Virtual histology: a window to the heart of atherosclerosis

Coronary artery properties in atherosclerosis: A deep learning predictive model

In this work an Artificial Neural Network (ANN) was developed to help in the diagnosis of plaque vulnerability by predicting the Young modulus of the core (E _core ) and the plaque (E _plaque ) of atherosclerotic coronary arteries. A representative in silico database was constructed to train the ANN using Finite Element simulations covering the ranges of mechanical properties present in the bibliography. A statistical analysis to pre-process the data and determine the most influential variables was performed to select the inputs of the ANN. The ANN was based on Multilayer Perceptron architecture and trained using the developed database, resulting in a Mean Squared Error (MSE) in the loss function under 10^-7, enabling accurate predictions on the test dataset for E _core and E _plaque . Finally, the ANN was applied to estimate the mechanical properties of 10,000 realistic plaques, resulting in relative errors lower than 3%.

An Ex Vivo Study of Outward Electrical Impedance Tomography (OEIT) for Intravascular Imaging

OBJECTIVE

Atherosclerosis is a chronic immuno-inflammatory condition emerging in arteries and considered the cause of a myriad of cardiovascular diseases. Atherosclerotic lesion characterization through invasive imaging modalities is essential in disease evaluation and determining intervention strategy. Recently, electrical properties of the lesions have been utilized in assessing its vulnerability mainly owing to its capability to differentiate lipid content existing in the lesion, albeit with limited detection resolution. Electrical impedance tomography is the natural extension of conventional spectrometric measurement by incorporating larger number of interrogating electrodes and advanced algorithm to achieve imaging of target objects and thus provides significantly richer information. It is within this context that we develop Outward Electrical Impedance Tomography (OEIT), aimed at intravascular imaging for atherosclerotic lesion characterization.

METHODS

We utilized flexible electronics to establish the 32-electrode OEIT device with outward facing configuration suitable for imaging of vessels. We conducted comprehensive studies through simulation model and ex vivo setup to demonstrate the functionality of OEIT.

RESULTS

Quantitative characterization for OEIT regarding its proximity sensing and conductivity differentiation was achieved using well-controlled experimental conditions. Imaging capability for OEIT was further verified with phantom setup using porcine aorta to emulate in vivo environment.

CONCLUSION

We have successfully demonstrated a novel tool for intravascular imaging, OEIT, with unique advantages for atherosclerosis detection.

SIGNIFICANCE

This study demonstrates for the first time a novel electrical tomography-based platform for intravascular imaging, and we believe it paves the way for further adaptation of OEIT for intravascular detection in more translational settings and offers great potential as an alternative imaging tool for medical diagnosis.

A Learning-Based Microultrasound System for the Detection of Inflammation of the Gastrointestinal Tract

Inflammation of the gastrointestinal (GI) tract accompanies several diseases, including Crohn's disease. Currently, video capsule endoscopy and deep bowel enteroscopy are the main means for direct visualisation of the bowel surface. However, the use of optical imaging limits visualisation to the luminal surface only, which makes early-stage diagnosis difficult. In this study, we propose a learning enabled microultrasound ( μ US) system that aims to classify inflamed and non-inflamed bowel tissues. μ US images of the caecum, small bowel and colon were obtained from mice treated with agents to induce inflammation. Those images were then used to train three deep learning networks and to provide a ground truth of inflammation status. The classification accuracy was evaluated using 10-fold evaluation and additional B-scan images. Our deep learning approach allowed robust differentiation between healthy tissue and tissue with early signs of inflammation that is not detectable by current endoscopic methods or by human inspection of the μ US images. The methods may be a foundation for future early GI disease diagnosis and enhanced management with computer-aided imaging.

Ultrasound capsule endoscopy: sounding out the future

Video capsule endoscopy (VCE) has been of immense benefit in the diagnosis and management of gastrointestinal (GI) disorders since its introduction in 2001. However, it suffers from a number of well recognized deficiencies. Amongst these is the limited capability of white light imaging, which is restricted to analysis of the mucosal surface. Current capsule endoscopes are dependent on visual manifestation of disease and limited in regards to transmural imaging and detection of deeper pathology. Ultrasound capsule endoscopy (USCE) has the potential to overcome surface only imaging and provide transmural scans of the GI tract. The integration of high frequency microultrasound (µUS) into capsule endoscopy would allow high resolution transmural images and provide a means of both qualitative and quantitative assessment of the bowel wall. Quantitative ultrasound (QUS) can provide data in an objective and measurable manner, potentially reducing lengthy interpretation times by incorporation into an automated diagnostic process. The research described here is focused on the development of USCE and other complementary diagnostic and therapeutic modalities. Presently investigations have entered a preclinical phase with laboratory investigations running concurrently.

Imaging Modalities to Identity Inflammation in an Atherosclerotic Plaque

Atherosclerosis is a chronic, progressive, multifocal arterial wall disease caused by local and systemic inflammation responsible for major cardiovascular complications such as myocardial infarction and stroke. With the recent understanding that vulnerable plaque erosion and rupture, with subsequent thrombosis, rather than luminal stenosis, is the underlying cause of acute ischemic events, there has been a shift of focus to understand the mechanisms that make an atherosclerotic plaque unstable or vulnerable to rupture. The presence of inflammation in the atherosclerotic plaque has been considered as one of the initial events which convert a stable plaque into an unstable and vulnerable plaque. This paper systemically reviews the noninvasive and invasive imaging modalities that are currently available to detect this inflammatory process, at least in the intermediate stages, and discusses the ongoing studies that will help us to better understand and identify it at the molecular level.

Photographic image tissue characterization of the ulcerated diabetic foot during treatment: technical note

Treatment of an ulcerated diabetic foot was documented photographically. We adapted the ultrasonographic tissue characterization (USTC or CATUS) technique to develop a photographic image tissue characterization (p-IMTC or CATIM) method. Five photographs, taken during medical treatment of an ulcerated diabetic foot following digital amputation, were quantified using imaging software designed to determine brightness intensity in grey scale images. The grey scale median (GSM) changed from 127 to 98; 86; 76; and 83 (out of 255) during follow-up. The area of lesion was estimated by number of pixels and reduced from 17.85 cm² to 12.44; 3.68; 2.11; and 0.15 cm². The percentage of total number of pixels showing granulation tissue increased from 11% to 34%; 56%; 62%; and 75%. p-IMTC quantified treatment progress. GSM quantified generalized changes in tissues, while the area of lesion and granulation tissue were documented quantitatively. Lesions, ulcers, wounds or other tissues can be analyzed using p-IMTC, allowing quantification, characterization and control of the progression of a condition or treatment.

The vulnerable coronary plaque: update on imaging technologies

Several studies have been carried out on vulnerable plaque as the main culprit for ischaemic cardiac events. Historically, the most important diagnostic technique for studying coronary atherosclerotic disease was to determine the residual luminal diameter by angiographic measurement of the stenosis. However, it has become clear that vulnerable plaque rupture as well as thrombosis, rather than stenosis, triggers most acute ischaemic events and that the quantification of risk based merely on severity of the arterial stenosis is not sufficient. In the last decades, substantial progresses have been made on optimisation of techniques detecting the arterial wall morphology, plaque composition and inflammation. To date, the use of a single technique is not recommended to precisely identify the progression of the atherosclerotic process in human beings. In contrast, the integration of data that can be derived from multiple methods might improve our knowledge about plaque destabilisation. The aim of this narrative review is to update evidence on the accuracy of the currently available non-invasive and invasive imaging techniques in identifying components and morphologic characteristics associated with coronary plaque vulnerability.

Biological imaging of atherosclerosis: moving beyond anatomy

Biological or molecular imaging is now providing exciting new strategies to study atherosclerosis in both animals and humans. These technologies hold the promise to provide disease-specific, molecular information within the context of a systemic or organ-specific disease beyond traditional anatomical-based imaging. By integration of biological, chemical, and anatomical imaging knowledge into diagnostic strategies, a more comprehensive and predictive picture of atherosclerosis is likely to emerge. As such, biological imaging is well positioned to study different stages of atherosclerosis and its treatment, including the sequence of atheroma initiation, progression, and plaque rupture. In this review, we describe the evolving concepts in atherosclerosis imaging with a focus on coronary artery disease, and we provide an overview of recent exciting translational developments in biological imaging. The illuminated examples and discussions will highlight how biological imaging is providing new clinical approaches to identify high-risk plaques, and to streamline the development process of new atherosclerosis therapies.

Ultrasound tissue characterization of the normal kidney

AIM

Ultrasound tissue characterization (USTC) is a precursor of ultrasound virtual histology (USVH), already applied to B-mode images of coronary, carotid, and peripheral arteries, as well as venous thrombosis. Elevated echogenicity has been described for a rejected transplanted kidney. We analyzed data from healthy young adults as reference for further renal USTC.

METHODS

Ultrasound kidney images of 10 volunteers were analyzed. Pixel brightness in the 0-to-255 range was rescaled to zero for black and 200 for fascia brightness before automatic classification into 14 ranges, including "blood-like" (0-4), "fat-like" (8-26), "hypoechoic muscle-like" (41-60), "hyperechoic muscle-like" (61-76), 4 ranges of "fiber-like" (112-196), "calcium-like" (211-255) and intermediary intervals. Nomenclature was readapted using nonechoic, hypoechoic I to IV, echoic I to IV, hyperechoic I to IV, and saturated echoes to avoid inference to actual kidney tissue. Descriptive and comparative statistics were based on percentages of pixels in specific brightness ranges.

SAMPLE POPULATION

Eight women and 2 men, 26 ± 4 years (range, 22-34 years) old, were studied. Kidney length was 10.5 ± 0.9 cm (9.0-12.0 cm). Doppler US resistivity index was 0.67 ± 0.03 (0.62-0.71).

RESULTS

Original fascia brightness converted to 200 value had a mean ± SD of 206 ± 16 (range, 181-236). Kidney grayscale median averaged 37 ± 6 (27-48). Most pixels were hypoechoic II to IV (8-60), averaging 78% ± 6% (66%-87%). Percentages for fat-like, intermediary fat/muscle-like, and hypoechoic muscle-like intervals averaged 25%, 28%, and 25%, respectively.

CONCLUSIONS

A reference database for USTC/USVH of normal young kidneys was created for future comparisons with transplanted and abnormal kidneys. Normal renal echoes have low brightness. Hyperechoic pixels may represent abnormalities.

Ultrasound common carotid artery segmentation based on active shape model

Carotid atherosclerosis is a major reason of stroke, a leading cause of death and disability. In this paper, a segmentation method based on Active Shape Model (ASM) is developed and evaluated to outline common carotid artery (CCA) for carotid atherosclerosis computer-aided evaluation and diagnosis. The proposed method is used to segment both media-adventitia-boundary (MAB) and lumen-intima-boundary (LIB) on transverse views slices from three-dimensional ultrasound (3D US) images. The data set consists of sixty-eight, 17 × 2 × 2, 3D US volume data acquired from the left and right carotid arteries of seventeen patients (eight treated with 80 mg atorvastatin and nine with placebo), who had carotid stenosis of 60% or more, at baseline and after three months of treatment. Manually outlined boundaries by expert are adopted as the ground truth for evaluation. For the MAB and LIB segmentations, respectively, the algorithm yielded Dice Similarity Coefficient (DSC) of 94.4% ± 3.2% and 92.8% ± 3.3%, mean absolute distances (MAD) of 0.26 ± 0.18 mm and 0.33 ± 0.21 mm, and maximum absolute distances (MAXD) of 0.75 ± 0.46 mm and 0.84 ± 0.39 mm. It took 4.3 ± 0.5 mins to segment single 3D US images, while it took 11.7 ± 1.2 mins for manual segmentation. The method would promote the translation of carotid 3D US to clinical care for the monitoring of the atherosclerotic disease progression and regression.