Fully automatic luminal contour segmentation in intracoronary ultrasound imaging--a statistical approach

Deep Learning-Based Medical Ultrasound Image and Video Segmentation Methods: Overview, Frontiers, and Challenges

The intricate imaging structures, artifacts, and noise present in ultrasound images and videos pose significant challenges for accurate segmentation. Deep learning has recently emerged as a prominent field, playing a crucial role in medical image processing. This paper reviews ultrasound image and video segmentation methods based on deep learning techniques, summarizing the latest developments in this field, such as diffusion and segment anything models as well as classical methods. These methods are classified into four main categories based on the characteristics of the segmentation methods. Each category is outlined and evaluated in the corresponding section. We provide a comprehensive overview of deep learning-based ultrasound image segmentation methods, evaluation metrics, and common ultrasound datasets, hoping to explain the advantages and disadvantages of each method, summarize its achievements, and discuss challenges and future trends.

Automatic Detection of Atherosclerotic Plaque and Calcification From Intravascular Ultrasound Images by Using Deep Convolutional Neural Networks

Atherosclerosis is the major cause of cardiovascular diseases (CVDs). Intravascular ultrasound (IVUS) is a common imaging modality for diagnosing CVDs. However, an efficient analyzer for IVUS image segmentation is required for assisting cardiologists. In this study, an end-to-end deep-learning convolutional neural network was developed for automatically detecting media-adventitia borders, luminal regions, and calcified plaque in IVUS images. A total of 713 grayscale IVUS images from 18 patients were used as training data for the proposed deep-learning model. The model is constructed using the three modified U-Nets and combined with the concept of cascaded networks to prevent errors in the detection of calcification owing to the interference of pixels outside the plaque regions. Three loss functions (Dice, Tversky, and focal loss) with various characteristics were tested to determine the best setting for the proposed model. The efficacy of the deep-learning model was evaluated by analyzing precision-recall curve. The average precision (AP), Dice score coefficient, precision, sensitivity, and specificity of the predicted and ground truth results were then compared. All training processes were validated using leave-one-subject-out cross-validation. The experimental results showed that the proposed deep-learning model exhibits high performance in segmenting the media-adventitia layers and luminal regions for all loss functions, with all tested metrics being higher than 0.90. For locating calcified tissues, the best result was obtained when the focal loss function was applied to the proposed model, with an AP of 0.73; however, the prediction efficacy was affected by the proportion of calcified tissues within the plaque region when the focal loss function was employed. Compared with commercial software, the proposed method exhibited high accuracy in segmenting IVUS images in some special cases, such as when shadow artifacts or side vessels surrounded the target vessel.

Automatic Lumen Border Detection in IVUS Images Using Deep Learning Model and Handcrafted Features

In the clinical analysis of Intravascular ultrasound (IVUS) images, the lumen size is an important indicator of coronary atherosclerosis, and is also the premise of coronary artery disease diagnosis and interventional treatment. In this study, a fully automatic method based on deep learning model and handcrafted features is presented for the detection of the lumen borders in IVUS images. First, 193 handcrafted features are extracted from the IVUS images. Then hybrid feature vectors are constructed by combining handcrafted features with 64 high-level features extracted from U-Net. In order to obtain the feature subsets with larger contribution, we employ the extended binary cuckoo search for feature selection. Finally, the selected 36-dimensional hybrid feature subset is used to classify the test images using dictionary learning based on kernel sparse coding. The proposed algorithm is tested on the publicly available dataset and evaluated using three indicators. Through ablation experiments, mean value of the experimental results (Jaccard: 0.88, Hausdorff distance: 0.36, Percentage of the area difference: 0.06) prove to be effective improving lumen border detection. Furthermore, compared with the recent methods used on the same dataset, the proposed method shows good performance and high accuracy.

Supervised machine learning for coronary artery lumen segmentation in intravascular ultrasound images

Intravascular ultrasound (IVUS) has been widely used to capture cross sectional lumen frames of inner wall of coronary arteries. This kind of medical imaging modalities is capable of providing detailed and significant information of lumen contour shape, which is very important for clinical diagnosis and analysis of cardiovascular diseases. Numerous learning based techniques have recently become very popular for coronary artery segmentation due to their impressive results. In this work, a supervised machine learning method for coronary artery lumen segmentation with high accuracy and minimal user interaction is designed. The fully discriminative lumen segmentation method jointly learning a classifier the weak learners rely on and the features of the classifier is developed. Additionally, the theoretical supports of the Gradient Boosting framework used in this work and its quadratic approximation are presented. The proposed algorithm is tested on the public datasets of boundary detection of lumen in IVUS challenge held in MICCAI 2011 and achieves a higher average Jaccard similarity of 96.8% and a lower mean error distance of 0.55 (in Cartesian coordinates), which shows higher accuracy compared to the existing learning based methods. Moreover, three real patient IVUS datasets are used to evaluate the performance of the proposed coronary artery lumen segmentation algorithm, which is shown to achieve lower percent error of lumen area of 1.861% ± 0.965%, 1.968% ± 0.864%, and 1.671% ± 0.584%, respectively, compared to the manually measured lumen area (ground truth). The proposed lumen segmentation method is found to be superior to the latest learning based segmentation techniques. Given the efficiency and robustness, our method has great potential in IVUS images processing and coronary artery segmentation and quantification. NOVELTY STATEMENT: The main contributions are summarized in the following aspects: A detailed review of related work about learning based coronary artery lumen segmentation in intravascular ultrasound images is presented. A fully discriminative lumen segmentation method jointly learning a classifier our weak learners rely on and the features of the classifier is developed. The theoretical supports of the Gradient Boosting framework and its quadratic approximation used in this work are presented.

Fast and accurate segmentation method of active shape model with Rayleigh mixture model clustering for prostate ultrasound images

BACKGROUND AND OBJECTIVE

The prostate cancer interventions, which need an accurate prostate segmentation, are performed under ultrasound imaging guidance. However, prostate ultrasound segmentation is facing two challenges. The first is the low signal-to-noise ratio and inhomogeneity of the ultrasound image. The second is the non-standardized shape and size of the prostate.

METHODS

For prostate ultrasound image segmentation, this paper proposed an accurate and efficient method of Active shape model (ASM) with Rayleigh mixture model Clustering (ASM-RMMC). Firstly, Rayleigh mixture model (RMM) is adopted for clustering the image regions which present similar speckle distributions. These content-based clustered images are then used to initialize and guide the deformation of an ASM model.

RESULTS

The performance of the proposed method is assessed on 30 prostate ultrasound images using four metrics as Mean Average Distance (MAD), Dice Similarity Coefficient (DSC), False Positive Error (FPE) and False Negative Error (FNE). The proposed ASM-RMMC reaches high segmentation accuracy with 95% ± 0.81% for DSC, 1.86 ± 0.02 pixels for MAD, 2.10% ± 0.36% for FPE and 2.78% ± 0.71% for FNE, respectively. Moreover, the average segmentation time is less than 8 s when treating a single prostate ultrasound image through ASM-RMMC.

CONCLUSIONS

This paper presents a method for prostate ultrasound image segmentation, which achieves high accuracy with less computational complexity and meets the clinical requirements.

Development of an innovative technology to segment luminal borders of intravascular ultrasound image sequences in a fully automated manner

Although intravascular ultrasound (IVUS) is the commonest intravascular imaging modality, it still is inefficient for clinical use as it requires laborious manual analysis. This study demonstrates the feasibility of a near real-time fully automated technology for accurate identification, detection, and quantification of luminal borders in intravascular images. This technology uses a combination of the novel approaches of a self-tuning engine, dynamic and static masking systems, radar-wise scan, and contour correction cycle method. The performance of the computer algorithm developed based on this technology was tested on a sequence of IVUS and True Vessel Characterization (TVC) images obtained from the left anterior descending (LAD) artery of 6 patients with coronary artery disease. The accuracy of the algorithm was evaluated by comparing luminal borders traced manually with those detected automatically. The processing time of the developed algorithm was also tested on a Dell laptop with an Intel Core i7-8750H Processor (4.1 GHz with 6 cores, 9 MB Cache). Linear regression and Bland-Altman analyses indicated high correlation between manual and automatic tracings (Y = 0.80 × X+1.70, R² = 0.88 & 0.67 ± 1.31 (bias±SD)). Whereas analysis of 2000 IVUS images using one CPU core with a 30% load took 23.12 min, the same analysis using six CPU cores with 90% load took 1.0 min. The performance, accuracy, and speed of the presented state-of-the-art technology demonstrates its capacity for use in clinical settings.

Ultrasound Image Segmentation: A Deeply Supervised Network With Attention to Boundaries

OBJECTIVE

Segmentation of anatomical structures in ultrasound images requires vast radiological knowledge and experience. Moreover, the manual segmentation often results in subjective variations, therefore, an automatic segmentation is desirable. We aim to develop a fully convolutional neural network (FCNN) with attentional deep supervision for the automatic and accurate segmentation of the ultrasound images.

METHOD

FCNN/CNNs are used to infer high-level context using low-level image features. In this paper, a sub-problem specific deep supervision of the FCNN is performed. The attention of fine resolution layers is steered to learn object boundary definitions using auxiliary losses, whereas coarse resolution layers are trained to discriminate object regions from the background. Furthermore, a customized scheme for downweighting the auxiliary losses and a trainable fusion layer are introduced. This produces an accurate segmentation and helps in dealing with the broken boundaries, usually found in the ultrasound images.

RESULTS

The proposed network is first tested for blood vessel segmentation in liver images. It results in F1 score, mean intersection over union, and dice index of 0.83, 0.83, and 0.79, respectively. The best values observed among the existing approaches are produced by U-net as 0.74, 0.81, and 0.75, respectively. The proposed network also results in dice index value of 0.91 in the lumen segmentation experiments on MICCAI 2011 IVUS challenge dataset, which is near to the provided reference value of 0.93. Furthermore, the improvements similar to vessel segmentation experiments are also observed in the experiment performed to segment lesions.

CONCLUSION

Deep supervision of the network based on the input-output characteristics of the layers results in improvement in overall segmentation accuracy.

SIGNIFICANCE

Sub-problem specific deep supervision for ultrasound image segmentation is the main contribution of this paper. Currently the network is trained and tested for fixed size inputs. It requires image resizing and limits the performance in small size images.

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

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

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

An automated framework for detecting lumen and media-adventitia borders in intravascular ultrasound images was developed on the basis of an adaptive region-growing method and an unsupervised clustering method. To demonstrate the capability of the framework, linear regression, Bland-Altman analysis and distance analysis were used to quantitatively investigate the correlation, agreement and spatial distance, respectively, between our detected borders and manually traced borders in 337 intravascular ultrasound images in vivo acquired from six patients. The results of these investigations revealed good correlation (r = 0.99), good agreement (>96.82% of results within the 95% confidence interval) and small average distance errors (lumen border: 0.08 mm, media-adventitia border: 0.10 mm) between the borders generated by the automated framework and the manual tracing method. The proposed framework was found to be effective in detecting lumen and media-adventitia borders in intravascular ultrasound images, indicating its potential for use in routine studies of vascular disease.

Computer Vision Techniques for Transcatheter Intervention

Minimally invasive transcatheter technologies have demonstrated substantial promise for the diagnosis and the treatment of cardiovascular diseases. For example, transcatheter aortic valve implantation is an alternative to aortic valve replacement for the treatment of severe aortic stenosis, and transcatheter atrial fibrillation ablation is widely used for the treatment and the cure of atrial fibrillation. In addition, catheter-based intravascular ultrasound and optical coherence tomography imaging of coronary arteries provides important information about the coronary lumen, wall, and plaque characteristics. Qualitative and quantitative analysis of these cross-sectional image data will be beneficial to the evaluation and the treatment of coronary artery diseases such as atherosclerosis. In all the phases (preoperative, intraoperative, and postoperative) during the transcatheter intervention procedure, computer vision techniques (e.g., image segmentation and motion tracking) have been largely applied in the field to accomplish tasks like annulus measurement, valve selection, catheter placement control, and vessel centerline extraction. This provides beneficial guidance for the clinicians in surgical planning, disease diagnosis, and treatment assessment. In this paper, we present a systematical review on these state-of-the-art methods. We aim to give a comprehensive overview for researchers in the area of computer vision on the subject of transcatheter intervention. Research in medical computing is multi-disciplinary due to its nature, and hence, it is important to understand the application domain, clinical background, and imaging modality, so that methods and quantitative measurements derived from analyzing the imaging data are appropriate and meaningful. We thus provide an overview on the background information of the transcatheter intervention procedures, as well as a review of the computer vision techniques and methodologies applied in this area.

Automated detection framework of the calcified plaque with acoustic shadowing in IVUS images

Intravascular Ultrasound (IVUS) is one ultrasonic imaging technology to acquire vascular cross-sectional images for the visualization of the inner vessel structure. This technique has been widely used for the diagnosis and treatment of coronary artery diseases. The detection of the calcified plaque with acoustic shadowing in IVUS images plays a vital role in the quantitative analysis of atheromatous plaques. The conventional method of the calcium detection is manual drawing by the doctors. However, it is very time-consuming, and with high inter-observer and intra-observer variability between different doctors. Therefore, the computer-aided detection of the calcified plaque is highly desired. In this paper, an automated method is proposed to detect the calcified plaque with acoustic shadowing in IVUS images by the Rayleigh mixture model, the Markov random field, the graph searching method and the prior knowledge about the calcified plaque. The performance of our method was evaluated over 996 in-vivo IVUS images acquired from eight patients, and the detected calcified plaques are compared with manually detected calcified plaques by one cardiology doctor. The experimental results are quantitatively analyzed separately by three evaluation methods, the test of the sensitivity and specificity, the linear regression and the Bland-Altman analysis. The first method is used to evaluate the ability to distinguish between IVUS images with and without the calcified plaque, and the latter two methods can respectively measure the correlation and the agreement between our results and manual drawing results for locating the calcified plaque in the IVUS image. High sensitivity (94.68%) and specificity (95.82%), good correlation and agreement (>96.82% results fall within the 95% confidence interval in the Student t-test) demonstrate the effectiveness of the proposed method in the detection of the calcified plaque with acoustic shadowing in IVUS images.

Phase-based probabilistic active contour for nerve detection in ultrasound images for regional anesthesia

Ultrasound guided regional anesthesia (UGRA) is steadily growing in popularity, owing to advances in ultrasound imaging technology and the advantages that this technique presents for safety and efficiency. The aim of this work is to assist anaesthetists during the UGRA procedure by automatically detecting the nerve blocks in the ultrasound images. The main disadvantage of ultrasound images is the poor quality of the images, which are also affected by the speckle noise. Moreover, the nerve structure is not salient amid the other tissues, which makes its detection a challenging problem. In this paper we propose a new method to tackle the problem of nerve zone detection in ultrasound images. The method consists in a combination of three approaches: probabilistic, edge phase information and active contours. The gradient vector flow (GVF) is adopted as an edge-based active contour. The phase analysis of the monogenic signal is used to provide reliable edges for the GVF. Then, a learned probabilistic model reduces the false positives and increases the likelihood energy term of the target region. It yields a new external force field that attracts the active contour toward the desired region of interest. The proposed scheme has been applied to sciatic nerve regions. The qualitative and quantitative evaluations show a high accuracy and a significant improvement in performance.

Despeckle filtering software toolbox for ultrasound imaging of the common carotid artery

Ultrasound imaging of the common carotid artery (CCA) is a non-invasive tool used in medicine to assess the severity of atherosclerosis and monitor its progression through time. It is also used in border detection and texture characterization of the atherosclerotic carotid plaque in the CCA, the identification and measurement of the intima-media thickness (IMT) and the lumen diameter that all are very important in the assessment of cardiovascular disease (CVD). Visual perception, however, is hindered by speckle, a multiplicative noise, that degrades the quality of ultrasound B-mode imaging. Noise reduction is therefore essential for improving the visual observation quality or as a pre-processing step for further automated analysis, such as image segmentation of the IMT and the atherosclerotic carotid plaque in ultrasound images. In order to facilitate this preprocessing step, we have developed in MATLAB(®) a unified toolbox that integrates image despeckle filtering (IDF), texture analysis and image quality evaluation techniques to automate the pre-processing and complement the disease evaluation in ultrasound CCA images. The proposed software, is based on a graphical user interface (GUI) and incorporates image normalization, 10 different despeckle filtering techniques (DsFlsmv, DsFwiener, DsFlsminsc, DsFkuwahara, DsFgf, DsFmedian, DsFhmedian, DsFad, DsFnldif, DsFsrad), image intensity normalization, 65 texture features, 15 quantitative image quality metrics and objective image quality evaluation. The software is publicly available in an executable form, which can be downloaded from http://www.cs.ucy.ac.cy/medinfo/. It was validated on 100 ultrasound images of the CCA, by comparing its results with quantitative visual analysis performed by a medical expert. It was observed that the despeckle filters DsFlsmv, and DsFhmedian improved image quality perception (based on the expert's assessment and the image texture and quality metrics). It is anticipated that the system could help the physician in the assessment of cardiovascular image analysis.

An integrated system for the segmentation of atherosclerotic carotid plaque ultrasound video

The robust border identification of atherosclerotic carotid plaque, the corresponding degree of stenosis of the common carotid artery (CCA), and also the characteristics of the arterial wall, including plaque size, composition, and elasticity, have significant clinical relevance for the assessment of future cardiovascular events. To facilitate the follow-up and analysis of the carotid stenosis in serial clinical investigations, we propose and evaluate an integrated system for the segmentation of atherosclerotic carotid plaque in ultrasound videos of the CCA based on video frame normalization, speckle reduction filtering, M-mode state-based identification, parametric active contours, and snake segmentation. Initially, the cardiac cycle in each video is identified and the video M-mode is generated, thus identifying systolic and diastolic states. The video is then segmented for a time period of at least one full cardiac cycle. The algorithm is initialized in the first video frame of the cardiac cycle, with human assistance if needed, and the moving atherosclerotic plaque borders are tracked and segmented in the subsequent frames. Two different initialization methods are investigated in which initial contours are estimated every 20 video frames. In the first initialization method, the initial snake contour is estimated using morphology operators; in the second initialization method, the Chan-Vese active contour model is used. The performance of the algorithm is evaluated on 43 real CCA digitized videos from B-mode longitudinal ultrasound segments and is compared with the manual segmentations of an expert, available every 20 frames in a time span of 3 to 5 s, covering, in general, 2 cardiac cycles. The segmentation results were very satisfactory, according to the expert objective evaluation, for the two different methods investigated, with true-negative fractions (TNF-specificity) of 83.7 ± 7.6% and 84.3 ± 7.5%; true-positive fractions (TPF-sensitivity) of 85.42 ± 8.1% and 86.1 ± 8.0%; and between the ground truth and the proposed segmentation method, kappa indices (KI) of 84.6% and 85.3% and overlap indices of 74.7% and 75.4%. The segmentation contours were also used to compute the cardiac state identification and radial, longitudinal, and shear strain indices for the CCA wall and plaque between the asymptomatic and symptomatic groups were investigated. The results of this study show that the integrated system investigated in this study can be successfully used for the automated video segmentation of the CCA plaque in ultrasound videos.

Standardized evaluation methodology and reference database for evaluating IVUS image segmentation

This paper describes an evaluation framework that allows a standardized and quantitative comparison of IVUS lumen and media segmentation algorithms. This framework has been introduced at the MICCAI 2011 Computing and Visualization for (Intra)Vascular Imaging (CVII) workshop, comparing the results of eight teams that participated. We describe the available data-base comprising of multi-center, multi-vendor and multi-frequency IVUS datasets, their acquisition, the creation of the reference standard and the evaluation measures. The approaches address segmentation of the lumen, the media, or both borders; semi- or fully-automatic operation; and 2-D vs. 3-D methodology. Three performance measures for quantitative analysis have been proposed. The results of the evaluation indicate that segmentation of the vessel lumen and media is possible with an accuracy that is comparable to manual annotation when semi-automatic methods are used, as well as encouraging results can be obtained also in case of fully-automatic segmentation. The analysis performed in this paper also highlights the challenges in IVUS segmentation that remains to be solved.

Automatic lumen segmentation in IVOCT images using binary morphological reconstruction

Background

Atherosclerosis causes millions of deaths, annually yielding billions in expenses round the world. Intravascular Optical Coherence Tomography (IVOCT) is a medical imaging modality, which displays high resolution images of coronary cross-section. Nonetheless, quantitative information can only be obtained with segmentation; consequently, more adequate diagnostics, therapies and interventions can be provided. Since it is a relatively new modality, many different segmentation methods, available in the literature for other modalities, could be successfully applied to IVOCT images, improving accuracies and uses.

Method

An automatic lumen segmentation approach, based on Wavelet Transform and Mathematical Morphology, is presented. The methodology is divided into three main parts. First, the preprocessing stage attenuates and enhances undesirable and important information, respectively. Second, in the feature extraction block, wavelet is associated with an adapted version of Otsu threshold; hence, tissue information is discriminated and binarized. Finally, binary morphological reconstruction improves the binary information and constructs the binary lumen object.

Results

The evaluation was carried out by segmenting 290 challenging images from human and pig coronaries, and rabbit iliac arteries; the outcomes were compared with the gold standards made by experts. The resultant accuracy was obtained: True Positive (%) = 99.29 ± 2.96, False Positive (%) = 3.69 ± 2.88, False Negative (%) = 0.71 ± 2.96, Max False Positive Distance (mm) = 0.1 ± 0.07, Max False Negative Distance (mm) = 0.06 ± 0.1.

Conclusions

In conclusion, by segmenting a number of IVOCT images with various features, the proposed technique showed to be robust and more accurate than published studies; in addition, the method is completely automatic, providing a new tool for IVOCT segmentation.

Robust myocardial motion tracking for echocardiography: variational framework integrating local-to-global deformation

This paper proposes a robust real-time myocardial border tracking algorithm for echocardiography. Commonly, after an initial contour of LV border is traced at one or two frames from the entire cardiac cycle, LV contour tracking is performed over the remaining frames. Among a variety of tracking techniques, optical flow method is the most widely used for motion estimation of moving objects. However, when echocardiography data is heavily corrupted in some local regions, the errors bring the tracking point out of the endocardial border, resulting in distorted LV contours. This shape distortion often occurs in practice since the data acquisition is affected by ultrasound artifacts, dropouts, or shadowing phenomena of cardiac walls. The proposed method is designed to deal with this shape distortion problem by integrating local optical flow motion and global deformation into a variational framework. The proposed descent method controls the individual tracking points to follow the local motions of a specific speckle pattern, while their overall motions are confined to the global motion constraint being approximately an affine transform of the initial tracking points. Many real experiments show that the proposed method achieves better overall performance than conventional methods.

Improving quantification of intravascular fluorescence imaging using structural information

Intravascular near-infrared fluorescence (iNIRF) imaging can enable the in vivo visualization of biomarkers of vascular pathology, including high-risk plaques. The technique resolves the bio-distribution of systemically administered fluorescent probes with molecular specificity in the vessel wall. However, the geometrical variations that may occur in the distance between fibre-tip and vessel wall can lead to signal intensity variations and challenge quantification. Herein we examined whether the use of anatomical information of the cross-section vessel morphology, obtained from co-registered intravascular ultrasound (IVUS), can lead to quantification improvements when fibre-tip and vessel wall distance variations are present. The algorithm developed employs a photon propagation model derived from phantom experiments that is used to calculate the relative attenuation of fluorescence signals as they are collected over 360° along the vessel wall, and utilizes it to restore accurate fluorescence readings. The findings herein point to quantification improvements when employing hybrid iNIRF, with possible implications to the clinical detection of high-risk plaques or blood vessel theranostics.

Segmentation of skin lesions in 2-D and 3-D ultrasound images using a spatially coherent generalized Rayleigh mixture model

This paper addresses the problem of jointly estimating the statistical distribution and segmenting lesions in multiple-tissue high-frequency skin ultrasound images. The distribution of multiple-tissue images is modeled as a spatially coherent finite mixture of heavy-tailed Rayleigh distributions. Spatial coherence inherent to biological tissues is modeled by enforcing local dependence between the mixture components. An original Bayesian algorithm combined with a Markov chain Monte Carlo method is then proposed to jointly estimate the mixture parameters and a label-vector associating each voxel to a tissue. More precisely, a hybrid Metropolis-within-Gibbs sampler is used to draw samples that are asymptotically distributed according to the posterior distribution of the Bayesian model. The Bayesian estimators of the model parameters are then computed from the generated samples. Simulation results are conducted on synthetic data to illustrate the performance of the proposed estimation strategy. The method is then successfully applied to the segmentation of in vivo skin tumors in high-frequency 2-D and 3-D ultrasound images.

Combination of the Level-Set Methods with the Contourlet Transform for the Segmentation of the IVUS Images

Intravascular ultrasound (IVUS) imaging is a catheter-based medical methodology establishing itself as a useful modality for studying atherosclerosis. The detection of lumen and media-adventitia boundaries in IVUS images constitutes an essential step towards the reliable quantitative diagnosis of atherosclerosis. In this paper, a novel scheme is proposed to automatically detect lumen and media-adventitia borders. This segmentation method is based on the level-set model and the contourlet multiresolution analysis. The contourlet transform decomposes the original image into low-pass components and band-pass directional bands. The circular hough transform (CHT) is adopted in low-pass bands to yield the initial lumen and media-adventitia contours. The anisotropic diffusion filtering is then used in band-pass subbands to suppress noise and preserve arterial edges. Finally, the curve evolution in the level-set functions is used to obtain final contours. The proposed method is experimentally evaluated via 20 simulated images and 30 real images from human coronary arteries. It is demonstrated that the mean distance error and the relative mean distance error have increased by 5.30 pixels and 7.45%, respectively, as compared with those of a recently traditional level-set model. These results reveal that the proposed method can automatically and accurately extract two vascular boundaries.

A state-of-the-art review on segmentation algorithms in intravascular ultrasound (IVUS) images

Over the past two decades, intravascular ultrasound (IVUS) image segmentation has remained a challenge for researchers while the use of this imaging modality is rapidly growing in catheterization procedures and in research studies. IVUS provides cross-sectional grayscale images of the arterial wall and the extent of atherosclerotic plaques with high spatial resolution in real time. In this paper, we review recently developed image processing methods for the detection of media-adventitia and luminal borders in IVUS images acquired with different transducers operating at frequencies ranging from 20 to 45 MHz. We discuss methodological challenges, lack of diversity in reported datasets, and weaknesses of quantification metrics that make IVUS segmentation still an open problem despite all efforts. In conclusion, we call for a common reference database, validation metrics, and ground-truth definition with which new and existing algorithms could be benchmarked.

Semi-automatic vessel tracking and segmentation using epicardial ultrasound in bypass surgery

The purpose of intraoperative quality assessment of coronary artery bypass graft surgery is to confirm graft patency and disclose technical errors to reduce cardiac mortality, morbidity and improve clinical outcome for the patient. Epicardial ultrasound has been suggested as an alternative approach for quality assessment of anastomoses. To make a quantitative assessment of the anastomotic quality using ultrasound images, the vessel border has to be delineated to estimate the area of the vessel lumen. A tracking and segmentation algorithm was developed consisting of an active contour modeling approach and quality control of the segmentations. Evaluation of the tracking algorithm showed 91.96% of the segmentations were segmented correct with a mean error in height and width at 5.65% and 11.50% respectively.

A Parallel Method for Segmenting Intravascular Ultrasound Image Sequence

Intravascular Ultrasound (IVUS) is one of interventional imaging modalities widely used in clinical diagnosis of vascular diseases, especially coronary artery diseases. Segmentation of IVUS images to extract vessel wall boundaries is of importance for quantitative analysis and 3D vessel reconstruction. A 3D parallel method for segmenting IVUS image sequence is proposed in this paper. Firstly, original images are preprocessed to reduce possible noises and eliminate ring-down artifacts. Then, several longitudinal cuts are obtained and intima-lumen and media-adventitia boundaries are detected. Once these boundaries are mapped onto each cross-sectional slice, initial plan of vessel wall boundaries in each frame is obtained. Finally, these initial contours evolve continuously until stop at target contours. Consequently, segmentation of each IVUS tomographic frame is implemented simultaneously and the efficiency is greatly raised compared with 2D sequential approaches.

Automatic coronary wall segmentation in intravascular ultrasound images using binary morphological reconstruction

Intravascular ultrasound (IVUS) image segmentation can provide more detailed vessel and plaque information, resulting in better diagnostics, evaluation and therapy planning. A novel automatic segmentation proposal is described herein; the method relies on a binary morphological object reconstruction to segment the coronary wall in IVUS images. First, a preprocessing followed by a feature extraction block are performed, allowing for the desired information to be extracted. Afterward, binary versions of the desired objects are reconstructed, and their contours are extracted to segment the image. The effectiveness is demonstrated by segmenting 1300 images, in which the outcomes had a strong correlation to their corresponding gold standard. Moreover, the results were also corroborated statistically by having as high as 92.72% and 91.9% of true positive area fraction for the lumen and media adventitia border, respectively. In addition, this approach can be adapted easily and applied to other related modalities, such as intravascular optical coherence tomography and intravascular magnetic resonance imaging.

A regularization technique for closed contour segmentation in ultrasound images

Segmentation of a target object in the form of a closed curve has many potential applications in medical imaging because it provides quantitative information related to the target objext's size and shape. However, ultrasound image segmentation for boundary delineation of the target object is a very difficult task because of its inherent drawbacks, including uncertainty of the segmentation boundary caused by speckle noise, relatively low SNR, and low contrast. Indeed, in automatic ultrasound image segmentation, conventional techniques with standard regularization often fail to reach the desired segmentation in the form of a simple closed curve because of the weakness of edge detector functions in finding the likely target boundary. In this paper, we propose a new regularization model which has the property of encouraging a closed curve by deliberately controlling the curve smoothness. The new model may be combined with various fitting terms to enhance segmentation results. The key features of the proposed model are demonstrated in detail. Numerical simulations and experiments show that the proposed model enhances the segmentation ability for extracting the target boundary as a closed contour.

A snake-based method for segmentation of intravascular ultrasound images and its in vivo validation

Image segmentation for detection of vessel walls is necessary for quantitative assessment of vessel diseases by intravascular ultrasound. A new segmentation method based on gradient vector flow (GVF) snake model is proposed in this paper. The main characteristics of the proposed method include two aspects: one is that nonlinear filtering is performed on GVF field to reduce the critical points, change the morphological structure of the parallel curves and extend the capture range; the other is that balloon snake is combined with the model. Thus, the improved GVF and balloon snake can be automatically initialized and overcome the problem caused by local energy minima. Results of 20 in vivo cases validated the accuracy and stability of the segmentation method for intravascular ultrasound images.

Ultrasound image segmentation and tissue characterization

Ultrasound image segmentation deals with delineating the boundaries of structures, as a step towards semi-automated or fully automated measurement of dimensions or for characterizing tissue regions. Ultrasound tissue characterization (UTC) is driven by knowledge of the physics of ultrasound and its interactions with biological tissue, and has traditionally used signal modelling and analysis to characterize and differentiate between healthy and diseased tissue. Thus, both aim to enhance the capabilities of ultrasound as a quantitative tool in clinical medicine, and the two end goals can be the same, namely to characterize the health of tissue. This article reviews both research topics, and finds that the two fields are becoming more tightly coupled, even though there are key challenges to overcome in each area, influenced by factors such as more open software-based ultrasound system architectures, increased computational power, and advances in imaging transducer design.

Registering preprocedure volumetric images with intraprocedure 3-D ultrasound using an ultrasound imaging model

For many image-guided interventions there exists a need to compute the registration between preprocedure image(s) and the physical space of the intervention. Real-time intraprocedure imaging such as ultrasound (US) can be used to image the region of interest directly and provide valuable anatomical information for computing this registration. Unfortunately, real-time US images often have poor signal-to-noise ratio and suffer from imaging artefacts. Therefore, registration using US images can be challenging and significant preprocessing is often required to make the registrations robust. In this paper we present a novel technique for computing the image-to-physical registration for minimally invasive cardiac interventions using 3-D US. Our technique uses knowledge of the physics of the US imaging process to reduce the amount of preprocessing required on the 3-D US images. To account for the fact that clinical US images normally undergo significant image processing before being exported from the US machine our optimization scheme allows the parameters of the US imaging model to vary. We validated our technique by computing rigid registrations for 12 cardiac US/magnetic resonance imaging (MRI) datasets acquired from six volunteers and two patients. The technique had mean registration errors of 2.1-4.4 mm, and 75% capture ranges of 5-30 mm. We also demonstrate how the same approach can be used for respiratory motion correction: on 15 datasets acquired from five volunteers the registration errors due to respiratory motion were reduced by 45%-92%.

Automatic segmentation of calcifications in intravascular ultrasound images using snakes and the contourlet transform

It is valuable to detect calcifications in intravascular ultrasound images for studies of coronary artery diseases. An image segmentation method based on snakes and the Contourlet transform is proposed to automatically and accurately detect calcifications. With the Contourlet transform, an original image is decomposed into low-pass bands and band-pass directional sub-bands. The 2-D Renyi's entropy is used to adaptively threshold the low-pass bands in a multiresolution hierarchy to determine regions-of-interest (ROIs). Then a mean intensity ratio, reflecting acoustic shadowing, is presented to classify calcifications from noncalcifications and obtain initial contours of calcifications. The anisotropic diffusion is used in bandpass directional sub-bands to suppress noise and preserve calcific edges. Finally, the contour deformation in the boundary vector field is used to obtain final contours of calcifications. The method was evaluated via 60 simulated images and 86 in vivo images. It outperformed a recently proposed method, the Santos Filho method, by 2.76% and 14.53%, in terms of the sensitivity and specificity of calcification detection, respectively. The area under the receiver operating characteristic curve increased by 0.041. The relative mean distance error, relative difference degree, relative arc difference, relative thickness difference and relative length difference were reduced by 5.73%, 19.79%, 11.62%, 12.06% and 20.51%, respectively. These results reveal that the proposed method can automatically and accurately detect calcifications and delineate their boundaries. (E-mail: yywang@fudan.edu.cn).

Noninvasive carotid strain imaging using angular compounding at large beam steered angles: validation in vessel phantoms

Stroke and myocardial infarction are initiated by rupturing vulnerable atherosclerotic plaques. With noninvasive ultrasound elastography, these plaques might be detected in carotid arteries. However, since the ultrasound beam is generally not aligned with the radial direction in which the artery pulsates, radial and circumferential strains need to be derived from axial and lateral data. Conventional techniques to perform this conversion have the disadvantage that lateral strain is required. Since the lateral strain has relatively poor accuracy, the quality of the radial and circumferential strains is reduced. In this study, the radial and circumferential strain estimates are improved by combining axial strain data acquired at multiple insonification angles. Adaptive techniques to correct for grating lobe interference and other artifacts that occur when performing beam steering at large angles are introduced. Acquisitions at multiple angles are performed with a beam steered linear array. For each beam steered angle, there are two spatially restricted regions of the circular vessel cross section where the axial strain is closely aligned with the radial strain and two spatially restricted regions (different from the radial strain regions) where the axial strain is closely aligned with the circumferential strain. These segments with high quality strain estimates are compounded to form radial or circumferential strain images. Compound radial and circumferential strain images were constructed for a homogeneous vessel phantom with a concentric lumen subjected to different intraluminal pressures. Comparison of the elastographic signal-to-noise ratio (SNR(e)) and contrast-to-noise ratio (CNR(e)) revealed that compounding increases the image quality considerably compared to images from 0 degrees information only. SNR(e) and CNR(e) increase up to 2.7 and 6.6 dB, respectively. The highest image quality was achieved by projecting axial data, completed with a small segment determined by either principal component analysis or by application of a rotation matrix.

Segmentation in ultrasonic B-mode images of healthy carotid arteries using mixtures of Nakagami distributions and stochastic optimization

The goal of this work is to perform a segmentation of the intimamedia thickness (IMT) of carotid arteries in view of computing various dynamical properties of that tissue, such as the elasticity distribution (elastogram). The echogenicity of a region of interest comprising the intima-media layers, the lumen, and the adventitia in an ultrasonic B-mode image is modeled by a mixture of three Nakagami distributions. In a first step, we compute the maximum a posteriori estimator of the proposed model, using the expectation maximization (EM) algorithm. We then compute the optimal segmentation based on the estimated distributions as well as a statistical prior for disease-free IMT using a variant of the exploration/selection (ES) algorithm. Convergence of the ES algorithm to the optimal solution is assured asymptotically and is independent of the initial solution. In particular, our method is well suited to a semi-automatic context that requires minimal manual initialization. Tests of the proposed method on 30 sequences of ultrasonic B-mode images of presumably disease-free control subjects are reported. They suggest that the semi-automatic segmentations obtained by the proposed method are within the variability of the manual segmentations of two experts.

Image analysis techniques for automated IVUS contour detection

Intravascular ultrasound (IVUS) constitutes a valuable technique for the diagnosis of coronary atherosclerosis. The detection of lumen and media-adventitia borders in IVUS images represents a necessary step towards the reliable quantitative assessment of atherosclerosis. In this work, a fully automated technique for the detection of lumen and media-adventitia borders in IVUS images is presented. This comprises two different steps for contour initialization: one for each corresponding contour of interest and a procedure for the refinement of the detected contours. Intensity information, as well as the result of texture analysis, generated by means of a multilevel discrete wavelet frames decomposition, are used in two different techniques for contour initialization. For subsequently producing smooth contours, three techniques based on low-pass filtering and radial basis functions are introduced. The different combinations of the proposed methods are experimentally evaluated in large datasets of IVUS images derived from human coronary arteries. It is demonstrated that our proposed segmentation approaches can quickly and reliably perform automated segmentation of IVUS images.

Robust principal component analysis and clustering methods for automated classification of tissue response to ARFI excitation

We introduce a new method for automatic classification of acoustic radiation force impulse (ARFI) displacement profiles using what have been termed "robust" methods for principal component analysis (PCA) and clustering. Unlike classical approaches, the robust methods are less sensitive to high variance outlier profiles and require no a priori information regarding expected tissue response to ARFI excitation. We first validate our methods using synthetic data with additive noise and/or outlier curves. Second, the robust techniques are applied to classifying ARFI displacement profiles acquired in an atherosclerotic familial hypercholesterolemic (FH) pig iliac artery in vivo. The in-vivo classification results are compared with parametric ARFI images showing peak induced displacement and time to 67% recovery and to spatially correlated immunohistochemistry. Our results support that robust techniques outperform conventional PCA and clustering approaches to classification when ARFI data are inclusive of low to relatively high noise levels (up to 5 dB average signal-to-noise [SNR] to amplitude) but no outliers: for example, 99.53% correct for robust techniques vs. 97.75% correct for the classical approach. The robust techniques also perform better than conventional approaches when ARFI data are inclusive of moderately high noise levels (10 dB average SNR to amplitude) in addition to a high concentration of outlier displacement profiles (10% outlier content): for example, 99.87% correct for robust techniques vs. 33.33% correct for the classical approach. This work suggests that automatic identification of tissue structures exhibiting similar displacement responses to ARFI excitation is possible, even in the context of outlier profiles. Moreover, this work represents an important first step toward automatic correlation of ARFI data to spatially matched immunohistochemistry.

Detection and quantification of calcifications in intravascular ultrasound images by automatic thresholding

An innovative application of automatic thresholding is used for the detection of calcification regions in intravascular ultrasound images. A priori knowledge of the acoustic shadow that usually accompanies calcification regions is used to discriminate these from other bright regions in the image. A method for the calculation of the angle of calcification has also been developed. The proposed algorithms are applied to in-vivo images obtained from left anterior descending coronary arteries during percutaneous transluminal coronary angioplasty (n = 14). The resulting specificity is 72% and the sensitivity 84%. The receiver operating characteristic curve, the area under the curve being equal to 0.91, is plotted to evaluate the algorithm performance.