Constrained snake vs. conventional snake for carotid ultrasound automated IMT measurements on multi-center data sets

Attention-Based UNet Deep Learning Model for Plaque Segmentation in Carotid Ultrasound for Stroke Risk Stratification: An Artificial Intelligence Paradigm

Stroke and cardiovascular diseases (CVD) significantly affect the world population. The early detection of such events may prevent the burden of death and costly surgery. Conventional methods are neither automated nor clinically accurate. Artificial Intelligence-based methods of automatically detecting and predicting the severity of CVD and stroke in their early stages are of prime importance. This study proposes an attention-channel-based UNet deep learning (DL) model that identifies the carotid plaques in the internal carotid artery (ICA) and common carotid artery (CCA) images. Our experiments consist of 970 ICA images from the UK, 379 CCA images from diabetic Japanese patients, and 300 CCA images from post-menopausal women from Hong Kong. We combined both CCA images to form an integrated database of 679 images. A rotation transformation technique was applied to 679 CCA images, doubling the database for the experiments. The cross-validation K5 (80% training: 20% testing) protocol was applied for accuracy determination. The results of the Attention-UNet model are benchmarked against UNet, UNet++, and UNet3P models. Visual plaque segmentation showed improvement in the Attention-UNet results compared to the other three models. The correlation coefficient (CC) value for Attention-UNet is 0.96, compared to 0.93, 0.96, and 0.92 for UNet, UNet++, and UNet3P models. Similarly, the AUC value for Attention-UNet is 0.97, compared to 0.964, 0.966, and 0.965 for other models. Conclusively, the Attention-UNet model is beneficial in segmenting very bright and fuzzy plaque images that are hard to diagnose using other methods. Further, we present a multi-ethnic, multi-center, racial bias-free study of stroke risk assessment.

Encoder-Decoder Architecture for Ultrasound IMC Segmentation and cIMT Measurement

Cardiovascular diseases (CVDs) have shown a huge impact on the number of deaths in the world. Thus, common carotid artery (CCA) segmentation and intima-media thickness (IMT) measurements have been significantly implemented to perform early diagnosis of CVDs by analyzing IMT features. Using computer vision algorithms on CCA images is not widely used for this type of diagnosis, due to the complexity and the lack of dataset to do it. The advancement of deep learning techniques has made accurate early diagnosis from images possible. In this paper, a deep-learning-based approach is proposed to apply semantic segmentation for intima-media complex (IMC) and to calculate the cIMT measurement. In order to overcome the lack of large-scale datasets, an encoder-decoder-based model is proposed using multi-image inputs that can help achieve good learning for the model using different features. The obtained results were evaluated using different image segmentation metrics which demonstrate the effectiveness of the proposed architecture. In addition, IMT thickness is computed, and the experiment showed that the proposed model is robust and fully automated compared to the state-of-the-art work.

Measurement of Intima-Media Thickness Depending on Intima Media Complex Segmentation by Deep Neural Networks

Intima Media Thickness (IMT) of the carotid artery is an important marker indicating the sign of cardiovascular disease. Automated measurement of IMT requires segmentation of intima media complex (IMC).Traditional methods which use shape, color and texture for classification have poor generalization capability. This paper proposes two models- the pipeline model and the end-to-end model using Convolutional Neural Networks (CNN) and auto encoder–decoder network respectively. CNN architecture is implemented and tested by varying the number of convolutional layer, size of the kernel as well as the number of kernels. Auto encoder–decoder performs pixel wise classification using two interconnected pathways for identifying the boundary of lumen-intima (LI) and media adventitia (MA). This helps in reconstruction of the segmented portion for measurement of IMT. Both methods are tested using a dataset of 550 subjects. The results clearly indicate that end-to-end model has an edge over the pipeline model exhibiting lesser deviation between the automated measurement and the measurement made by the radiologist. The pipeline model however has better segmentation accuracy when the size of the image used for training is small. The convolutional neural network with auto encoder–decoder proves robust through sparse representation, and faster learning with better generalization. Also, the experimental setup is analyzed by interconnecting Tensor flow simulated result with Raspberry PI and the outcomes are analyzed.

Automated Diagnosis of Cardiovascular Disease Through Measurement of Intima Media Thickness Using Deep Neural Networks

Ultrasound images(US) of carotid artery aid in the detection and diagnosis of Cardiovascular Diseases (CVD). Traditional methods for analysis of US images employ hand crafted features to classify images, which need expert knowledge for careful design and lack robustness to variations, leading to low sensitivity in clinical applications. Intima Media Thickness (IMT) and elasticity are the predominant markers used for carotid artery (CA) atherosclerotic plaque detection. This paper proposes to address the problem by building Convolutional Neural Network (CNN) for segmentation of intima media complex (ie) Region of Interest (RoI). A dataset consisting of 450 subjects is used to train and validate the proposed CNN. Segmentation is done in the far wall region of the artery from the longitudinal B-mode images enabling atleast 24 RoIs and RoNIs (Region of Non Interest) for each image. The result of 10-fold cross validation shows accuracy of 99.54%. Mean deviation of IMT from manual tracings is found to be 0.06645mm.

Two-stage artificial intelligence model for jointly measurement of atherosclerotic wall thickness and plaque burden in carotid ultrasound: A screening tool for cardiovascular/stroke risk assessment

MOTIVATION

The early screening of cardiovascular diseases (CVD) can lead to effective treatment. Thus, accurate and reliable atherosclerotic carotid wall detection and plaque measurements are crucial. Current measurement methods are time-consuming and do not utilize the power of knowledge-based paradigms such as artificial intelligence (AI). We present an AI-based methodology for the joint automated detection and measurement of wall thickness and carotid plaque (CP) in the form of carotid intima-media thickness (cIMT) and total plaque area (TPA), a class of AtheroEdge™ system (AtheroPoint™, CA, USA).

METHOD

The novel system consists of two stages, and each stage comprises an independent deep learning (DL) model. In Stage I, the first DL model segregates the common carotid artery (CCA) patches from ultrasound (US) images into the rectangular wall and non-wall patches. The characterized wall patches are integrated to form the region of interest (ROI), which is then fed into Stage II. In Stage II, the second DL model segments the far wall region. Lumen-intima (LI) and media-adventitial (MA) boundaries are then extracted from the wall region, which is then used for cIMT and PA measurement.

RESULTS

Using the database of 250 carotid scans, the cIMT error using the AI model is 0.0935±0.0637 mm, which is lower than those of all previous methods. The PA error is found to be 2.7939±2.3702 mm². The system's correlation coefficient (CC) between AI and ground truth (GT) values for cIMT is 0.99 (p < 0.0001), which is higher compared with the CC of 0.96 (p < 0.0001) shown by the earlier DL method. The CC for PA between AI and GT values is 0.89 (p < 0.0001).

CONCLUSION

A novel AI-based strategy was applied to carotid US images for the joint detection of carotid wall thickness (cWT) and plaque area (PA), followed by cIMT and PA measurement. This AI-based strategy shows improved performance using the patch technique compared with previous methods using full carotid scans.

Automatic Optic Nerve Measurement: A New Tool to Standardize Optic Nerve Assessment in Ultrasound B-Mode Images

Transorbital sonography provides reliable information about the estimation of intra-cranial pressure by measuring the optic nerve sheath diameter (ONSD), whereas the optic nerve (ON) diameter (OND) may reveal ON atrophy in patients with multiple sclerosis. Here, an AUTomatic Optic Nerve MeAsurement (AUTONoMA) system for OND and ONSD assessment in ultrasound B-mode images based on deformable models is presented. The automated measurements were compared with manual ones obtained by two operators, with no significant differences. AUTONoMA correctly segmented the ON and its sheath in 71 out of 75 images. The mean error compared with the expert operator was 0.06 ± 0.52 mm and 0.06 ± 0.35 mm for the ONSD and OND, respectively. The agreement between operators and AUTONoMA was good and a positive correlation was found between the readers and the algorithm with errors comparable with the inter-operator variability. The AUTONoMA system may allow for standardization of OND and ONSD measurements, reducing manual evaluation variability.

Morphological Carotid Plaque Area Is Associated With Glomerular Filtration Rate: A Study of South Asian Indian Patients With Diabetes and Chronic Kidney Disease

We evaluated the association between automatically measured carotid total plaque area (TPA) and the estimated glomerular filtration rate (eGFR), a biomarker of chronic kidney disease (CKD). Automated average carotid intima-media thickness (cIMTave) and TPA measurements in carotid ultrasound (CUS) were performed using AtheroEdge (AtheroPoint). Pearson correlation coefficient (CC) was then computed between the TPA and eGFR for (1) males versus females, (2) diabetic versus nondiabetic patients, and (3) between the left and right carotid artery. Overall, 339 South Asian Indian patients with either type 2 diabetes mellitus (T2DM) or CKD, or hypertension (stage 1 or stage 2) were retrospectively analyzed by acquiring cIMTave and TPA measurements of their left and right common carotid arteries (CCA; total CUS: 678, mean age: 54.2 ± 9.8 years; 75.2% males; 93.5% with T2DM). The CC between TPA and eGFR for different scenarios were (1) for males and females -0.25 (P < .001) and -0.35 (P < .001), respectively; (2) for T2DM and non-T2DM -0.26 (P < .001) and -0.49 (P = .02), respectively, and (3) for left and right CCA -0.25 (P < .001) and -0.23 (P < .001), respectively. Automated TPA is an equally reliable biomarker compared with cIMTave for patients with CKD (with or without T2DM) with subclinical atherosclerosis.

Evaluation Of Atherosclerosis Severity Based On Carotid Artery Intima-Media Thickness Changes: A New Diagnostic Criterion

This study aimed to identify instant intima-media thickness changes (ΔIMT) in the common carotid artery (CCA) during cardiac cycle in order to assess atherosclerosis progression. Using a computerized semi-automated method, instant IMT changes were extracted in the two walls of the left CCA (240 consecutive patients) using B-mode ultrasound images. We found that CCA ΔIMT increased from 8 ± 4% of IMT_max in the controls to 15 ± 6% of IMT_max in the severe stenosis group. According to the multiple ordinal regression analysis, ΔIMT was associated with the severity of carotid artery stenosis (odds ratio [OR], 4.95; p < 0.001), independent of sex (OR, 1.11; p = 0.04), age (OR, 1.14; p < 0.001), body mass index; OR, 1.13; p = 0.036), hypertension (OR, 2.04; p < 0.001), diabetes (OR, 1.38; p = 0.045) and hyperlipidemia (OR, 1.54; p = 0.002). We concluded that increment of CCA ΔIMT during the cardiac cycle was strongly and independently associated with severity of carotid artery stenosis or atherosclerosis progression.

Improved Deep Learning Network Based in combination with Cost-sensitive Learning for Early Detection of Ovarian Cancer in Color Ultrasound Detecting System

With the development of theories and technologies in medical imaging, most of the tumors can be detected in the early stage. However, the nature of ovarian cysts lacks accurate judgement, leading to that many patients with benign nodules still need Fine Needle Aspiration (FNA) biopsies or surgeries, increasing the physical pain and mental pressure of patients as well as unnecessary medical health care costs. Therefore, we present an image diagnosis system for classifying the ovarian cysts in color ultrasound images, which novelly applies the image features fused by both high-level features from deep learning network and low-level features from texture descriptor. Firstly, the ultrasound images are enhanced to improve the quality of training data set and the rotation invariant uniform local binary pattern (ULBP) features are extracted from each of the images as the low-level texture features. Then the high-level deep features extracted by the fine-tuned GoogLeNet neural network and the low-level ULBP features are normalized and cascaded as one fusion feature that can represent both the semantic context and the texture patterns distributed in the image. Finally, the fusion features are input to the Cost-sensitive Random Forest classifier to classify the images into "malignant" and "benign". The high-level features extracted by the deep neural network from the medical ultrasound image can reflect the visual features of the lesion region, while the low-level texture features can describe the edges, direction and distribution of intensities. Experimental results indicate that the combination of the two types of features can describe the differences between the lesion regions and other regions, and the differences between lesions regions of malignant and benign ovarian cysts.

Automated localization and segmentation techniques for B-mode ultrasound images: A review

B-mode ultrasound imaging is used extensively in medicine. Hence, there is a need to have efficient segmentation tools to aid in computer-aided diagnosis, image-guided interventions, and therapy. This paper presents a comprehensive review on automated localization and segmentation techniques for B-mode ultrasound images. The paper first describes the general characteristics of B-mode ultrasound images. Then insight on the localization and segmentation of tissues is provided, both in the case in which the organ/tissue localization provides the final segmentation and in the case in which a two-step segmentation process is needed, due to the desired boundaries being too fine to locate from within the entire ultrasound frame. Subsequenly, examples of some main techniques found in literature are shown, including but not limited to shape priors, superpixel and classification, local pixel statistics, active contours, edge-tracking, dynamic programming, and data mining. Ten selected applications (abdomen/kidney, breast, cardiology, thyroid, liver, vascular, musculoskeletal, obstetrics, gynecology, prostate) are then investigated in depth, and the performances of a few specific applications are compared. In conclusion, future perspectives for B-mode based segmentation, such as the integration of RF information, the employment of higher frequency probes when possible, the focus on completely automatic algorithms, and the increase in available data are discussed.

Appraisal of different ultrasonography indices in patients with carotid artery atherosclerosis

In this study a semi-automated image-processing based method was designed in which the parameters such as intima-media thickness (IMT), resistive index (RI), pulsatility index (PI), dicrotic notch index (DNI), and mean wavelet entropy (MWE) were evaluated in B-mode and Doppler ultrasound in patients presenting with carotid artery atherosclerosis. In a cross-sectional design, 144 men were divided into four groups of control, mild, moderate and severe stenosis subjects. In all individuals, far wall IMT, RI, PI, DNI, and MWE of the left common carotid artery (CCA) were extracted using the proposed method. Our findings showed that the maximum far wall IMT, RI, PI, DNI in the CCA were significantly different in the patients with mild, moderate, and severe stenosis compared to control group (p-value < 0.05), however, there were no significant differences in MWE among the four groups (p-value > 0.05). The proposed method can help physicians to better identify patients at risk of cardiovascular diseases.

Plaque Tissue Morphology-Based Stroke Risk Stratification Using Carotid Ultrasound: A Polling-Based PCA Learning Paradigm

Severe atherosclerosis disease in carotid arteries causes stenosis which in turn leads to stroke. Machine learning systems have been previously developed for plaque wall risk assessment using morphology-based characterization. The fundamental assumption in such systems is the extraction of the grayscale features of the plaque region. Even though these systems have the ability to perform risk stratification, they lack the ability to achieve higher performance due their inability to select and retain dominant features. This paper introduces a polling-based principal component analysis (PCA) strategy embedded in the machine learning framework to select and retain dominant features, resulting in superior performance. This leads to more stability and reliability. The automated system uses offline image data along with the ground truth labels to generate the parameters, which are then used to transform the online grayscale features to predict the risk of stroke. A set of sixteen grayscale plaque features is computed. Utilizing the cross-validation protocol (K = 10), and the PCA cutoff of 0.995, the machine learning system is able to achieve an accuracy of 98.55 and 98.83%corresponding to the carotidfar wall and near wall plaques, respectively. The corresponding reliability of the system was 94.56 and 95.63%, respectively. The automated system was validated against the manual risk assessment system and the precision of merit for same cross-validation settings and PCA cutoffs are 98.28 and 93.92%for the far and the near wall, respectively.PCA-embedded morphology-based plaque characterization shows a powerful strategy for risk assessment and can be adapted in clinical settings.

Automated segmental-IMT measurement in thin/thick plaque with bulb presence in carotid ultrasound from multiple scanners: Stroke risk assessment

BACKGROUND AND OBJECTIVES

Standardization of the carotid IMT requires a reference marker in ultrasound scans. It has been shown previously that manual reference marker and manually created carotid segments are used for measuring IMT in these segments. Manual methods are tedious, time consuming, subjective, and prone to errors. Bulb edge can be considered as a reference marker for measurements of the cIMT. However, bulb edge can be difficult to locate in ultrasound scans due to: (a) low signal to noise ratio in the bulb region as compared to common carotid artery region; (b) uncertainty of bulb location in craniocaudal direction; and (c) variability in carotid bulb shape and size. This paper presents an automated system (a class of AtheroEdge™ system from AtheroPoint™, Roseville, CA, USA) for locating the bulb edge as a reference marker and further develop segmental-IMT (sIMT) which measures IMT in 10mm segments (namely: s1, s2 and s3) proximal to the bulb edge.

METHODS

The patented methodology uses an integrated approach which combines carotid geometry and pixel-classification paradigms. The system first finds the bulb edge and then measures the sIMT proximal to the bulb edge. The system also estimates IMT in bulb region (bIMT). The 649 image database consists of varying plaque (light, moderate to heavy), image resolutions, shapes, sizes and ethnicity.

RESULTS

Our results show that the IMT contributions in different carotid segments are as follows: bulb-IMT 34%, s1-IMT 29.46%, s2-IMT 11.48%, and s3-IMT 12.75%, respectively. We compare our automated results against reader's tracings demonstrating the following performance: mean lumen-intima error: 0.01235 ± 0.01224mm, mean media-adventitia error: 0.020933 ± 0.01539mm and mean IMT error: 0.01063 ± 0.0031mm. Our system's Precision of Merit is: 98.23%, coefficient of correlation between automated and Reader's IMT is: 0.998 (p-value < 0.0001). These numbers are improved compared to previous publications by Suri's group which is automated multi-resolution conventional cIMT.

CONCLUSIONS

Our fully automated bulb detection system reports 92.67% precision against ideal bulb edge locations as marked by the reader in the bulb transition zone.

Accurate lumen diameter measurement in curved vessels in carotid ultrasound: an iterative scale-space and spatial transformation approach

Monitoring of cerebrovascular diseases via carotid ultrasound has started to become a routine. The measurement of image-based lumen diameter (LD) or inter-adventitial diameter (IAD) is a promising approach for quantification of the degree of stenosis. The manual measurements of LD/IAD are not reliable, subjective and slow. The curvature associated with the vessels along with non-uniformity in the plaque growth poses further challenges. This study uses a novel and generalized approach for automated LD and IAD measurement based on a combination of spatial transformation and scale-space. In this iterative procedure, the scale-space is first used to get the lumen axis which is then used with spatial image transformation paradigm to get a transformed image. The scale-space is then reapplied to retrieve the lumen region and boundary in the transformed framework. Then, inverse transformation is applied to display the results in original image framework. Two hundred and two patients' left and right common carotid artery (404 carotid images) B-mode ultrasound images were retrospectively analyzed. The validation of our algorithm has done against the two manual expert tracings. The coefficient of correlation between the two manual tracings for LD was 0.98 (p < 0.0001) and 0.99 (p < 0.0001), respectively. The precision of merit between the manual expert tracings and the automated system was 97.7 and 98.7%, respectively. The experimental analysis demonstrated superior performance of the proposed method over conventional approaches. Several statistical tests demonstrated the stability and reliability of the automated system.

Stroke Risk Stratification and its Validation using Ultrasonic Echolucent Carotid Wall Plaque Morphology: A Machine Learning Paradigm

Stroke risk stratification based on grayscale morphology of the ultrasound carotid wall has recently been shown to have a promise in classification of high risk versus low risk plaque or symptomatic versus asymptomatic plaques. In previous studies, this stratification has been mainly based on analysis of the far wall of the carotid artery. Due to the multifocal nature of atherosclerotic disease, the plaque growth is not restricted to the far wall alone. This paper presents a new approach for stroke risk assessment by integrating assessment of both the near and far walls of the carotid artery using grayscale morphology of the plaque. Further, this paper presents a scientific validation system for stroke risk assessment. Both these innovations have never been presented before. The methodology consists of an automated segmentation system of the near wall and far wall regions in grayscale carotid B-mode ultrasound scans. Sixteen grayscale texture features are computed, and fed into the machine learning system. The training system utilizes the lumen diameter to create ground truth labels for the stratification of stroke risk. The cross-validation procedure is adapted in order to obtain the machine learning testing classification accuracy through the use of three sets of partition protocols: (5, 10, and Jack Knife). The mean classification accuracy over all the sets of partition protocols for the automated system in the far and near walls is 95.08% and 93.47%, respectively. The corresponding accuracies for the manual system are 94.06% and 92.02%, respectively. The precision of merit of the automated machine learning system when compared against manual risk assessment system are 98.05% and 97.53% for the far and near walls, respectively. The ROC of the risk assessment system for the far and near walls is close to 1.0 demonstrating high accuracy.

Two Automated Techniques for Carotid Lumen Diameter Measurement: Regional versus Boundary Approaches

The degree of stenosis in the carotid artery can be predicted using automated carotid lumen diameter (LD) measured from B-mode ultrasound images. Systolic velocity-based methods for measurement of LD are subjective. With the advancement of high resolution imaging, image-based methods have started to emerge. However, they require robust image analysis for accurate LD measurement. This paper presents two different algorithms for automated segmentation of the lumen borders in carotid ultrasound images. Both algorithms are modeled as a two stage process. Stage one consists of a global-based model using scale-space framework for the extraction of the region of interest. This stage is common to both algorithms. Stage two is modeled using a local-based strategy that extracts the lumen interfaces. At this stage, the algorithm-1 is modeled as a region-based strategy using a classification framework, whereas the algorithm-2 is modeled as a boundary-based approach that uses the level set framework. Two sets of databases (DB), Japan DB (JDB) (202 patients, 404 images) and Hong Kong DB (HKDB) (50 patients, 300 images) were used in this study. Two trained neuroradiologists performed manual LD tracings. The mean automated LD measured was 6.35 ± 0.95 mm for JDB and 6.20 ± 1.35 mm for HKDB. The precision-of-merit was: 97.4 % and 98.0 % w.r.t to two manual tracings for JDB and 99.7 % and 97.9 % w.r.t to two manual tracings for HKDB. Statistical tests such as ANOVA, Chi-Squared, T-test, and Mann-Whitney test were conducted to show the stability and reliability of the automated techniques.

An automated technique for carotid far wall classification using grayscale features and wall thickness variability

PURPOSE

To test a computer-aided diagnostic method for differentiating symptomatic from asymptomatic carotid B-mode ultrasonographic images.

METHODS

Our system (called Atheromatic) automatically computed the intima-media thickness (IMT) of the carotid far wall using AtheroEdge, calculated nonlinear features based on higher order spectra, and used these features and IMT and IMT variability (IMTVpoly ) to associate each image to a feature vector that was then labeled as symptomatic or asymptomatic (Sym/Asym) by a multiclassifiers system. We tested this method on a database of 118 carotid artery images from 37 symptomatic and 22 asymptomatic patients

RESULTS

The highest accuracy (99.1%) was obtained by the support vector machine classifier using seven features. These features, relevant to discriminate Sym/Asym, included IMT and IMTVpoly , along with the bispectral entropies of the distal wall image at 77°, 78°, and 79° angles.

CONCLUSIONS

Classification in Sym/Asym of the far carotid wall is feasible and accurate and could be useful for the early detection of atherosclerosis and to identify patients with higher cardiovascular risk.

Association of automated carotid IMT measurement and HbA1c in Japanese patients with coronary artery disease

AIMS

The purpose of this study was to evaluate whether carotid IMT (cIMT) identified using automated software is associated with HbA1c in Japanese patients with coronary artery disease.

METHODS

370 consecutive patients (males 218; median age 69 years ± 11) who underwent carotid-US and first coronary angiography were prospectively analyzed. After ultrasonographic examinations were performed, the plaque score (PS) was calculated and automated IMT analysis was obtained with a dedicated algorithm. Pearson correlation analysis was performed to calculate the association between automated IMT, PS and HbA1c.

RESULTS

The mean value of cIMT was 1.00 ± 0.47 mm for the right carotid and 1.04 ± 0.49 mm for the left carotid; the average bilateral value was 1.02 ± 0.43 mm. No significant difference of cIMT was detected between men and women. We found a direct correlation between cIMT values and HbA1c (p=0.0007) whereas the plaque score did not correlate with the HbA1c values (p>0.05) CONCLUSION: The results of our study confirm that automated cIMT values and levels of HbA1c in Japanese patients with coronary artery disease are correlated whereas the plaque score does not show a statistically significant correlation.