Automated Framework for Detecting Lumen and Media-Adventitia Borders in Intravascular Ultrasound Images

Distraction-aware hierarchical learning for vascular structure segmentation in intravascular ultrasound images

Vascular structure segmentation in intravascular ultrasound (IVUS) images plays an important role in pre-procedural evaluation of percutaneous coronary intervention (PCI). However, vascular structure segmentation in IVUS images has the challenge of structure-dependent distractions. Structure-dependent distractions are categorized into two cases, structural intrinsic distractions and inter-structural distractions. Traditional machine learning methods often rely solely on low-level features, overlooking high-level features. This way limits the generalization of these methods. The existing semantic segmentation methods integrate low-level and high-level features to enhance generalization performance. But these methods also introduce additional interference, which is harmful to solving structural intrinsic distractions. Distraction cue methods attempt to address structural intrinsic distractions by removing interference from the features through a unique decoder. However, they tend to overlook the problem of inter-structural distractions. In this paper, we propose distraction-aware hierarchical learning (DHL) for vascular structure segmentation in IVUS images. Inspired by distraction cue methods for removing interference in a decoder, the DHL is designed as a hierarchical decoder that gradually removes structure-dependent distractions. The DHL includes global perception process, distraction perception process and structural perception process. The global perception process and distraction perception process remove structural intrinsic distractions then the structural perception process removes inter-structural distractions. In the global perception process, the DHL searches for the coarse structural region of the vascular structures on the slice of IVUS sequence. In the distraction perception process, the DHL progressively refines the coarse structural region of the vascular structures to remove structural distractions. In the structural perception process, the DHL detects regions of inter-structural distractions in fused structure features then separates them. Extensive experiments on 361 subjects show that the DHL is effective (e.g., the average Dice is greater than 0.95), and superior to ten state-of-the-art IVUS vascular structure segmentation methods.

A State-Of-The-Art Review on Coronary Artery Border Segmentation Algorithms for Intravascular Ultrasound (IVUS) Images

Intravascular Ultrasound images (IVUS) is a useful guide for medical practitioners to identify the vascular status of coronary arteries in human beings. IVUS is a unique intracoronary imaging modality that is used as an adjunct to angioplasty to view vessel structures using a catheter with high resolutions. Segmentation of IVUS images has always remained a challenging task due to various impediments, for example, similar tissue components, vessel structures, and artifacts imposed during the acquisition process. Many researchers have applied various techniques to develop standard methods of image interpretation, however, the ultimate goal is still elusive to most researchers. This challenge was presented at the MICCAI- Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop in 2011. This paper presents a major review of recently reported work in the field, with a detailed analysis of various segmentation techniques applied in IVUS, and highlights the directions for future research. The findings recommend a reference database with a larger number of samples acquired at varied transducer frequencies with special consideration towards complex lesions, suitable validation metrics, and ground-truth definition as a standard against which to compare new and current algorithms.

Convolutional networks for the segmentation of intravascular ultrasound images: Evaluation on a multicenter dataset

BACKGROUND AND OBJECTIVE

The delineation of the lumen contour and external elastic lamina (EEL) in intravascular ultrasound (IVUS) images is crucial for the quantitative analysis of coronary atherosclerotic plaques. However, the presence of ultrasonic shadows and anatomical structures (such as bifurcations and calcified plaque) complicates the automatic delineation of the lumen contour and EEL. The purpose of this paper is to evaluate the IVUS segmentation performances of different convolutional networks and the impact factors on a large-scale multiple-center dataset.

METHODS

A total of 6516 cross-sectional images from 175 IVUS pullbacks acquired in different centers by different IVUS imaging catheters were screened from a corelab to evaluate the segmentation methods. The IVUS images included bifurcation, side branch ostia, and various image artifacts to reflect the general image characteristics in routine clinical acquisition. We compared three generic fully convolutional networks (FCNs) and two FCNs specifically designed for the segmentation of IVUS images and explored the factors impacting the segmentation performance, including the training images and the input of consecutive images to the models. The performance of the FCNs was evaluated by using the Dice similarity coefficient (DSC), the Jaccard index (JI), the Hausdorff distance (HD), linear regression and Bland-Altman analysis.

RESULTS

The 4-cascaded RefineNet and DeepLabv3+ outperformed U-net and IVUS-net in the segmentation of the lumen contour and EEL on IVUS images. DeepLabv3+ had the best segmentation performance, with DSCs of 0.927 and 0.944, JIs of 0.911 and 0.933, and HDs of 0.336 mm and 0.367 mm for delineation of the lumen and EEL, respectively. Excellent agreement between DeepLabv3+ and the manual delineation was found in the quantification of the coronary plaque area (r = 0.98).

CONCLUSIONS

The convolutional network architecture is effective in the automatic segmentation of IVUS images. It might contribute to the clinical application of quantitative IVUS analysis in real-world as well as the efficient assessment of coronary atherosclerosis.

On a hybrid lossless compression technique for three-dimensional medical images

In the last two decades, incredible progress in various medical imaging modalities and sensing techniques have been made, leading to the proliferation of three-dimensional (3D) imagery. Byproduct of such great progress is the production of huge volume of medical images and this big data place a burden on automatic image processing methods for diagnostic assistance processes. Moreover, large amount of medical imaging data needs to be transmitted with no loss of information for the purpose of telemedicine, remote diagnosis etc. In this work, we consider a hybrid lossless compression technique with object-based features for three-dimensional (3D) medical images. Our approach utilizes two phases as follows: first we determine the volume of interest (VOI) for a given 3D medical imagery using selective bounding volume (SBV) method, and second the obtained VOI is encoded using a hybrid lossless algorithm using Lembel-Ziv-Welch Coding (LZW) followed by arithmetic coding (L to A). Experimental results show that our proposed 3D medical image compression method is comparable with other existing standard lossless encoding methods such as Huffman Coding, Run Length Coding, LZW, and Arithmetic Coding and obtains superior results overall.

Using optical coherence tomography and intravascular ultrasound imaging to quantify coronary plaque cap thickness and vulnerability: a pilot study

Background

Detecting coronary vulnerable plaques in vivo and assessing their vulnerability have been great challenges for clinicians and the research community. Intravascular ultrasound (IVUS) is commonly used in clinical practice for diagnosis and treatment decisions. However, due to IVUS limited resolution (about 150–200 µm), it is not sufficient to detect vulnerable plaques with a threshold cap thickness of 65 µm. Optical Coherence Tomography (OCT) has a resolution of 15–20 µm and can measure fibrous cap thickness more accurately. The aim of this study was to use OCT as the benchmark to obtain patient-specific coronary plaque cap thickness and evaluate the differences between OCT and IVUS fibrous cap quantifications. A cap index with integer values 0–4 was also introduced as a quantitative measure of plaque vulnerability to study plaque vulnerability.

Methods

Data from 10 patients (mean age: 70.4; m: 6; f: 4) with coronary heart disease who underwent IVUS, OCT, and angiography were collected at Cardiovascular Research Foundation (CRF) using approved protocol with informed consent obtained. 348 slices with lipid core and fibrous caps were selected for study. Convolutional Neural Network (CNN)-based and expert-based data segmentation were performed using established methods previously published. Cap thickness data were extracted to quantify differences between IVUS and OCT measurements.

Results

For the 348 slices analyzed, the mean value difference between OCT and IVUS cap thickness measurements was 1.83% (p = 0.031). However, mean value of point-to-point differences was 35.76%. Comparing minimum cap thickness for each plaque, the mean value of the 20 plaque IVUS-OCT differences was 44.46%, ranging from 2.36% to 91.15%. For cap index values assigned to the 348 slices, the disagreement between OCT and IVUS assignments was 25%. However, for the OCT cap index = 2 and 3 groups, the disagreement rates were 91% and 80%, respectively. Furthermore, the observation of cap index changes from baseline to follow-up indicated that IVUS results differed from OCT by 80%.

Conclusions

These preliminary results demonstrated that there were significant differences between IVUS and OCT plaque cap thickness measurements. Large-scale patient studies are needed to confirm our findings.

Privileged Modality Distillation for Vessel Border Detection in Intracoronary Imaging

Intracoronary imaging is a crucial imaging technology in coronary disease diagnosis as it visualizes the internal tissue morphologies of coronary arteries. Vessel border detection in intracoronary images (VBDI) is desired because it can help the succeeding procedures of computer-aided disease diagnosis. However, existing VDBI methods suffer from the challenge of vessel-environment variability (i.e. high intra- and inter-subject diversity of vessels and their surrounding tissues appeared in images). This challenge leads to the ineffectiveness in the vessel region representation for hand-crafted features, in the receptive field extraction for deeply-represented features, as well as performance suppression derived from clinical data limitation. To solve this challenge, we propose a novel privileged modality distillation (PMD) framework for VBDI. PMD transforms the single-input-single-task (SIST) learning problem in the single-mode VBDI to a multiple-input-multiple-task (MIMT) problem by using the privileged image modality to help the learning model in the target modality. This learns the enriched high-level knowledge with similar semantics and generalizes PMD on diversity-increased low-level image features for improving the model adaptation to diverse vessel environments. Moreover, PMD refines MIMT to SIST by distilling the learned knowledge from multiple to one modality. This eliminates the reliance on privileged modality in the test phase, and thus enables the applicability to each of different intracoronary modalities. A structure-deformable neural network is proposed as an elaborately-designed implementation of PMD. It expands a conventional SIST network structure to the MIMT structure, and then recovers it to the final SIST structure. The PMD is validated on intravascular ultrasound imaging and optical coherence tomography imaging. One modality is the target, and the other one can be considered as the privileged modality owing to their semantic relatedness. The experiments show that our PMD is effective in VBDI (e.g. the Dice index is larger than 0.95), as well as superior to six state-of-the-art VBDI methods.

Detecting vulnerable plaque with vulnerability index based on convolutional neural networks

Plaque rupture and subsequent thrombosis are major processes of acute cardiovascular events. The Vulnerability Index is a very important indicator of whether a plaque is ruptured, and these easily ruptured or fragile plaques can be detected early. The higher the general vulnerability index, the higher the instability of the plaque. Therefore, determining a clear vulnerability index classification point can effectively reduce unnecessary interventional therapy. However, the current critical value of the vulnerability index has not been well defined. In this study, we proposed a neural network-based method to determine the critical point of vulnerability index that distinguishes vulnerable plaques from stable ones. Firstly, based on MatConvNet, the intravascular ultrasound images under different vulnerability index labels are classified. Different vulnerability indexes can obtain different accuracy rates for the demarcation points. The corresponding data points are fitted to find the existing relationship to judge the highest classification. In this way, the vulnerability index corresponding to the highest classification accuracy rate is judged. Then the article is based on the same experiment of different components of the aortic artery in the artificial neural network, and finally the vulnerability index corresponding to the highest classification accuracy can be obtained. The results show that the best vulnerability index point is 1.716 when the experiment is based on the intravascular ultrasound image, and the best vulnerability index point is 1.607 when the experiment is based on the aortic artery component data. Moreover, the vulnerability index and classification accuracy rate has a periodic relationship within a certain range, and finally the highest AUC is 0.7143 based on the obtained vulnerability index point on the verification set. In this paper, the convolution neural network is used to find the best vulnerability index classification points. The experimental results show that this method has the guiding significance for the classification and diagnosis of vulnerable plaques, further reduce interventional treatment of cardiovascular disease.

HG-SVNN: HARMONIC GENETIC-BASED SUPPORT VECTOR NEURAL NETWORK CLASSIFIER FOR THE GLAUCOMA DETECTION

Glaucoma has emerged as the one of the leading causes of blindness. Even though the diagnosis of this disease has not yet been found, the early detection can cure the glaucoma disease. Various works presented for the glaucoma detection have many disadvantages such as increased run time, complex architecture, etc., during the real-time implementations. This work introduces the glaucoma detection system based on the proposed harmonic genetic-based support vector neural network (HG-SVNN) classifier. The proposed system detects glaucoma in the database through four major steps, (1) pre-processing, (2) proposed hybrid feature extraction, (3) segmentation and (4) classification through the proposed HG-SVNN classifier. The proposed model uses both the statistical and the vessel features from the segmented and the pre-processed images to construct the feature vector. The proposed HG-SVNN classifier uses both the harmonic operator and the genetic algorithm (GA) for the neural network training. From the simulation results, it is evident that the proposed glaucoma detection system has better performance than the existing works with the values of 0.945, 0.9, 0.9333 and 0.86667 for the segmentation accuracy, accuracy, sensitivity and specificity metric.

CLASSIFICATION OF PHONOCARDIOGRAM SIGNALS BASED ON ENVELOPE OPTIMIZATION MODEL AND SUPPORT VECTOR MACHINE

The prevention and diagnosis of cardiovascular diseases have become one of the primary problems in the medical community since the mortality of this kind of diseases accounts for 31% of global deaths in 2016. Heart sound, which is an important physiological signal of human body, mainly comes from the pulsing of cardiac structures and blood turbulence. The analysis of heart sounds plays an irreplaceable role in early diagnosis of heart disease since they contain a large amount of pathological information about each part of human heart. Heart sounds can be detected and recorded by Phonocardiogram (PCG). As a noninvasive method to detect and diagnose heart disease, PCG signals have been paid more and more attention by researchers. In this paper, a novel envelope extraction model is proposed and used to estimate the cardiac cycle of each PCG signal. We present a strategy combining empirical mode decomposition (EMD) technique and the proposed envelope model to extract the time-domain features. After applying EMD process to each PCG signal, the second intrinsic mode function is chosen for further analysis. Based on the proposed envelope model, the cardiac cycles of PCG signals can be estimated and then the time-domain features can be extracted. Combining with the frequency-domain features and wavelet-domain features, the feature vectors are obtained. Finally, the support vector machine (SVM) classifier is used to detect the normal and abnormal PCG signals. Two public datasets are used to test our framework in this paper. And classification accuracies of more than [Formula: see text] on both datasets show the effectiveness of the proposed model.

Intelligent Diabetes Detection System based on Tongue Datasets

Background:

Scanning Electron Microscope (SEM) Camera Imaging shows and helps analyze hidden organs in the human body. SEM image analysis provides in-depth and critical details of organ abnormalities. Similarly, the human tongue finds use in the detection of organ dysfunction with tongue reflexology.

Objective:

To detect diabetes at an early stage using a non-invasive method of diabetes detection through tongue images and to utilize the reasonable cost of modality (SEM camera) for capturing the tongue images instead of the existing and expensive imaging modalities like X-ray, Computed Tomography, Magnetic Resonance Imaging, Positron Emission Tomography, Single-Photon Emission Computed Tomography etc.

Methods:

The tongue image is captured via SEM camera, it is preprocessed to remove noise and resize the tongue such that it is suitable for segmentation. Greedy Snake Algorithm (GSA) is used to segment the tongue image. The texture features of the tongue are analyzed and finally it is classified as diabetic or normal.

Results:

Failure of organs stomach, intestine, liver and pancreas results in change of the color of the tongue, coating thickness and cracks on the tongue. Changes in pancreas proactive behavior also reflect on tongue coating. The tongue coating texture varies from white or vanilla to yellow also the tongue coating thickness also increases.

Conclusion:

In this paper, the author proposes to diagnose Diabetes Type2 (DT2) at an early stage from tongue digital image. The tongue image is acquired and processed with Greedy Snake Algorithm (GSA) to extract edge and texture features.

Lumen-intima and media-adventitia segmentation in IVUS images using supervised classifications of arterial layers and morphological structures

BACKGROUND

Intravascular ultrasound (IVUS) provides axial grey-scale images of blood vessels. The large number of images require automatic analysis, specifically to identify the lumen and outer vessel wall. However, the high amount of noise, the presence of artifacts and anatomical structures, such as bifurcations, calcifications and fibrotic plaques, usually hinder the proper automatic segmentation of the vessel wall.

METHODS

Lumen, media, adventitia and surrounding tissues are automatically detected using Support Vector Machines (SVMs). The classification performance of the SVMs vary according to the kind of structure present within each region of the image. Random Forest (RF) is used to detect different morphological structures and to modify the initial layer classification depending on the detected structure. The resulting classification maps are fed into a segmentation method based on deformable contours to detect lumen-intima (LI) and media-adventitia (MA) interfaces.

RESULTS

The modifications in the layer classifications according to the presence of structures proved to be effective improving LI and MA segmentations. The proposed method reaches a Jaccard Measure (JM) of 0.88 ± 0.08 for LI segmentation, compared with 0.88 ± 0.05 of a semiautomatic method. When looking at MA, our method reaches a JM of 0.84 ± 0.09, and outperforms previous automatic methods in terms of HD, with 0.51mm ± 0.30.

CONCLUSIONS

A simple modification to the arterial layer classification produces results that match and improve state-of-the-art fully-automatic segmentation methods for LI and MA in 20MHz IVUS images. For LI segmentation, the proposed automatic method performs accurately as semi-automatic methods. For MA segmentation, our method matched the quality of state-of-the-art automatic methods described in the literature. Furthermore, our implementation is modular and open-source, allowing for future extensions and improvements.

A safe percutaneous technique for the reduction of irreducible femoral neck fractures using ultrasound localization of the femoral vascular and nervous structures at the hip

We present a safe percutaneous technique for the placement of Kirschner wires into the femoral head to assist in the reduction of irreducible femoral neck fractures using ultrasound to identify the vascular and nervous structures about the hip.From January 2011 to June 2014, a total of 36 patients (25 males and 11 females) were enrolled in this study. Patients were placed on a fracture reduction table for limb traction. After 3 unsuccessful reductions with limb traction, ultrasound-guided localization of the patient's femoral artery, vein, and nerve at the hip was performed. These structures were marked on the overlying skin and then Kirschner wires were inserted into the femoral head avoiding these marked structures. After the surgery, the Kirschner wire insertions were routinely reviewed by ultrasound, the hip fracture reduction and the femoral nerve sensorimotor function were routinely examined as well.All 36 patients with an irreducible variant of a femoral neck fracture showed anatomic reduction under C-arm fluoroscopy using ultrasound to avoid K wire injury to the femoral vascular structures and nerve. No major vascular injury during operation. In post-surgical ultrasound examination, local hematoma formation was not evident. There was normal function of the femoral nerve. On follow-up, there were no infections, wound problems, recurrence of fracture displacement, laxity, or implant breakage.Preoperative ultrasonic localization of the femoral artery, vein, and femoral nerve safely allowed. Kirschner wire placement under C-arm fluoroscopy into the femoral head to assist in fracture reduction. This assisted reduction method for irreducible femoral neck fractures had a number of advantages, including closed anatomic reduction with minimal attempts, used simple equipment, and avoided further destruction of the blood supply to the femoral head.

Peripheral vascular disease assessment in the lower limb: a review of current and emerging non-invasive diagnostic methods

BACKGROUND

Worldwide, at least 200 million people are affected by peripheral vascular diseases (PVDs), including peripheral arterial disease (PAD), chronic venous insufficiency (CVI) and deep vein thrombosis (DVT). The high prevalence and serious consequences of PVDs have led to the development of several diagnostic tools and clinical guidelines to assist timely diagnosis and patient management. Given the increasing number of diagnostic methods available, a comprehensive review of available technologies is timely in order to understand their limitations and direct future development effort.

MAIN BODY

This paper reviews the available diagnostic methods for PAD, CVI, and DVT with a focus on non-invasive modalities. Each method is critically evaluated in terms of sensitivity, specificity, accuracy, ease of use, procedure time duration, and training requirements where applicable.

CONCLUSION

This review emphasizes the limitations of existing methods, highlighting a latent need for the development of new non-invasive, efficient diagnostic methods. Some newly emerging technologies are identified, in particular wearable sensors, which demonstrate considerable potential to address the need for simple, cost-effective, accurate and timely diagnosis of PVDs.

Lumen and media-adventitia border detection in IVUS images using texture enhanced deformable model

Lumen and media-adventitia (MA) borders in intravascular ultrasound (IVUS) images are critical for assessing the dimensions of vascular structures and providing plaque information in the diagnosis and navigation of vascular interventions. However, manual delineation of the lumen and MA borders is an intricate and time-consuming process. In this paper, a texture-enhanced deformable model (TEDM) is proposed to accurately detect these borders by incorporating texture information with the morphological factors of deformable model. An ensemble support vector machine classifier is used to classify IVUS pixels presented by texture features into different tissue types. The image regionalization maps of different tissue types are further used for texture enhancement modules in the TEDM. The proposed TEDM method has been tested on 1500 images from 15 clinical IVUS datasets by comparing with the manual delineations. Evaluation results demonstrate that our method can accurately detect lumen and MA surfaces with small surface distance errors of 0.17 and 0.19 mm, respectively. Accurate segmentation results provide 2D measurements of MA/lumen areas and 3D vessel visualizations for vascular interventions.

Contour segmentation of the intima, media, and adventitia layers in intracoronary OCT images: application to fully automatic detection of healthy wall regions

PURPOSE

Quantitative and automatic analysis of intracoronary optical coherence tomography images is useful and time-saving to assess cardiovascular risk in the clinical arena.

METHODS

First, the interfaces of the intima, media, and adventitia layers are segmented, by means of an original front propagation scheme, running in a 4D multi-parametric space, to simultaneously extract three non-crossing contours in the initial cross-sectional image. Second, information resulting from the tentative contours is exploited by a machine learning approach to identify healthy and diseased regions of the arterial wall. The framework is fully automatic.

RESULTS

The method was applied to 40 patients from two different medical centers. The framework was trained on 140 images and validated on 260 other images. For the contour segmentation method, the average segmentation errors were [Formula: see text] for the intima-media interface, [Formula: see text] for the media-adventitia interface, and [Formula: see text] for the adventitia-periadventitia interface. The classification method demonstrated a good accuracy, with a median Dice coefficient equal to 0.93 and an interquartile range of (0.78-0.98).

CONCLUSION

The proposed framework demonstrated promising offline performances and could potentially be translated into a reliable tool for various clinical applications, such as quantification of tissue layer thickness and global summarization of healthy regions in entire pullbacks.

Automatic segmentation of the lumen region in intravascular images of the coronary artery

Image assessment of the arterial system plays an important role in the diagnosis of cardiovascular diseases. The segmentation of the lumen and media-adventitia in intravascular (IVUS) images of the coronary artery is the first step towards the evaluation of the morphology of the vessel under analysis and the identification of possible atherosclerotic lesions. In this study, a fully automatic method for the segmentation of the lumen in IVUS images of the coronary artery is presented. The proposed method relies on the K-means algorithm and the mean roundness to identify the region corresponding to the potential lumen. An approach to identify and eliminate side branches on bifurcations is also proposed to delimit the area with the potential lumen regions. Additionally, an active contour model is applied to refine the contour of the lumen region. In order to evaluate the segmentation accuracy, the results of the proposed method were compared against manual delineations made by two experts in 326 IVUS images of the coronary artery. The average values of the Jaccard measure, Hausdorff distance, percentage of area difference and Dice coefficient were 0.88 ± 0.06, 0.29 ± 0.17  mm, 0.09 ± 0.07 and 0.94 ± 0.04, respectively, in 324 IVUS images successfully segmented. Additionally, a comparison with the studies found in the literature showed that the proposed method is slight better than the majority of the related methods that have been proposed. Hence, the new automatic segmentation method is shown to be effective in detecting the lumen in IVUS images without using complex solutions and user interaction.