Characterization of single thyroid nodules by contrast-enhanced 3-D ultrasound

Cardiovascular Disease Risk Stratification Using Hybrid Deep Learning Paradigm: First of Its Kind on Canadian Trial Data

BACKGROUND

The risk of cardiovascular disease (CVD) has traditionally been predicted via the assessment of carotid plaques. In the proposed study, AtheroEdge™ 3.0HDL (AtheroPoint™, Roseville, CA, USA) was designed to demonstrate how well the features obtained from carotid plaques determine the risk of CVD. We hypothesize that hybrid deep learning (HDL) will outperform unidirectional deep learning, bidirectional deep learning, and machine learning (ML) paradigms.

METHODOLOGY

500 people who had undergone targeted carotid B-mode ultrasonography and coronary angiography were included in the proposed study. ML feature selection was carried out using three different methods, namely principal component analysis (PCA) pooling, the chi-square test (CST), and the random forest regression (RFR) test. The unidirectional and bidirectional deep learning models were trained, and then six types of novel HDL-based models were designed for CVD risk stratification. The AtheroEdge™ 3.0HDL was scientifically validated using seen and unseen datasets while the reliability and statistical tests were conducted using CST along with p-value significance. The performance of AtheroEdge™ 3.0HDL was evaluated by measuring the p-value and area-under-the-curve for both seen and unseen data.

RESULTS

The HDL system showed an improvement of 30.20% (0.954 vs. 0.702) over the ML system using the seen datasets. The ML feature extraction analysis showed 70% of common features among all three methods. The generalization of AtheroEdge™ 3.0HDL showed less than 1% (p-value < 0.001) difference between seen and unseen data, complying with regulatory standards.

CONCLUSIONS

The hypothesis for AtheroEdge™ 3.0HDL was scientifically validated, and the model was tested for reliability and stability and is further adaptable clinically.

DermAI 1.0: A Robust, Generalized, and Novel Attention-Enabled Ensemble-Based Transfer Learning Paradigm for Multiclass Classification of Skin Lesion Images

Skin lesion classification plays a crucial role in dermatology, aiding in the early detection, diagnosis, and management of life-threatening malignant lesions. However, standalone transfer learning (TL) models failed to deliver optimal performance. In this study, we present an attention-enabled ensemble-based deep learning technique, a powerful, novel, and generalized method for extracting features for the classification of skin lesions. This technique holds significant promise in enhancing diagnostic accuracy by using seven pre-trained TL models for classification. Six ensemble-based DL (EBDL) models were created using stacking, softmax voting, and weighted average techniques. Furthermore, we investigated the attention mechanism as an effective paradigm and created seven attention-enabled transfer learning (aeTL) models before branching out to construct three attention-enabled ensemble-based DL (aeEBDL) models to create a reliable, adaptive, and generalized paradigm. The mean accuracy of the TL models is 95.30%, and the use of an ensemble-based paradigm increased it by 4.22%, to 99.52%. The aeTL models' performance was superior to the TL models in accuracy by 3.01%, and aeEBDL models outperformed aeTL models by 1.29%. Statistical tests show significant p-value and Kappa coefficient along with a 99.6% reliability index for the aeEBDL models. The approach is highly effective and generalized for the classification of skin lesions.

Use of 3D ultrasound to characterise temporal changes in thyroid nodules: an in vitro study

OBJECTIVE

Thyroid nodules are extremely common, with prevalence rate up to 68%, yet only 7-15% of these are malignant. Many nodules require surveillance and 2-dimensional ultrasound (2D US) is used. Issues include the huge workload of obtaining and labeling images and difficulty comparing sizes of nodules over time due to large inter-operator variability. Inaccuracies may result in unnecessary FNAC or missed diagnosis of malignant nodules.

METHODS

We compared two techniques: freehand plain 2D US against freehand 2D US with gyroscopic guidance, both followed by 3D reconstruction using software. We measured the volume of nodules and a normal thyroid gland.

RESULTS

We found 2D US with gyroscopic guidance to be superior to plain 2D US as 3D reconstructions of greater accuracy are produced. The volume of the thyroid lobe measured 8.42 cm3 ± 0.94 was reasonably close to the normal average volume. However, the measured volume of the ellipsoidal nodule by the software is 8.69 cm3 ± 0.97 while the measured volume of the spherical nodule is 7.09 cm3 ± 0.79. As the expected volume of the nodules were 4.24cm3 and 4.19 cm3 respectively, the measured volume of the nodule was not accurate. The time taken to characterise nodules was reduced greatly from over 30 min in usual procedure to less than 10 min.

CONCLUSION

We find 3D US promising for evaluating size of thyroid nodules, with potential to study other TIRAD characteristics. Freehand 2D US with gyroscopic guidance shows the most promise for producing reliable, accurate and faster 3D reconstructions of thyroid nodules.

Contrast-Enhanced Ultrasonography for Differential Diagnosis of Benign and Malignant Thyroid Lesions: Single-Institutional Prospective Study of Qualitative and Quantitative CEUS Characteristics

Objectives

To extend and revise the diagnostic value of contrast-enhanced ultrasonography (CEUS) for differentiation between malignant and benign thyroid nodules.

Methods

This single-institution prospective study aims to compare CEUS qualitative and objective quantitative parameters in benign and malignant thyroid nodules. Consecutive cohort of 100 patients was examined by CEUS, 68 out of them were further analysed in detail. All included patients underwent cytological and/or histopathological verification of the diagnosis.

Results

Fifty-five (81%) thyroid nodules were benign, and 13 (19%) were malignant. Ring enhancement pattern was strongly associated with a benign aetiology (positive predictive value 100%) and heterogeneous enhancement pattern with malignant aetiology (positive predictive value 72.7%). The shape of the TIC (time-intensity curve) was more often identical in the benign lesion (98.2%) than in malignant lesions (69.2%), p=0.004.

Conclusions

This study indicates that CEUS enhancement patterns were significantly different in benign and malignant lesions. Ring enhancement was a very strong indicator of benign lesions, whereas heterogeneous enhancement was valuable to detect malignant lesions.

Cardiovascular Risk Stratification in Diabetic Retinopathy via Atherosclerotic Pathway in COVID-19/non-COVID-19 Frameworks using Artificial Intelligence Paradigm: A Narrative Review

Diabetes is one of the main causes of the rising cases of blindness in adults. This microvascular complication of diabetes is termed diabetic retinopathy (DR) and is associated with an expanding risk of cardiovascular events in diabetes patients. DR, in its various forms, is seen to be a powerful indicator of atherosclerosis. Further, the macrovascular complication of diabetes leads to coronary artery disease (CAD). Thus, the timely identification of cardiovascular disease (CVD) complications in DR patients is of utmost importance. Since CAD risk assessment is expensive for low-income countries, it is important to look for surrogate biomarkers for risk stratification of CVD in DR patients. Due to the common genetic makeup between the coronary and carotid arteries, low-cost, high-resolution imaging such as carotid B-mode ultrasound (US) can be used for arterial tissue characterization and risk stratification in DR patients. The advent of artificial intelligence (AI) techniques has facilitated the handling of large cohorts in a big data framework to identify atherosclerotic plaque features in arterial ultrasound. This enables timely CVD risk assessment and risk stratification of patients with DR. Thus, this review focuses on understanding the pathophysiology of DR, retinal and CAD imaging, the role of surrogate markers for CVD, and finally, the CVD risk stratification of DR patients. The review shows a step-by-step cyclic activity of how diabetes and atherosclerotic disease cause DR, leading to the worsening of CVD. We propose a solution to how AI can help in the identification of CVD risk. Lastly, we analyze the role of DR/CVD in the COVID-19 framework.

Automated deep learning-based paradigm for high-risk plaque detection in B-mode common carotid ultrasound scans: an asymptomatic Japanese cohort study

BACKGROUND

The death due to stroke is caused by embolism of the arteries which is due to the rupture of the atherosclerotic lesions in carotid arteries. The lesion formation is over time, and thus, early screening is recommended for asymptomatic and moderate-risk patients. The previous techniques adopted conventional methods or semi-automated and, more recently, machine learning solutions. A handful of studies have emerged based on solo deep learning (SDL) models such as UNet architecture.

METHODS

The proposed research is the first to adopt hybrid deep learning (HDL) artificial intelligence models such as SegNet-UNet. This model is benchmarked against UNet and advanced conventional models using scale-space such as AtheroEdge 2.0 (AtheroPoint, CA, USA). All our resultant statistics of the three systems were in the order of UNet, SegNet-UNet, and AtheroEdge 2.0.

RESULTS

Using the database of 379 ultrasound scans from a Japanese cohort of 190 patients having moderate risk and implementing the cross-validation deep learning framework, our system performance using area-under-the-curve (AUC) for UNet, SegNet-UNet, and AtheroEdge 2.0 were 0.93, 0.94, and 0.95 (p<0.001), respectively. The coefficient of correlation between the three systems and ground truth (GT) were: 0.82, 0.89, and 0.85 (p<0.001 for all three), respectively. The mean absolute area error for the three systems against manual GT was 4.07±4.70 mm2, 3.11±3.92 mm2, 3.72±4.76 mm2, respectively, proving the superior performance SegNet-UNet against UNet and AtheroEdge 2.0, respectively. Statistical tests were also conducted for their reliability and stability.

CONCLUSIONS

The proposed study demonstrates a fast, accurate, and reliable solution for early detection and quantification of plaque lesions in common carotid artery ultrasound scans. The system runs on a test US image in < 1 second, proving overall performance to be clinically reliable.

Inter-Variability Study of COVLIAS 1.0: Hybrid Deep Learning Models for COVID-19 Lung Segmentation in Computed Tomography

Background: For COVID-19 lung severity, segmentation of lungs on computed tomography (CT) is the first crucial step. Current deep learning (DL)-based Artificial Intelligence (AI) models have a bias in the training stage of segmentation because only one set of ground truth (GT) annotations are evaluated. We propose a robust and stable inter-variability analysis of CT lung segmentation in COVID-19 to avoid the effect of bias. Methodology: The proposed inter-variability study consists of two GT tracers for lung segmentation on chest CT. Three AI models, PSP Net, VGG-SegNet, and ResNet-SegNet, were trained using GT annotations. We hypothesized that if AI models are trained on the GT tracings from multiple experience levels, and if the AI performance on the test data between these AI models is within the 5% range, one can consider such an AI model robust and unbiased. The K5 protocol (training to testing: 80%:20%) was adapted. Ten kinds of metrics were used for performance evaluation. Results: The database consisted of 5000 CT chest images from 72 COVID-19-infected patients. By computing the coefficient of correlations (CC) between the output of the two AI models trained corresponding to the two GT tracers, computing their differences in their CC, and repeating the process for all three AI-models, we show the differences as 0%, 0.51%, and 2.04% (all < 5%), thereby validating the hypothesis. The performance was comparable; however, it had the following order: ResNet-SegNet > PSP Net > VGG-SegNet. Conclusions: The AI models were clinically robust and stable during the inter-variability analysis on the CT lung segmentation on COVID-19 patients.

Clinical value of SMI Combined with Low-Dose CT Scanning in differential diagnosis of Thyroid Lesions and Tumor Staging

Objectives

To investigate the clinical value of Superb Microvascular Imaging (SMI) combined with low dose CT scanning in differential diagnosis of thyroid lesions and tumor staging.

Methods

A total of 120 patients with thyroid nodules admitted to the Chinese PLA General Hospital from January 2017 to July 2020 were selected. Paired design was adopted in this study. SMI and SMI combined with low-dose CT scanning were respectively carried out to these patients. The results were judged by two senior imaging physicians and two senior sonographers respectively. And t-test, χ² test, Pearson correlation coefficient check and other methods were adopted to comparatively analyze the above two methods and the pathological results after operation or puncture.

Results

Compared with pathologic findings, the coincidence rate of SMI was 40%, and the coincidence rate of SMI combined with low dose CT scanning was 84%. The difference was significant (p=0.00); among the 120 thyroid nodule patients, 50 were diagnosed as malignant by pathological diagnosis, and 70 as benign; 27 malignant cases and 93 benign cases were detected by SMI; 48 malignant cases and 72 benign cases were detected by SMI combined with low dose CT scanning. The sensitivity and accuracy of the latter were significantly higher than those of the former, and the difference was statistically significant (p=0.00); the enhancement, edge sharpness and homogeneity of SMI increased with the increase of tumor malignancy, showing positive correlation property.

Conclusion

SMI combined with low dose CT scanning has a higher diagnostic coincidence rate. Its sensitivity and accuracy are significantly superior. With the increase of tumor malignancy, the enhancement and unhomogeneity of SMI increase, and the edge is more blurred. That suggests: with the increase of tumor malignancy, neovascularization in the tumor is more obvious and more unevenly distributed; the increase of edge blur indicates more obvious tumor infiltration. The method has considerable clinical value for predicting the malignancy of tumors.

COVLIAS 1.0: Lung Segmentation in COVID-19 Computed Tomography Scans Using Hybrid Deep Learning Artificial Intelligence Models

BACKGROUND

COVID-19 lung segmentation using Computed Tomography (CT) scans is important for the diagnosis of lung severity. The process of automated lung segmentation is challenging due to (a) CT radiation dosage and (b) ground-glass opacities caused by COVID-19. The lung segmentation methodologies proposed in 2020 were semi- or automated but not reliable, accurate, and user-friendly. The proposed study presents a COVID Lung Image Analysis System (COVLIAS 1.0, AtheroPoint™, Roseville, CA, USA) consisting of hybrid deep learning (HDL) models for lung segmentation.

METHODOLOGY

The COVLIAS 1.0 consists of three methods based on solo deep learning (SDL) or hybrid deep learning (HDL). SegNet is proposed in the SDL category while VGG-SegNet and ResNet-SegNet are designed under the HDL paradigm. The three proposed AI approaches were benchmarked against the National Institute of Health (NIH)-based conventional segmentation model using fuzzy-connectedness. A cross-validation protocol with a 40:60 ratio between training and testing was designed, with 10% validation data. The ground truth (GT) was manually traced by a radiologist trained personnel. For performance evaluation, nine different criteria were selected to perform the evaluation of SDL or HDL lung segmentation regions and lungs long axis against GT.

RESULTS

Using the database of 5000 chest CT images (from 72 patients), COVLIAS 1.0 yielded AUC of ~0.96, ~0.97, ~0.98, and ~0.96 (p-value < 0.001), respectively within 5% range of GT area, for SegNet, VGG-SegNet, ResNet-SegNet, and NIH. The mean Figure of Merit using four models (left and right lung) was above 94%. On benchmarking against the National Institute of Health (NIH) segmentation method, the proposed model demonstrated a 58% and 44% improvement in ResNet-SegNet, 52% and 36% improvement in VGG-SegNet for lung area, and lung long axis, respectively. The PE statistics performance was in the following order: ResNet-SegNet > VGG-SegNet > NIH > SegNet. The HDL runs in <1 s on test data per image.

CONCLUSIONS

The COVLIAS 1.0 system can be applied in real-time for radiology-based clinical settings.

Hybrid deep learning segmentation models for atherosclerotic plaque in internal carotid artery B-mode ultrasound

The automated and accurate carotid plaque segmentation in B-mode ultrasound (US) is an essential part of stroke risk stratification. Previous segmented methods used AtheroEdge™ 2.0 (AtheroPoint™, Roseville, CA) for the common carotid artery (CCA). This study focuses on automated plaque segmentation in the internal carotid artery (ICA) using solo deep learning (SDL) and hybrid deep learning (HDL) models. The methodology consists of a novel design of 10 types of SDL/HDL models (AtheroEdge™ 3.0 systems (AtheroPoint™, Roseville, CA) with a depth of four layers each. Five of the models use cross-entropy (CE)-loss, and the other five models use Dice similarity coefficient (DSC)-loss functions derived from UNet, UNet+, SegNet, SegNet-UNet, and SegNet-UNet+. The K10 protocol (Train:Test:90%:10%) was applied for all 10 models for training and predicting (segmenting) the plaque region, which was then quantified to compute the plaque area in mm². Further, the data augmentation effect was analyzed. The database consisted of 970 ICA B-mode US scans taken from 99 moderate to high-risk patients. Using the difference area threshold of 10 mm² between ground truth (GT) and artificial intelligence (AI), the area under the curve (AUC) values were 0.91, 0.911, 0.908, 0.905, and 0.898, all with a p-value of <0.001 (for CE-loss models) and 0.883, 0.889, 0.905, 0.889, and 0.907, all with a p-value of <0.001 (for DSC-loss models). The correlations between the AI-based plaque area and GT plaque area were 0.98, 0.96, 0.97, 0.98, and 0.97, all with a p-value of <0.001 (for CE-loss models) and 0.98, 0.98, 0.97, 0.98, and 0.98 (for DSC-loss models). Overall, the online system performs plaque segmentation in less than 1 s. We validate our hypothesis that HDL and SDL models demonstrate comparable performance. SegNet-UNet was the best-performing hybrid architecture.

Multimodality carotid plaque tissue characterization and classification in the artificial intelligence paradigm: a narrative review for stroke application

Cardiovascular disease (CVD) is one of the leading causes of morbidity and mortality in the United States of America and globally. Carotid arterial plaque, a cause and also a marker of such CVD, can be detected by various non-invasive imaging modalities such as magnetic resonance imaging (MRI), computer tomography (CT), and ultrasound (US). Characterization and classification of carotid plaque-type in these imaging modalities, especially into symptomatic and asymptomatic plaque, helps in the planning of carotid endarterectomy or stenting. It can be challenging to characterize plaque components due to (I) partial volume effect in magnetic resonance imaging (MRI) or (II) varying Hausdorff values in plaque regions in CT, and (III) attenuation of echoes reflected by the plaque during US causing acoustic shadowing. Artificial intelligence (AI) methods have become an indispensable part of healthcare and their applications to the non-invasive imaging technologies such as MRI, CT, and the US. In this narrative review, three main types of AI models (machine learning, deep learning, and transfer learning) are analyzed when applied to MRI, CT, and the US. A link between carotid plaque characteristics and the risk of coronary artery disease is presented. With regard to characterization, we review tools and techniques that use AI models to distinguish carotid plaque types based on signal processing and feature strengths. We conclude that AI-based solutions offer an accurate and robust path for tissue characterization and classification for carotid artery plaque imaging in all three imaging modalities. Due to cost, user-friendliness, and clinical effectiveness, AI in the US has dominated the most.

Role of artificial intelligence in cardiovascular risk prediction and outcomes: comparison of machine-learning and conventional statistical approaches for the analysis of carotid ultrasound features and intra-plaque neovascularization

The aim of this study was to compare machine learning (ML) methods with conventional statistical methods to investigate the predictive ability of carotid plaque characteristics for assessing the risk of coronary artery disease (CAD) and cardiovascular (CV) events. Focused carotid B-mode ultrasound, contrast-enhanced ultrasound, and coronary angiography were performed on 459 participants. These participants were followed for 30 days. Plaque characteristics such as carotid intima-media thickness (cIMT), maximum plaque height (MPH), total plaque area (TPA), and intraplaque neovascularization (IPN) were measured at baseline. Two ML-based algorithms-random forest (RF) and random survival forest (RSF) were used for CAD and CV event prediction. The performance of these algorithms was compared against (i) univariate and multivariate analysis for CAD prediction using the area-under-the-curve (AUC) and (ii) Cox proportional hazard model for CV event prediction using the concordance index (c-index). There was a significant association between CAD and carotid plaque characteristics [cIMT (odds ratio (OR) = 1.49, p = 0.03), MPH (OR = 2.44, p < 0.0001), TPA (OR = 1.61, p < 0.0001), and IPN (OR = 2.78, p < 0.0001)]. IPN alone reported significant CV event prediction (hazard ratio = 1.24, p < 0.0001). CAD prediction using the RF algorithm reported an improvement in AUC by ~ 3% over the univariate analysis with IPN alone (0.97 vs. 0.94, p < 0.0001). Cardiovascular event prediction using RSF demonstrated an improvement in the c-index by ~ 17.8% over the Cox-based model (0.86 vs. 0.73). Carotid imaging phenotypes and IPN were associated with CAD and CV events. The ML-based system is superior to the conventional statistically-derived approaches for CAD prediction and survival analysis.

Wilson disease tissue classification and characterization using seven artificial intelligence models embedded with 3D optimization paradigm on a weak training brain magnetic resonance imaging datasets: a supercomputer application

Wilson's disease (WD) is caused by copper accumulation in the brain and liver, and if not treated early, can lead to severe disability and death. WD has shown white matter hyperintensity (WMH) in the brain magnetic resonance scans (MRI) scans, but the diagnosis is challenging due to (i) subtle intensity changes and (ii) weak training MRI when using artificial intelligence (AI). Design and validate seven types of high-performing AI-based computer-aided design (CADx) systems consisting of 3D optimized classification, and characterization of WD against controls. We propose a "conventional deep convolution neural network" (cDCNN) and an "improved DCNN" (iDCNN) where rectified linear unit (ReLU) activation function was modified ensuring "differentiable at zero." Three-dimensional optimization was achieved by recording accuracy while changing the CNN layers and augmentation by several folds. WD was characterized using (i) CNN-based feature map strength and (ii) Bispectrum strengths of pixels having higher probabilities of WD. We further computed the (a) area under the curve (AUC), (b) diagnostic odds ratio (DOR), (c) reliability, and (d) stability and (e) benchmarking. Optimal results were achieved using 9 layers of CNN, with 4-fold augmentation. iDCNN yields superior performance compared to cDCNN with accuracy and AUC of 98.28 ± 1.55, 0.99 (p < 0.0001), and 97.19 ± 2.53%, 0.984 (p < 0.0001), respectively. DOR of iDCNN outperformed cDCNN fourfold. iDCNN also outperformed (a) transfer learning-based "Inception V3" paradigm by 11.92% and (b) four types of "conventional machine learning-based systems": k-NN, decision tree, support vector machine, and random forest by 55.13%, 28.36%, 15.35%, and 14.11%, respectively. The AI-based systems can potentially be useful in the early WD diagnosis. Graphical Abstract.

A Novel Block Imaging Technique Using Nine Artificial Intelligence Models for COVID-19 Disease Classification, Characterization and Severity Measurement in Lung Computed Tomography Scans on an Italian Cohort

Computer Tomography (CT) is currently being adapted for visualization of COVID-19 lung damage. Manual classification and characterization of COVID-19 may be biased depending on the expert's opinion. Artificial Intelligence has recently penetrated COVID-19, especially deep learning paradigms. There are nine kinds of classification systems in this study, namely one deep learning-based CNN, five kinds of transfer learning (TL) systems namely VGG16, DenseNet121, DenseNet169, DenseNet201 and MobileNet, three kinds of machine-learning (ML) systems, namely artificial neural network (ANN), decision tree (DT), and random forest (RF) that have been designed for classification of COVID-19 segmented CT lung against Controls. Three kinds of characterization systems were developed namely (a) Block imaging for COVID-19 severity index (CSI); (b) Bispectrum analysis; and (c) Block Entropy. A cohort of Italian patients with 30 controls (990 slices) and 30 COVID-19 patients (705 slices) was used to test the performance of three types of classifiers. Using K10 protocol (90% training and 10% testing), the best accuracy and AUC was for DCNN and RF pairs were 99.41 ± 5.12%, 0.991 (p < 0.0001), and 99.41 ± 0.62%, 0.988 (p < 0.0001), respectively, followed by other ML and TL classifiers. We show that diagnostics odds ratio (DOR) was higher for DL compared to ML, and both, Bispecturm and Block Entropy shows higher values for COVID-19 patients. CSI shows an association with Ground Glass Opacities (0.9146, p < 0.0001). Our hypothesis holds true that deep learning shows superior performance compared to machine learning models. Block imaging is a powerful novel approach for pinpointing COVID-19 severity and is clinically validated.

Artificial intelligence framework for predictive cardiovascular and stroke risk assessment models: A narrative review of integrated approaches using carotid ultrasound

RECENT FINDINGS

Cardiovascular disease (CVD) is the leading cause of mortality and poses challenges for healthcare providers globally. Risk-based approaches for the management of CVD are becoming popular for recommending treatment plans for asymptomatic individuals. Several conventional predictive CVD risk models based do not provide an accurate CVD risk assessment for patients with different baseline risk profiles. Artificial intelligence (AI) algorithms have changed the landscape of CVD risk assessment and demonstrated a better performance when compared against conventional models, mainly due to its ability to handle the input nonlinear variations. Further, it has the flexibility to add risk factors derived from medical imaging modalities that image the morphology of the plaque. The integration of noninvasive carotid ultrasound image-based phenotypes with conventional risk factors in the AI framework has further provided stronger power for CVD risk prediction, so-called "integrated predictive CVD risk models."

PURPOSE

of the review: The objective of this review is (i) to understand several aspects in the development of predictive CVD risk models, (ii) to explore current conventional predictive risk models and their successes and challenges, and (iii) to refine the search for predictive CVD risk models using noninvasive carotid ultrasound as an exemplar in the artificial intelligence-based framework.

CONCLUSION

Conventional predictive CVD risk models are suboptimal and could be improved. This review examines the potential to include more noninvasive image-based phenotypes in the CVD risk assessment using powerful AI-based strategies.

Contrast-Enhanced Ultrasound Quantification: From Kinetic Modeling to Machine Learning

Ultrasound contrast agents (UCAs) have opened up immense diagnostic possibilities by combined use of indicator dilution principles and dynamic contrast-enhanced ultrasound (DCE-US) imaging. UCAs are microbubbles encapsulated in a biocompatible shell. With a rheology comparable to that of red blood cells, UCAs provide an intravascular indicator for functional imaging of the (micro)vasculature by quantitative DCE-US. Several models of the UCA intravascular kinetics have been proposed to provide functional quantitative maps, aiding diagnosis of different pathological conditions. This article is a comprehensive review of the available methods for quantitative DCE-US imaging based on temporal, spatial and spatiotemporal analysis of the UCA kinetics. The recent introduction of novel UCAs that are targeted to specific vascular receptors has advanced DCE-US to a molecular imaging modality. In parallel, new kinetic models of increased complexity have been developed. The extraction of multiple quantitative maps, reflecting complementary variables of the underlying physiological processes, requires an integrative approach to their interpretation. A probabilistic framework based on emerging machine-learning methods represents nowadays the ultimate approach, improving the diagnostic accuracy of DCE-US imaging by optimal combination of the extracted complementary information. The current value and future perspective of all these advances are critically discussed.

Quantification of Morphological Features in Non-Contrast-Enhanced Ultrasound Microvasculature Imaging

There are significant differences in microvascular morphological features in diseased tissues, such as cancerous lesions, compared to noncancerous tissue. Quantification of microvessel morphological features could play an important role in disease diagnosis and tumor classification. However, analyzing microvessel morphology in ultrasound Doppler is a challenging task due to limitations associated with this technique. Our main objective is to provide methods for quantifying morphological features of microvasculature obtained by ultrasound Doppler imaging. To achieve this goal, we propose multiple image enhancement techniques and appropriate morphological feature extraction methods that enable quantitative analysis of microvasculature structures. Vessel segments obtained by the skeletonization of the regularized microvasculature images are further analyzed to satisfy other constraints, such as vessel segment diameter and length. Measurements of some morphological metrics, such as tortuosity, depend on preserving large vessel trunks. To address this issue, additional filtering methods are proposed. These methods are tested on in vivo images of breast lesion and thyroid nodule microvasculature, and the outcomes are discussed. Initial results show that using vessel morphological features allows for differentiation between malignant and benign breast lesions (p-value < 0.005) and thyroid nodules (p-value < 0.01). This paper provides a tool for the quantification of microvasculature images obtained by non-contrast ultrasound imaging, which may serve as potential biomarkers for the diagnosis of some diseases.

Automatic skin lesion area determination of basal cell carcinoma using optical coherence tomography angiography and a skeletonization approach: Preliminary results

Cutaneous blood flow plays a key role in numerous physiological and pathological processes and has significant potential to be used as a biomarker to diagnose skin diseases such as basal cell carcinoma (BCC). The determination of the lesion area and vascular parameters within it, such as vessel density, is essential for diagnosis, surgical treatment and follow-up procedures. Here, an automatic skin lesion area determination algorithm based on optical coherence tomography angiography (OCTA) images is presented for the first time. The blood vessels are segmented within the OCTA images and then skeletonized. Subsequently, the skeleton is searched over the volume and numerous quantitative vascular parameters are calculated. The vascular density is then used to segment the lesion area. The algorithm is tested on both nodular and superficial BCC, and comparing with dermatological and histological results, the proposed method provides an accurate, non-invasive, quantitative and automatic tool for BCC lesion area determination.

Diagnostic value of 3D power Doppler ultrasound in the characterization of thyroid nodules

Background/aim

This study aimed to evaluate the diagnostic value of vascular indices obtained using 3D power Doppler ultrasound (3D PDUS) in differentiation of benign and malignant thyroid nodules.

Materials and methods

Sixty-seven patients (56 female, 11 male, mean age 44.6) with 81 thyroid nodules exhibiting mixed (peripheral and central) vascularization patterns, with the largest diameter between 10 and 30 mm, were prospectively evaluated using 3D PDUS. Nodule volume, vascularization index (VI), flow index (FI), and vascularization flow index (VFI) were calculated using the Virtual Organ Computer-aided Analysis (VOCAL) software, and these indices were then compared with regard to the cytohistopathology-based diagnosis. The optimum cutoff values for the differentiation of benign and malignant nodules were identified, and diagnostic efficacy was calculated using receiver operating characteristic (ROC) analysis.

Results

Fifty-six of the 81 nodules included in this study were diagnosed as benign and 25 as malignant. Vascular indices in malignant nodules were significantly higher than those in benign nodules (P < 0.05). In benign nodules, the mean VI was 11.61 ± 6.88, mean FI was 39.75 ± 3.93, and mean VFI was 4.82 ± 2.94, compared to 18.64 ± 12.81, 41.82 ± 4.43, and 8.17 ± 6.37, respectively, in malignant nodules. The area under the curves (AUCs) was calculated as 0.68, 0.61, and 0.67 for VI, FI, and VFI, respectively. At optimal cutoff values of 10.2 for VI, 40.8 for FI, and 5.5 for VFI, the sensitivity and specificity were 72%/55.4%, 68%/57.1%, and 68%/67.9%, respectively.

Conclusion

3D PDUS can be useful in the characterization of thyroid nodules.

Value of Contrast-Enhanced Ultrasound and Acoustic Radiation Force Impulse Imaging for the Differential Diagnosis of Benign and Malignant Thyroid Nodules

Objectives: To assess the value of contrast-enhanced ultrasound (CEUS) and acoustic radiation force impulse (ARFI) imaging for the differential diagnosis of benign and malignant thyroid nodules.

Methods: CEUS was performed in eighty-eight thyroid nodules. The patterns of CEUS were analyzed, and ARFI was then performed. The shear wave velocities (SWVs) of the nodules and the surrounding normal thyroid tissue were obtained. The areas under the curve (AUCs) and cut-off value were obtained by a receiver operating characteristic (ROC) curve analysis. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and diagnostic rate of each modality were assessed and compared using pathological diagnosis.

Results: Among 88 nodules, 29 nodules were malignant and 59 were benign. The sensitivity, specificity, PPV, NPV, and diagnostic rate of CEUS were 79.3, 91.5, 82.1, 90, and 87.5%, respectively. Using a cut-off value of 2.565 m/s for SWV, the sensitivity, specificity, PPV, NPV and diagnostic rate for malignancy were 75.9, 94.9, 88.0, 88.9, and 88.6%, respectively. The AUC was 0.878. The sensitivity, specificity, PPV, NPV and diagnostic rate of CEUS in combination with ARFI were 93.1, 89.8, 81.8, 96.3, and 90.9%, respectively.

Conclusion: Both CEUS and ARFI are valuable for the differential diagnosis of benign and malignant thyroid nodules. Combining these two methods can improve the diagnostic rate.

Monitoring of tumor vascular normalization: the key points from basic research to clinical application

Tumor vascular normalization alleviates hypoxia in the tumor microenvironment, reduces the degree of malignancy, and increases the efficacy of traditional therapy. However, the time window for vascular normalization is narrow; therefore, how to determine the initial and final points of the time window accurately is a key factor in combination therapy. At present, the gold standard for detecting the normalization of tumor blood vessels is histological staining, including tumor perfusion, microvessel density (MVD), vascular morphology, and permeability. However, this detection method is almost unrepeatable in the same individual and does not dynamically monitor the trend of the time window; therefore, finding a relatively simple and specific monitoring index has important clinical significance. Imaging has long been used to assess changes in tumor blood vessels and tumor changes caused by the oxygen environment in clinical practice; some preclinical and clinical research studies demonstrate the feasibility to assess vascular changes, and some new methods were in preclinical research. In this review, we update the most recent insights of evaluating tumor vascular normalization.

Application of contrast-enhanced ultrasound for evaluation of thyroid nodules

Contrast-enhanced ultrasound (CEUS) is widely used to evaluate tumor microcirculation, which is useful in the differential diagnosis between benignity and malignancy. In the last 10 years, the applicability of CEUS to thyroid nodules has greatly improved due to technological refinements and the development of second-generation contrast agents. In this review, we summarize the applications of CEUS for thyroid nodules, focusing on the imaging findings of malignant and benign nodules in the existing literature and the use of those findings to predict malignancies, with an additional brief description of the utilization of CEUS for other thyroid-related diseases.

Quantitative analysis of thyroid tumors vascularity: A comparison between 3-D contrast-enhanced ultrasound and 3-D Power Doppler on benign and malignant thyroid nodules

PURPOSE

To perform a comparative quantitative analysis of Power Doppler ultrasound (PDUS) and Contrast-Enhancement ultrasound (CEUS) for the quantification of thyroid nodules vascularity patterns, with the goal of identifying biomarkers correlated with the malignancy of the nodule with both imaging techniques.

METHODS

We propose a novel method to reconstruct the vascular architecture from 3-D PDUS and CEUS images of thyroid nodules, and to automatically extract seven quantitative features related to the morphology and distribution of vascular network. Features include three tortuosity metrics, the number of vascular trees and branches, the vascular volume density, and the main spatial vascularity pattern. Feature extraction was performed on 20 thyroid lesions (ten benign and ten malignant), of which we acquired both PDUS and CEUS. MANOVA (multivariate analysis of variance) was used to differentiate benign and malignant lesions based on the most significant features.

RESULTS

The analysis of the extracted features showed a significant difference between the benign and malignant nodules for both PDUS and CEUS techniques for all the features. Furthermore, by using a linear classifier on the significant features identified by the MANOVA, benign nodules could be entirely separated from the malignant ones.

CONCLUSIONS

Our early results confirm the correlation between the morphology and distribution of blood vessels and the malignancy of the lesion, and also show (at least for the dataset used in this study) a considerable similarity in terms of findings of PDUS and CEUS imaging for thyroid nodules diagnosis and classification.

Celiac Artery Compression Syndrome Evaluated with 3-D Contrast-Enhanced Ultrasonography: a New Approach

This study was performed to estimate the value of 3-D contrast-enhanced ultrasonography (3-D-CEUS) in the diagnosis of celiac artery compression syndrome (CACS). Patients suspected of having CACS were assessed with 3-D-CEUS and contrasted with computed tomography angiography. Diagnostic accuracy was evaluated with a receiver operating characteristic curve. Three-dimensional CEUS revealed 19 positive and 9 negative cases. In the negative group, the contrast agent did not change with respiration. In the positive group, the contrast agent exhibited a hook-shaped stenosis on expiration and returned to normal on inspiration. Computed tomography angiography indicated 1 false-positive case and 1 false-negative case. The sensitivity and specificity of 3-D-CEUS were 95% and 89%, respectively. The area under the receiver operating characteristic curve was 0.982 (p <0.01). In conclusion, 3-D-CEUS can accurately reveal the characteristic hooked appearance and dynamic nature of CACS with respiration, and thus, it represents a new, non-invasive approach to CACS diagnosis.

An Algorithm of Image Heterogeneity with Contrast-Enhanced Ultrasound in Differential Diagnosis of Solid Thyroid Nodules

Enhancement heterogeneity on contrast-enhanced ultrasonography (CEUS) is used to differentiate between benign and malignant thyroid nodules. In this study, we used an algorithm to quantify enhancement heterogeneity of solid thyroid nodules on CEUS. The heterogeneity value (HV) is calculated as standard deviation/mean intensity × 100 (using Adobe Photoshop). The heterogeneity ratio (HR) is calculated as the ratio of the HV of the nodule to that of the surrounding parenchyma. Three phases-ascending, peak and descending phases-were studied. HV values at ascending (HV_a) and peak (HV_p) phases were significantly higher in malignant nodules than in benign nodules (95.57 ± 43.87 vs. 73.06 ± 44.04, p = 0.009, and 32.53 ± 10.73 vs. 26.44 ± 8.25, p = 0.002, respectively). HR_a, HR_p and HR_d were significantly higher in malignant nodules than in benign nodules (1.93 ± 1.03 vs. 1.00 ± 0.47, p = 0.000, 1.43 ± 0.51 vs. 1.09 ± 0.28, p = 0.000, and 1.33 ± 0.40 vs. 1.08 ± 0.33, p = 0.001, respectively). HR_a achieved optimal diagnostic performance on receiver operating characteristic curve analysis. The algorithm used for assessment of image heterogeneity on CEUS examination may be a useful adjunct to conventional ultrasound for differential diagnosis of solid thyroid nodules.

Inter-observer Variability Analysis of Automatic Lung Delineation in Normal and Disease Patients

Human interaction has become almost mandatory for an automated medical system wishing to be accepted by clinical regulatory agencies such as Food and Drug Administration. Since this interaction causes variability in the gathered data, the inter-observer and intra-observer variability must be analyzed in order to validate the accuracy of the system. This study focuses on the variability from different observers that interact with an automated lung delineation system that relies on human interaction in the form of delineation of the lung borders. The database consists of High Resolution Computed Tomography (HRCT): 15 normal and 81 diseased patients' images taken retrospectively at five levels per patient. Three observers manually delineated the lungs borders independently and using software called ImgTracer™ (AtheroPoint™, Roseville, CA, USA) to delineate the lung boundaries in all five levels of 3-D lung volume. The three observers consisted of Observer-1: lesser experienced novice tracer who is a resident in radiology under the guidance of radiologist, whereas Observer-2 and Observer-3 are lung image scientists trained by lung radiologist and biomedical imaging scientist and experts. The inter-observer variability can be shown by comparing each observer's tracings to the automated delineation and also by comparing each manual tracing of the observers with one another. The normality of the tracings was tested using D'Agostino-Pearson test and all observers tracings showed a normal P-value higher than 0.05. The analysis of variance (ANOVA) test between three observers and automated showed a P-value higher than 0.89 and 0.81 for the right lung (RL) and left lung (LL), respectively. The performance of the automated system was evaluated using Dice Similarity Coefficient (DSC), Jaccard Index (JI) and Hausdorff (HD) Distance measures. Although, Observer-1 has lesser experience compared to Obsever-2 and Obsever-3, the Observer Deterioration Factor (ODF) shows that Observer-1 has less than 10% difference compared to the other two, which is under acceptable range as per our analysis. To compare between observers, this study used regression plots, Bland-Altman plots, two tailed T-test, Mann-Whiney, Chi-Squared tests which showed the following P-values for RL and LL: (i) Observer-1 and Observer-3 were: 0.55, 0.48, 0.29 for RL and 0.55, 0.59, 0.29 for LL; (ii) Observer-1 and Observer-2 were: 0.57, 0.50, 0.29 for RL and 0.54, 0.59, 0.29 for LL; (iii) Observer-2 and Observer-3 were: 0.98, 0.99, 0.29 for RL and 0.99, 0.99, 0.29 for LL. Further, CC and R-squared coefficients were computed between observers which came out to be 0.9 for RL and LL. All three observers however manage to show the feature that diseased lungs are smaller than normal lungs in terms of area.

Diagnostic value of contrast-enhanced ultrasound in papillary thyroid microcarcinoma

The aim of the present study was to explore the value and characteristics of contrast-enhanced ultrasound (CEUS) in the diagnosis of papillary thyroid microcarcinoma (PTMC). By analyzing CEUS information of 130 nodules obtained from 106 patients with PTMC, who had been diagnosed by surgery and pathological analysis, CEUS characteristics of PTMC nodules were concluded. Based on the results, the PTMC nodules were divided into three groups as follows: 32 nodules (24.62%) were found to be enhanced earlier than the surrounding normal thyroid tissue, 95 nodules (73.08%) were enhanced at the same time as the normal thyroid tissue and 3 nodules (2.30%) were enhanced later than the normal thyroid tissue. The results also demonstrated that the peak enhancement intensity of the 130 nodules was lower compared with the irregular intensity of the normal parenchyma in corresponding thyroids, and that PTMC enhancement washed out faster than in normal thyroid parenchyma. In conclusion, the PTMC characteristics that CEUS can detect may improve the diagnostic accuracy and provide valuable information for the treatment of the disease.

Ultrasound imaging of breast tumor perfusion and neovascular morphology

A novel image processing strategy is detailed for simultaneous measurement of tumor perfusion and neovascular morphology parameters from a sequence of dynamic contrast-enhanced ultrasound (DCE-US) images. After normalization and tumor segmentation, a global time-intensity curve describing contrast agent flow was analyzed to derive surrogate measures of tumor perfusion (i.e., peak intensity, time-to-peak intensity, area under the curve, wash-in rate, wash-out rate). A maximum intensity image was generated from these same segmented image sequences, and each vascular component was skeletonized via a thinning algorithm. This skeletonized data set and collection of vessel segments were then investigated to extract parameters related to the neovascular network and physical architecture (i.e., vessel-to-tissue ratio, number of bifurcations, vessel count, average vessel length and tortuosity). An efficient computation of local perfusion parameters was also introduced and operated by averaging time-intensity curve data over each individual neovascular segment. Each skeletonized neovascular segment was then color-coded by these local measures to produce a parametric map detailing spatial properties of tumor perfusion. Longitudinal DCE-US image data sets were collected in six patients diagnosed with invasive breast cancer using a Philips iU22 ultrasound system equipped with a L9-3 transducer and Definity contrast agent. Patients were imaged using US before and after contrast agent dosing at baseline and again at weeks 6, 12, 18 and 24 after treatment started. Preliminary clinical results suggested that breast tumor response to neoadjuvant chemotherapy may be associated with temporal and spatial changes in DCE-US-derived parametric measures of tumor perfusion. Moreover, changes in neovascular morphology parametric measures may also help identify any breast tumor response (or lack thereof) to systemic treatment. Breast cancer management from early detection to therapeutic monitoring is currently undergoing profound changes. Novel imaging techniques that are sensitive to the unique biological conditions of each individual tumor represent valuable tools in the pursuit of personalized medicine.

Quantification of Microvascular Tortuosity during Tumor Evolution Using Acoustic Angiography

The recent design of ultra-broadband, multifrequency ultrasound transducers has enabled high-sensitivity, high-resolution contrast imaging, with very efficient suppression of tissue background using a technique called acoustic angiography. Here we perform the first application of acoustic angiography to evolving tumors in mice predisposed to develop mammary carcinoma, with the intent of visualizing and quantifying angiogenesis progression associated with tumor growth. Metrics compared include vascular density and two measures of vessel tortuosity quantified from segmentations of vessels traversing and surrounding 24 tumors and abdominal vessels from control mice. Quantitative morphologic analysis of tumor vessels revealed significantly increased vascular tortuosity abnormalities associated with tumor growth, with the distance metric elevated approximately 14% and the sum of angles metric increased 60% in tumor vessels versus controls. Future applications of this imaging approach may provide clinicians with a new tool in tumor detection, differentiation or evaluation, though with limited depth of penetration using the current configuration.

Contrast-enhanced ultrasound in diagnosis of gallbladder adenoma

BACKGROUND

Gallbladder adenoma is a pre-cancerous neoplasm and needs surgical resection. It is difficult to differentiate adenoma from other gallbladder polyps using imaging examinations. The study aimed to illustrate characteristics of contrast-enhanced ultrasound (CEUS) and its diagnostic value in gallbladder adenoma.

METHODS

Thirty-seven patients with 39 gallbladder adenomatoid lesions (maximal diameter ≥10 mm and without metastasis) were enrolled in this study. Lesion appearances in conventional ultrasound and CEUS were documented. The imaging features were compared individually among gallbladder cholesterol polyp, gallbladder adenoma and malignant lesion.

RESULTS

Adenoma lesions showed iso-echogenicity in ultrasound, and an eccentric enhancement pattern, "fast-in and synchronous-out" contrast enhancement pattern and homogeneous at peak-time enhancement in CEUS. The homogenicity at peak-time enhancement showed the highest diagnostic ability in differentiating gallbladder adenoma from cholesterol polyps. The sensitivity, specificity, positive predictive value, negative predictive value, accuracy and Youden index were 100%, 90.9%, 92.9%, 100%, 95.8% and 0.91, respectively. The characteristic of continuous gallbladder wall shown by CEUS had the highest diagnostic ability in differentiating adenoma from malignant lesion (100%, 86.7%, 86.7%, 100%, 92.9% and 0.87, respectively). The characteristic of the eccentric enhancement pattern had the highest diagnostic ability in differentiating adenoma from cholesterol polyp and malignant lesion, with corresponding indices of 69.2%, 88.5%, 75.0%, 85.2%, 82.1% and 0.58, respectively.

CONCLUSIONS

CEUS is valuable in differentiating gallbladder adenoma from other gallbladder polyps (≥10 mm in diameter). Homogeneous echogenicity on peak-time enhancement, a continuous gallbladder wall, and the eccentric enhancement pattern are important indicators of gallbladder adenoma on CEUS.

GyneScan: an improved online paradigm for screening of ovarian cancer via tissue characterization

Ovarian cancer is the fifth highest cause of cancer in women and the leading cause of death from gynecological cancers. Accurate diagnosis of ovarian cancer from acquired images is dependent on the expertise and experience of ultrasonographers or physicians, and is therefore, associated with inter observer variabilities. Computer Aided Diagnostic (CAD) techniques use a number of different data mining techniques to automatically predict the presence or absence of cancer, and therefore, are more reliable and accurate. A review of published literature in the field of CAD based ovarian cancer detection indicates that many studies use ultrasound images as the base for analysis. The key objective of this work is to propose an effective adjunct CAD technique called GyneScan for ovarian tumor detection in ultrasound images. In our proposed data mining framework, we extract several texture features based on first order statistics, Gray Level Co-occurrence Matrix and run length matrix. The significant features selected using t-test are then used to train and test several supervised learning based classifiers such as Probabilistic Neural Networks (PNN), Support Vector Machine (SVM), Decision Tree (DT), k-Nearest Neighbor (KNN), and Naive Bayes (NB). We evaluated the developed framework using 1300 benign and 1300 malignant images. Using 11 significant features in KNN/PNN classifiers, we were able to achieve 100% classification accuracy, sensitivity, specificity, and positive predictive value in detecting ovarian tumor. Even though more validation using larger databases would better establish the robustness of our technique, the preliminary results are promising. This technique could be used as a reliable adjunct method to existing imaging modalities to provide a more confident second opinion on the presence/absence of ovarian tumor.

A Review on Ultrasound-Based Thyroid Cancer Tissue Characterization and Automated Classification

In this paper, we review the different studies that developed Computer Aided Diagnostic (CAD) for automated classification of thyroid cancer into benign and malignant types. Specifically, we discuss the different types of features that are used to study and analyze the differences between benign and malignant thyroid nodules. These features can be broadly categorized into (a) the sonographic features from the ultrasound images, and (b) the non-clinical features extracted from the ultrasound images using statistical and data mining techniques. We also present a brief description of the commonly used classifiers in ultrasound based CAD systems. We then review the studies that used features based on the ultrasound images for thyroid nodule classification and highlight the limitations of such studies. We also discuss and review the techniques used in studies that used the non-clinical features for thyroid nodule classification and report the classification accuracies obtained in these studies.

Correlation between maximum intensity and microvessel density for differentiation of malignant from benign thyroid nodules on contrast-enhanced sonography

OBJECTIVES

The purpose of this study was to retrospectively evaluate contrast-enhanced sonography for differentiation of benign and malignant thyroid nodules by analyzing the correlation between maximum intensity and microvessel density.

METHODS

From February 2010 to May 2012, 122 patients (85 female and 37 male; mean age ± SD, 45 ± 9.1 years) with thyroid nodules (62 papillary thyroid carcinomas, 30 nodular goiters, and 30 adenomas) that underwent routine thyroid sonography and were diagnosed by surgery were included in this study. Contrast-enhanced sonography was performed, and enhancement patterns were classified into 3 groups: high, equal, and low enhancement. As a time-intensity curve parameter, the correlation of maximum intensity with CD31 and CD34 microvessel density counts was analyzed.

RESULTS

On contrast-enhanced sonography, most patients with papillary thyroid carcinomas showed a heterogeneous low enhancement pattern, whereas most patients with nodular goiters showed an equal enhancement pattern, and patients with adenomas showed a high enhancement pattern. The detection of papillary thyroid carcinomas with low enhancement had sensitivity of 96.8%, specificity of 95.0%, and accuracy of 95.9%. Compared with the papillary thyroid group, the mean microvessel density counts were significantly higher in the nodular goiter and adenoma groups (P< .05). We also found that the maximum intensity was significantly associated with CD31 and CD34 counts (CD31, r = 0.963; P < .01; CD34, r = 0.968; P < .01).

CONCLUSIONS

Maximum intensity has a significant relationship with microvessel density. Contrast-enhanced sonography is a practical and convenient means for differentiating benign from malignant thyroid nodules.

Ultrasonographic thyroid findings suspicious for malignancy

Asymptomatic incidental thyroid nodules (thyroid incidentalomas) are found in up to a third of the adult population. There is notable overlap in the sonographic appearance of benign and malignant thyroid nodules. This paper provides a brief review of the ultrasound findings of thyroid nodules that are suspicious for malignancy with pathologic correlates. We then discuss the standard approach to a fine needle aspiration biopsy of a thyroid nodule at our institution. Finally, we review specific diagnostic challenges in image guided fine needle aspiration biopsies.

Diagnosis of solid breast tumors using vessel analysis in three-dimensional power Doppler ultrasound images

This study aims to evaluate whether the distribution of vessels inside and adjacent to tumor region at three-dimensional (3-D) power Doppler ultrasonography (US) can be used for the differentiation of benign and malignant breast tumors. 3-D power Doppler US images of 113 solid breast masses (60 benign and 53 malignant) were used in this study. Blood vessels within and adjacent to tumor were estimated individually in 3-D power Doppler US images for differential diagnosis. Six features including volume of vessels, vascularity index, volume of tumor, vascularity index in tumor, vascularity index in normal tissue, and vascularity index in surrounding region of tumor within 2 cm were evaluated. Neural network was then used to classify tumors by using these vascular features. The receiver operating characteristic (ROC) curve analysis and Student's t test were used to estimate the performance. All the six proposed vascular features are statistically significant (p < 0.001) for classifying the breast tumors as benign or malignant. The A Z (area under ROC curve) values for the classification result were 0.9138. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis performance based on all six proposed features were 82.30 (93/113), 86.79 (46/53), 78.33 (47/60), 77.97 (46/59), and 87.04 % (47/54), respectively. The p value of A Z values between the proposed method and conventional vascularity index method using z test was 0.04.

Quantitative assessment of cancer vascular architecture by skeletonization of high-resolution 3-D contrast-enhanced ultrasound images: role of liposomes and microbubbles

The accurate characterization and description of the vascular network of a cancer lesion is of paramount importance in clinical practice and cancer research in order to improve diagnostic accuracy or to assess the effectiveness of a treatment. The aim of this study was to show the effectiveness of liposomes as an ultrasound contrast agent to describe the 3-D vascular architecture of a tumor. Eight C57BL/6 mice grafted with syngeneic B16-F10 murine melanoma cells were injected with a bolus of 1,2-Distearoyl-sn-glycero-3-phosphocoline (DSPC)-based non-targeted liposomes and with a bolus of microbubbles. 3-D contrast-enhanced images of the tumor lesions were acquired in three conditions: pre-contrast, after the injection of microbubbles, and after the injection of liposomes. By using a previously developed reconstruction and characterization image processing technique, we obtained the 3-D representation of the vascular architecture in these three conditions. Six descriptive parameters of these networks were also computed: the number of vascular trees (NT), the vascular density (VD), the number of branches, the 2-D curvature measure, the number of vascular flexes of the vessels, and the 3-D curvature. Results showed that all the vascular descriptors obtained by liposome-based images were statistically equal to those obtained by using microbubbles, except the VD which was found to be lower for liposome images. All the six descriptors computed in pre-contrast conditions had values that were statistically lower than those computed in presence of contrast, both for liposomes and microbubbles. Liposomes have already been used in cancer therapy for the selective ultrasound-mediated delivery of drugs. This work demonstrated their effectiveness also as vascular diagnostic contrast agents, therefore proving that liposomes can be used as efficient “theranostic” (i.e. therapeutic + diagnostic) ultrasound probes.

Is there a real diagnostic impact of elastosonography and contrast-enhanced ultrasonography in the management of thyroid nodules?

Ultrasonography (US) and the new applications US elastography (USE) and contrast-enhanced US (CEUS) are used in the screening of thyroid nodules, for which fine-needle aspiration biopsy (FNAB) is the best single diagnostic test. The aim of the study was to compare the sensitivity, specificity, positive predictive value (PPV), and accuracy of the four examinations in nodules with cytological and histological diagnoses. The study used data from US, FNAB, USE (elasticity (ELX 2/1) index), and CEUS (Peak index and time to peak (TTP) index) evaluated in 73 thyroid nodules in 63 consecutive patients likely to undergo surgery. Cytological-histological correlation was available for 38 nodules. No correlation emerged between nodule size and cytological results. A significant (P=0.03) positive correlation between cumulative US findings and cytological results was found. In addition, significant correlations between cumulative US findings and cytology (P=0.02) and between cumulative US findings and histology (P<0.0001) were found. US showed the best specificity and PPV, and FNAB the best sensitivity. There was no significant difference in the ELX 2/1 index, Peak index, or TTP index among nodules subdivided according to cytological scores. No significant correlation was found between ELX 2/1 index, Peak index, and TTP index, on the one hand, and nodule size, US cumulative findings, cytology, and histology on the other hand. The sensitivity of the ELX 2/1 index was high, but its specificity was very low. The accuracy and PPV of USE were lower than those of the other procedures. Only the correlation between Peak index and cumulative US findings reached a value close to significance. Our ultimate aim is to minimise unnecessary thyroidectomy. US and FNAB continue to play a central diagnostic role. The use of a US score showed high specificity and PPV. The specificity of FNAB was low in this selected series because of the numbers of indeterminate cytological responses. USE and CEUS are innovative techniques that need to be standardized. The ELX 2/1 index, Peak index, and TTP index seem to be unrelated to histology. The best statistical data on USE and CEUS concerned their sensitivity and PPV, respectively. At present, USE and CEUS are too time-consuming and of limited utility in selecting patients for surgery.

Classification of thyroid nodules using a resonance-frequency-based electrical impedance spectroscopy: a preliminary assessment

BACKGROUND

Ultrasound and ultrasound-guided fine-needle aspiration biopsy are considered the most effective approaches for both identifying and classifying thyroid nodules. However, despite continuing improvements in scanner technology and refinements in ultrasound/cytological classification guidelines, indeterminate findings still lead to diagnostic lobectomy under general anesthesia. This study aims to investigate the feasibility of applying a modified noninvasive electrical impedance spectroscopy (EIS) approach to classifying thyroid nodules.

METHOD

To increase nodule classification sensitivity, we developed a new EIS-based model that introduces an optimized inductance component, which increases the measured signal-to-noise ratio of capacitance variation in and about thyroid nodules. Our model then measures the change of resonance frequency when the positive reactance of the system inductor cancels out the negative reactance of the nodule capacitance in a multi-frequency electrical signal scan. The system is termed "resonance-frequency-based electrical impedance spectroscopy" (REIS). A portable REIS system with multiple probes was assembled and preliminarily tested in our clinical facility. From an ongoing prospective study, an initial data set of 160 REIS examinations including 27 verified cancer cases was used. From the data set, a number of EIS signal features was extracted and analyzed. A multi-feature-based Bayesian Belief Network was built to classify the detected thyroid nodules. A receiver operating characteristic data analysis method was applied to evaluate classification performance.

RESULTS

The results showed that (i) the median resonance frequency measured by the probe nearest to malignant nodules was in general lower than that measured in benign cases, and (ii) the median descending slope of EIS signal sweep curves computed from cancer cases was larger than that computed from benign cases. The Bayesian Belief Network yielded a classification performance as measured by the area under the receiver operating characteristic curve of 0.794 [with a 95% confidence interval of 0.709-0.863].

CONCLUSIONS

The study demonstrates that noninvasive measurement of REIS signal features may potentially provide useful supplementary information to assist in classifying between malignant and benign thyroid nodules. Such an approach may ultimately lead to a reduction in the number of unnecessary thyroid surgeries.

Effect of complex wavelet transform filter on thyroid tumor classification in three-dimensional ultrasound

Ultrasonography has great potential in differentiating malignant thyroid nodules from the benign ones. However, visual interpretation is limited by interobserver variability, and further, the speckle distribution poses a challenge during the classification process. This article thus presents an automated system for tumor classification in three-dimensional contrast-enhanced ultrasonography data sets. The system first processes the contrast-enhanced ultrasonography images using complex wavelet transform-based filter to mitigate the effect of speckle noise. The higher order spectra features are then extracted and used as input for training and testing a fuzzy classifier. In the off-line training system, higher order spectra features are extracted from a set of images known as the training images. These higher order spectra features along with the clinically assigned ground truth are used to train the classifier and obtain an estimate of the classifier or training parameters. The ground truth tells the class label of the image (i.e. whether the image belongs to a benign or malignant nodule). During the online testing phase, the estimated classifier parameters are applied on the higher order spectra features that are extracted from the testing images to predict their class labels. The predicted class labels are compared with their corresponding original ground truth to evaluate the performance of the classifier. Without utilizing the complex wavelet transform filter, the fuzzy classifier demonstrated an accuracy of 91.6%, while utilizing the complex wavelet transform filter, the accuracy significantly boosted to 99.1%.

Current status and prospects for microbubbles in ultrasound theranostics

Encapsulated microbubbles have been developed over the past two decades to provide improvements both in imaging as well as new therapeutic applications. Microbubble contrast agents are used currently for clinical imaging where increased sensitivity to blood flow is required, such as echocardiography. These compressible spheres oscillate in an acoustic field, producing nonlinear responses which can be uniquely distinguished from surrounding tissue, resulting in substantial enhancements in imaging signal-to-noise ratio. Furthermore, with sufficient acoustic energy the oscillation of microbubbles can mediate localized biological effects in tissue including the enhancement of membrane permeability or increased thermal energy deposition. Structurally, microbubbles are comprised of two principal components--an encapsulating shell and an inner gas core. This configuration enables microbubbles to be loaded with drugs or genes for additional therapeutic effect. Application of sufficient ultrasound energy can release this payload, resulting in site-specific delivery. Extensive preclinical studies illustrate that combining microbubbles and ultrasound can result in enhanced drug delivery or gene expression at spatially selective sites. Thus, microbbubles can be used for imaging, for therapy, or for both simultaneously. In this sense, microbubbles combined with acoustics may be one of the most universal theranostic tools.

Mapping microvasculature with acoustic angiography yields quantifiable differences between healthy and tumor-bearing tissue volumes in a rodent model

PURPOSE

To determine if the morphologies of microvessels could be extracted from contrast material-enhanced acoustic angiographic ultrasonographic (US) images and used as a quantitative basis for distinguishing healthy from diseased tissue.

MATERIALS AND METHODS

All studies were institutional animal care and use committee approved. Three-dimensional contrast-enhanced acoustic angiographic images were acquired in both healthy (n = 7) and tumor-bearing (n = 10) rats. High-spatial-resolution and high signal-to-noise acquisition was enabled by using a prototype dual-frequency US transducer (transmit at 4 MHz, receive at 30 MHz). A segmentation algorithm was utilized to extract microvessel structure from image data, and the distance metric (DM) and the sum of angles metric (SOAM), designed to distinguish different types of tortuosity, were applied to image data. The vessel populations extracted from tumor-bearing tissue volumes were compared against vessels extracted from tissue volumes in the same anatomic location within healthy control animals by using the two-sided Student t test.

RESULTS

Metrics of microvascular tortuosity were significantly higher in the tumor population. The average DM of the tumor population (1.34 ± 0.40 [standard deviation]) was 23.76% higher than that of the control population (1.08 ± 0.08) (P < .0001), while the average SOAM (22.53 ± 7.82) was 50.73% higher than that of the control population (14.95 ± 4.83) (P < .0001). The DM and SOAM metrics for the control and tumor populations were significantly different when all vessels were pooled between the two animal populations. In addition, each animal in the tumor population had significantly different DM and SOAM metrics relative to the control population (P < .05 for all; P value ranges for DM, 3.89 × 10(-)(7) to 5.63 × 10(-)(3); and those for SOAM, 2.42 × 10(-)(12) to 1.57 × 10(-)(3)).

CONCLUSION

Vascular network quantification by using high-spatial-resolution acoustic angiographic images is feasible. Data suggest that the angiogenic processes associated with tumor development in the models studied result in higher instances of vessel tortuosity near the tumor site.

Quantitative assessment of tumor angiogenesis using real-time motion-compensated contrast-enhanced ultrasound imaging

PURPOSE

To develop and test a real-time motion compensation algorithm for contrast-enhanced ultrasound imaging of tumor angiogenesis on a clinical ultrasound system.

MATERIALS AND METHODS

The Administrative Institutional Panel on Laboratory Animal Care approved all experiments. A new motion correction algorithm measuring the sum of absolute differences in pixel displacements within a designated tracking box was implemented in a clinical ultrasound machine. In vivo angiogenesis measurements (expressed as percent contrast area) with and without motion compensated maximum intensity persistence (MIP) ultrasound imaging were analyzed in human colon cancer xenografts (n = 64) in mice. Differences in MIP ultrasound imaging signal with and without motion compensation were compared and correlated with displacements in x- and y-directions. The algorithm was tested in an additional twelve colon cancer xenograft-bearing mice with (n = 6) and without (n = 6) anti-vascular therapy (ASA-404). In vivo MIP percent contrast area measurements were quantitatively correlated with ex vivo microvessel density (MVD) analysis.

RESULTS

MIP percent contrast area was significantly different (P < 0.001) with and without motion compensation. Differences in percent contrast area correlated significantly (P < 0.001) with x- and y-displacements. MIP percent contrast area measurements were more reproducible with motion compensation (ICC = 0.69) than without (ICC = 0.51) on two consecutive ultrasound scans. Following anti-vascular therapy, motion-compensated MIP percent contrast area significantly (P = 0.03) decreased by 39.4 ± 14.6 % compared to non-treated mice and correlated well with ex vivo MVD analysis (Rho = 0.70; P = 0.05).

CONCLUSION

Real-time motion-compensated MIP ultrasound imaging allows reliable and accurate quantification and monitoring of angiogenesis in tumors exposed to breathing-induced motion artifacts.

Non-invasive automated 3D thyroid lesion classification in ultrasound: a class of ThyroScan™ systems

Ultrasound-based thyroid nodule characterization into benign and malignant types is limited by subjective interpretations. This paper presents a Computer Aided Diagnostic (CAD) technique that would present more objective and accurate classification and further would offer the physician a valuable second opinion. In this paradigm, we first extracted the features that quantify the local changes in the texture characteristics of the ultrasound off-line training images from both benign and malignant nodules. These features include: Fractal Dimension (FD), Local Binary Pattern (LBP), Fourier Spectrum Descriptor (FS), and Laws Texture Energy (LTE). The resulting feature vectors were used to build seven different classifiers: Support Vector Machine (SVM), Decision Tree (DT), Sugeno Fuzzy, Gaussian Mixture Model (GMM), K-Nearest Neighbor (KNN), Radial Basis Probabilistic Neural Network (RBPNN), and Naive Bayes Classifier (NBC). Subsequently, the feature vector-classifier combination that results in the maximum classification accuracy was used to predict the class of a new on-line test thyroid ultrasound image. Two data sets with 3D Contrast-Enhanced Ultrasound (CEUS) and 3D High Resolution Ultrasound (HRUS) images of 20 nodules (10 benign and 10 malignant) were used. Fine needle aspiration biopsy and histology results were used to confirm malignancy. Our results show that a combination of texture features coupled with SVM or Fuzzy classifiers resulted in 100% accuracy for the HRUS dataset, while GMM classifier resulted in 98.1% accuracy for the CEUS dataset. Finally, for each dataset, we have proposed a novel integrated index called Thyroid Malignancy Index (TMI) using the combination of FD, LBP, LTE texture features, to diagnose benign or malignant nodules. This index can help clinicians to make a more objective differentiation of benign/malignant thyroid lesions. We have compared and benchmarked the system with existing methods.

Cost-effective and non-invasive automated benign and malignant thyroid lesion classification in 3D contrast-enhanced ultrasound using combination of wavelets and textures: a class of ThyroScan™ algorithms

Ultrasound has great potential to aid in the differential diagnosis of malignant and benign thyroid lesions, but interpretative pitfalls exist and the accuracy is still poor. To overcome these difficulties, we developed and analyzed a range of knowledge representation techniques, which are a class of ThyroScan™ algorithms from Global Biomedical Technologies Inc., California, USA, for automatic classification of benign and malignant thyroid lesions. The analysis is based on data obtained from twenty nodules (ten benign and ten malignant) taken from 3D contrast-enhanced ultrasound images. Fine needle aspiration biopsy and histology confirmed malignancy. Discrete Wavelet Transform (DWT) and texture algorithms are used to extract relevant features from the thyroid images. The resulting feature vectors are fed to three different classifiers: K-Nearest Neighbor (K-NN), Probabilistic Neural Network (PNN), and Decision Tree (DeTr). The performance of these classifiers is compared using Receiver Operating Characteristic (ROC) curves. Our results show that combination of DWT and texture features coupled with K-NN resulted in good performance measures with the area of under the ROC curve of 0.987, a classification accuracy of 98.9%, a sensitivity of 98%, and a specificity of 99.8%. Finally, we have proposed a novel integrated index called Thyroid Malignancy Index (TMI), which is made up of texture features, to diagnose benign or malignant nodules using just one index. We hope that this TMI will help clinicians in a more objective detection of benign and malignant thyroid lesions.

Automated benign & malignant thyroid lesion characterization and classification in 3D contrast-enhanced ultrasound

In this work, we present a Computer Aided Diagnosis (CAD) based technique for automatic classification of benign and malignant thyroid lesions in 3D contrast-enhanced ultrasound images. The images were obtained from 20 patients. Fine needle aspiration biopsy and histology confirmed malignancy. Discrete Wavelet Transform (DWT) and texture based features were extracted from the thyroid images. The resulting feature vectors were used to train and test three different classifiers: K-Nearest Neighbor (K-NN), Probabilistic Neural Network (PNN), and Decision Tree (DeTr) using ten-fold cross validation technique. Our results show that combination of DWT and texture features in the K-NN classifier resulted in a classification accuracy of 98.9%, a sensitivity of 98%, and a specificity of 99.8%. Thus, the preliminary results of the proposed technique show that it could be adapted as an adjunct tool that can give valuable second opinions to the doctors regarding the nature of the thyroid nodule. The technique is cost-effective, non-invasive, fast, completely automated and gives more objective and reproducible results compared to manual analysis of the ultrasound images. We however intend to establish the clinical applicability of this technique by evaluating it with more data in the future.