resolution images corresponding to 0.0789 mm/pixel. Accuracy in IMT measurement with the proposed automated CMUDS technique makes this system adaptable to large multi-center studies, in which such an IMT measurement system would be very useful tool. © 2012 by the American Institute of Ultrasound in Medicine.
Saba L.,Azienda Ospedaliero Universitaria |
Raz E.,New York University |
Bassareo P.P.,Azienda Ospedaliero Universitaria |
Di Martino M.,University of Rome La Sapienza |
And 6 more authors.
Journal of Stroke and Cerebrovascular Diseases | Year: 2015
Purpose Cerebral microbleeds (CMBs) are small dot-like lesions appearing as hyposignals on gradient echo (GRE) T2∗ magnetic resonance (MR) sequences, whereas the leukoaraiosis (LA) indicates the presence of patchy areas of hypersignal on fluid-attenuated inversion recovery (FLAIR) MR sequences in the periventricular white matter. The purpose of this work was to evaluate the association between LA and CMBs. Material and Methods Eighty-five consecutive (men 55; median age 64 years) patients were retrospectively analyzed using a 1.5 T system; CMBs were studied using a T2∗-weighted GRE sequence and classified as absent (grade 1), mild (grade 2; total number of microbleeds, 1-2), moderate (grade 3; total number of microbleeds, 3-10), and severe (grade 4; total number of microbleeds, >10). LA was assessed with FLAIR MR sequences and was graded based on the European Task Force on Age-Related White Matter Changes as follows: 1 (no lesions), 2 (focal lesions > 5 mm), 3 (early confluent lesions), and 4 (diffuse involvement of an entire brain region). Results We considered 170 cerebral hemispheres. The prevalence of CMBs was 24.7% (42 of 170), whereas the prevalence of LA was 27.1% (46 of 170). A statistically significant correlation was observed between LA and CMBs (correlation rho =.495, P value =.001). Multiple logistic regression analysis showed an association between CMBs and cerebrovascular symptoms (P =.0023). Conclusion Results of this study suggest an association between CMBs and LA. Moreover, we found that LA is associated with the presence of cerebrovascular symptoms. © 2015 National Stroke Association.
AtheroPoint LLC | Date: 2013-02-26
Medical hand-held scanning devices for scanning blood vessels; computer programs for use in medical image analysis, diagnosis, and treatment, namely, software for processing digital images of the anatomy for analysis, diagnosis and treatment, and software for processing digital images of the anatomy to add additional visual elements to the digital images for enhanced analysis, diagnosis, monitoring, and treatment; computer software for creating searchable medical diagnosis, monitoring, and treatment databases.
AtheroPoint LLC | Date: 2012-08-20
Automated IMT system hypothesize that far wall of the common carotid artery has the highest intensity. In this current application, we verify that this hypothesis holds true for B-mode or RF-mode longitudinal ultrasound images of the carotid wall. The methodology consists of generating the composite image (arithmetic sum of images) from the database by first registering the carotid image frames with respect to a nearly straight carotid artery frame from the same database using (a) B-spline based non-rigid registration and (b) affine registration. Prior to registration, we segment the carotid artery lumen using a level set based algorithm followed by morphological image processing. The binary lumen images are registered and the transformations are applied to the original grayscale CCA images. These B-mode or RF-mode ultrasound images are then used for IMT computation using automated methods which hypothesize that far wall has the brightest intensity distribution.