Ultrasound Image Analysis with Vision Transformers-Review.

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges, such as a low imaging quality and high variability. There is a need to develop advanced automatic US image analysis methods to enhance its diagnostic accuracy and objectivity. Vision transformers, a recent innovation in machine learning, have demonstrated significant potential in various research fields, including general image analysis and computer vision, due to their capacity to process large datasets and learn complex patterns. Their suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformers and discusses their applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in their application in medical US image analysis. Vision transformers have shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and are expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

Thermometry using entropy imaging of ultrasound radio frequency signal time series.

Low intensity focused ultrasound (LIFU) is a novel approach that could activate drug release and considerably improve the delivery of anticancer drug. LIFU treatment has some features like is able to penetrate deep into the tissue and being non-invasive, as a consequence LIFU displays great capability for controlling the drug release and improving the chemotherapy treatment efficiency. The goal of this study is to research the feasibility of the entropy parameter of RF time series of ultrasound backscattered signals for measuring the changes in temperature induced by a LIFU device. Entropy Imaging is a technique for reconstructing ultrasound images based on the average uncertainty of time-series in a signal. Furthermore, the Shannon Entropy can quantify the uncertainty of a random process and is usually used as a measure for the information content of probability distributions. In this study, we use the Entropy Imaging method for measuring the LIFU-induced temperature changes in the deep region of ex vivo porcine tissue samples. The results obtained show that the changes of entropy parameter of RF time series signal are proportional to temperature changes recorded by a calibrated thermocouple in the temperature range of 37-47°C. In conclusion, in this study we show that Shannon entropy of RF time series signal possesses promising features like succinctly capturing the available information in a system by considering the uncertainty in a given data that can be used, as a new method, to measure temperature changes non-invasively and quantitatively in the deep region of tissue.

Automatic morphological classification of mitral valve diseases in echocardiographic images based on explainable deep learning methods.

PURPOSE: Carpentier's functional classification is a guide to explain the types of mitral valve regurgitation based on morphological features. There are four types of pathological morphologies, regardless of the presence or absence of mitral regurgitation: Type I, normal; Type II, mitral valve prolapse; Type IIIa, mitral valve stenosis; and Type IIIb, restricted mitral leaflet motion. The aim of this study was to automatically classify mitral valves using echocardiographic images. METHODS: In our procedure, after the classification of apical 4-chamber (A4C) and parasternal long-axis (PLA) views, we extracted the systolic/diastolic phase of the cardiac cycle by calculating the left ventricular area. Six typical pre-trained models were fine-tuned with a 4-class model for the PLA and a 3-class model for the A4C views. As an additional contribution, to provide explainability, we applied the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm to visualize areas of echocardiographic images where the different models generated a prediction. RESULTS: This approach conferred a proper understanding of where various networks "look" into echocardiographic images to predict the four types of pathological mitral valve morphologies. Considering the accuracy metric and Grad-CAM maps and by applying the Inception-ResNet-v2 architecture to classify Type II in the PLA view and ResNeXt50 architecture to classify the other three classes in the A4C view, we achieved an 80% rate of model accuracy in the test data set. CONCLUSIONS: We suggest an explainable, fully automated, and rule-based procedure to classify the four types of mitral valve morphologies based on Carpentier's functional classification using deep learning on transthoracic echocardiographic images. Our study results infer the feasibility of the use of deep learning models to prepare quick and precise assessments of mitral valve morphologies in echocardiograms. According to our knowledge, our study is the first one that provides a public data set regarding the Carpentier classification of MV pathologies.

Speckle Tracking Accuracy Enhancement by Temporal Super-Resolution of Three-Dimensional Echocardiography Images.

BACKGROUND: Speckle tracking has always been a challenging issue in echocardiography images due to the lowcontrast and noisy nature of ultrasonic imaging modality. While in ultrasound imaging, framerate is limited by image size and sound speed in tissue, speckle tracking results get worse inthree-dimensional imaging due to its lower frame rate. Therefore, numerous techniques have beenreported to overcome this limitation and enhance tracking accuracy. METHODS: In this work, we have proposedto increase the frame rate temporally for a sequence of three-dimensional (3D) echocardiographyframes to make tracking more accurate. To increase the number of frames, cubic B-spline is usedto interpolate between intensity variation time curves extracted from every single voxel in theimage during the cardiac cycle. We have shown that the frame rate increase will result in trackingaccuracy improvement. RESULTS: To prove the efficiency of the proposed method, numerical evaluation metricsfor tracking are reported to make a comparison between high temporal resolution sequences andlow temporal resolution sequences. Anatomical affine optical flow is selected as the state-of-the-artspeckle tracking method, and a 3D echocardiography dataset is used to evaluate the proposedmethod. CONCLUSION: Results show that it is beneficial for speckle tracking to perform on temporally condensedframes rather than ordinary clinical 3D echocardiography images. Normalized mean enhancementvalues for mean absolute error, Hausdorff distance, and Dice index for all cases and all frames are0.44 ± 0.09, 0.42± 0.09, and 0.36 ± 0.06, respectively.

Efficient synthetic transmit aperture ultrasound based on tensor completion.

One of the most important methods in medical ultrasound imaging is the synthetic transmit aperture (STA). Despite the image quality improvement in the STA, this method suffers from several limitations, including a limited data acquisition rate and an increase in the overall time to form a single frame. Tensor completion (TC) is a powerful technique that uses rank minimization to recover missing information from a low-rank tensor. This paper provides a novel random synthetic transmit aperture (RSTA) method based on using only a randomly selected part (a fraction) of the linear array elements in the transmit mode to increase the data acquisition rate and then applying the tensor completion (TC) to improve the image quality. By the proposed method, as it is not necessary to transmit all elements sequentially, the data acquisition rate is improved and the overall time for creating an image is also significantly reduced. We investigated the proposed idea by using several simulated and experimental phantoms. Results showed that the proposed method could increase the data acquisition rate up to three times with the image quality difference of less than 6% compared to the original STA method.

Coherent Plane Wave Compounding Combined With Tensor Completion Applied for Ultrafast Imaging.

To solve the problem of resolution and contrast in plane wave imaging (PWI), coherent plane wave compounding (CPWC) was introduced, in which scanning was performed at different angles, which can achieve the desired image quality by combining the images obtained from PWI at different angles. However, the application of this idea reduces the frame rate in proportion to the number of plane waves (PWs) or angles, so that in this modality, when dealing with some applications such as shear wave imaging (SWI) and strain imaging, there is always a compromise between the frame rate and the image quality. Tensor completion (TC) is a powerful technique to recover missing information of a low-rank tensor from limited observations based on rank minimization. In this article, we present an idea based on TC to make this compromise lighter; in other words, with a smaller number of angles, we can achieve the desired quality of the output image. To evaluate the proposed idea, plane wave imaging challenge in medical ultrasound (PICMUS) datasets was used, which were recorded at 75 different angles. The results of the resolution evaluation showed that using 20% of the coherent PWs and reconstructing other 80% by TC, compared with the situation of using only 20% of the coherent PWs provided a resolution improvement of 14.97% and 17.4% in the simulated and experimental point targets, respectively. Also, the results of the contrast investigation showed that the contrast ratio (CR) improved by 72.6%, 62.9%, and 111.4% in the simulated cyst target data, experimental cyst targets, and in vivo carotid cross section, respectively. The results confirmed that using 20% of the coherent PWs and reconstructing other 80% by TC, the image quality is very close to that obtained by considering all 75 angles, so that the difference in resolution is less than 2% and the difference in contrast to noise ratio (CNR) is less than 5 dB. Therefore, with this idea, it can be said that less compromise is needed; in other words, despite having a higher frame rate, an acceptable quality can be achieved.

Spatiotemporal registration and fusion of transthoracic echocardiography and volumetric coronary artery tree.

PURPOSE: Cardiac multimodal image fusion can offer an image with various types of information in a single image. Many coronary stenosis, which are anatomically clear, are not functionally significant. The treatment of such kind of stenosis can cause irreversible effects on the patient. Thus, choosing the best treatment planning depend on anatomical and functional information is very beneficial. METHODS: An algorithm for the fusion of coronary computed tomography angiography (CCTA) as an anatomical and transthoracic echocardiography (TTE) as a functional modality is presented. CCTA and TTE are temporally registered using manifold learning. A pattern search optimization algorithm, using normalized mutual information, is used to find the best match slice to TTE frame from CCTA volume. By employing a free-form deformation, the heart's non-rigid deformations are modeled. The spatiotemporal registered TTE frame is embedded to achieve the fusion result. RESULTS: The accuracy is evaluated on CCTA and TTE data obtained from 10 patients. In temporal registration, mean absolute error of 1.97 [Formula: see text] 1.23 is resulted from comparing the output frame numbers from the algorithm and from manual assignment by an expert. In spatial registration, the accuracy of the similarity between the best match slice from CCTA volume and TTE frame is resulted in 1.82 [Formula: see text] 0.024 mm, 6.74 [Formula: see text] 0.013 mm, and 0.901 [Formula: see text] 0.0548 due to mean absolute distance, Hausdorff distance, and Dice similarity coefficient, respectively. CONCLUSION: Without the use of ECG and Optical tracking systems, a semiautomatic framework of spatiotemporal registration and fusion of CCTA volume and TTE frame is presented. The experimental results showed the effectiveness of our proposed method to create complementary information from TTE and CCTA, which may help in the early diagnosis and effective treatment of cardiovascular diseases (CVDs).

Echocardiography image enhancement using texture-cartoon separation.

Due to the speckled nature of cardiac ultrasound imaging, it is not easy to process and extract useful information directly from the acquired image. In this work, we have proposed a method to reduce the effect of speckle artifacts through the decomposition of echocardiography images into cartoon and texture components. The first component (i.e., cartoon image) contains image structures containing smooth areas and sharp edges, and the texture component is mainly composed of highly oscillating and repetitive patterns. To decompose the image into these two subcomponents, convolutional sparse coding has been utilized as a solid tool for solving the decomposition optimization function. The significant advantage of using convolutional sparse coding, compared to classical sparse coding methods, is image quality enhancement due to not using the block coding, making the classic solutions computationally feasible. The original image has been masked with the cartoon part leading to suppress speckle artifacts which result in image quality enhancement. Besides, it has been shown that using this speckle reduction scenario, considerable accuracy enhancement of the segmentation task can be achieved, compared to segmentation of the original image. Numerical results provide acceptable reasons to prove the efficiency of the proposed algorithm. Resulting echocardiography videos show a mean segmentation enhancement of 15.98 for Hausdorff distance (in pixels) and 0.0632 for the Dice similarity coefficient.

A deep learning approach for the automatic recognition of prosthetic mitral valve in echocardiographic images.

The first step in the automatic evaluation of the cardiac prosthetic valve is the recognition of such valves in echocardiographic images. This research surveyed whether a deep convolutional neural network (DCNN) could improve the recognition of prosthetic mitral valve in conventional 2D echocardiographic images. An efficient intervention to decrease the misreading rate of the prosthetic mitral valve is required for non-expert cardiologists. This intervention could serve as a section of a fully-automated analysis chain, alleviate the cardiologist's workload, and improve precision and time management, especially in an emergent situation. Additionally, it might be suitable for pre-labeling large databases of unclassified images. We, therefore, introduce a large publicly-available annotated dataset for the purpose of prosthetic mitral valve recognition. We utilized 2044 comprehensive non-stress transthoracic echocardiographic studies. Totally, 1597 patients had natural mitral valves and 447 patients had prosthetic valves. Each case contained 1 cycle of echocardiographic images from the apical 4-chamber (A4C) and the parasternal long-axis (PLA) views. Thirteen versions of the state-of-the-art models were independently trained, and the ensemble predictions were performed using those versions. For the recognition of prosthetic mitral valves from natural mitral valves, the area under the receiver-operating characteristic curve (AUC) made by the deep learning algorithm was similar to that made by cardiologists (0.99). In this research, EfficientNetB3 architecture in the A4C view and the EfficientNetB4 architecture in the PLA view were the best models among the other pre-trained DCNN models.

Skull acoustic aberration correction in photoacoustic microscopy using a vector space similarity model: a proof-of-concept simulation study.

Skull bone represents a highly acoustical impedance mismatch and a dispersive barrier for the propagation of acoustic waves. Skull distorts the amplitude and phase information of the received waves at different frequencies in a transcranial brain imaging. We study a novel algorithm based on vector space similarity model for the compensation of the skull-induced distortions in transcranial photoacoustic microscopy. The results of the algorithm tested on a simplified numerical skull phantom, demonstrate a fully recovered vasculature with the recovery rate of 91.9%.

Carotid Wall Longitudinal Motion in Ultrasound Imaging: An Expert Consensus Review.

Motion extracted from the carotid artery wall provides unique information for vascular health evaluation. Carotid artery longitudinal wall motion corresponds to the multiphasic arterial wall excursion in the direction parallel to blood flow during the cardiac cycle. While this motion phenomenon has been well characterized, there is a general lack of awareness regarding its implications for vascular health assessment or even basic vascular physiology. In the last decade, novel estimation strategies and clinical investigations have greatly advanced our understanding of the bi-axial behavior of the carotid artery, necessitating an up-to-date review to summarize and classify the published literature in collaboration with technical and clinical experts in the field. Within this review, the state-of-the-art methodologies for carotid wall motion estimation are described, and the observed relationships between longitudinal motion-derived indices and vascular health are reported. The vast number of studies describing the longitudinal motion pattern in plaque-free arteries, with its putative application to cardiovascular disease prediction, point to the need for characterizing the added value and applicability of longitudinal motion beyond established biomarkers. To this aim, the main purpose of this review was to provide a strong base of theoretical knowledge, together with a curated set of practical guidelines and recommendations for longitudinal motion estimation in patients, to foster future discoveries in the field, toward the integration of longitudinal motion in basic science as well as clinical practice.

Temporal Super-resolution of Ultrasound Imaging Using Matrix Completion.

The temporal super-resolution of the dynamic ultrasound imaging, a means to observe rapid heart movements, is considered an important subject in medical diagnosis of cardiac conditions. Here, a new technique based on the acquisition scheme using the matrix completion (MC) theory is offered for the temporal super-resolution of the two-dimensional (2D) and three-dimensional (3D) ultrasound imaging. MC mentions the problem of completing a low-rank matrix when only a subset of its elements can be observed. Here, the lower scan lines are acquired. Whereby, the proposed method uses temporal and spatial information of the radio frequency (RF) image sequences for the reconstruction of skipped RF lines. This is performed using the construction of the MC images and then reconstruction of them by the MC theory. The results of the proposed method are compared with the compressive sensing (CS) reconstruction methods. The qualitative and quantitative evaluations of 2D and 3D data demonstrate that in the proposed method, which uses the spatial and temporal relation of RF images and the MC theory, the reconstruction is more accurate, and the reconstruction error is lower. The computational complexity of this method is very low. It also does not require hardware adjustments. Therefore, it can be easily implemented in current ultrasound-imaging devices with the frame-rate enhancement. For instance, the frame rate up to two times the original sequence is feasible using the proposed methods, while root mean square error is decreased by about 35% and 30% for 2D and 3D data, respectively, compared with the CS reconstruction method.

Granger causality analysis in combination with directed network measures for classification of MS patients and healthy controls using task-related fMRI.

Several studies have already assessed brain network variations in multiple sclerosis (MS) patients and healthy controls (HCs). The underlying neural system's functioning is apparently too complicated, however. Therefore, the neural time series' analysis through new methods is the aim of any recent research. Functional magnetic resonance imaging (fMRI) is a prominent modality for investigating the human brain's neural substrate, especially when cognitive impairment occurs. The present study was an attempt to investigate the brain network's differences between MS patients and HCs using graph-theoretic measures constructed by an effective connectivity measure through statistical tests. The results of the significant measures were then evaluated through machine learning methods. To this end, we gathered blood-oxygen level dependent (BOLD) fMRI data of the participants during the execution of paced auditory serial addition test (PASAT). Granger causality analysis (GCA) was then employed between brain regions' time series on each subject in order to construct a brain network. Afterward, the Wilcoxon rank-sum test was implemented to find the alteration of brain networks between the mentioned groups. According to the results, Global flow coefficient was significantly different between HCs and patients. Moreover, MS disease impacted several areas of the brain including Hippocampus, Para Hippocampal, Thalamus, Cuneus, Superior temporal gyrus, Heschl, Caudate, Medial Frontal Superior Gyrus, Fusiform, Pallidum, and several parts of Cerebellum in centrality measures and local flow coefficient. Most of the obtained regions were related to the cognitive impacts of the disease. We also found the best subset of graph features by means of Fisher score, and classified them to evaluate the features strength for the discrimination of MS patients from HCs via several machine learning methods. Having used the combination of Wilcoxon rank-sum test and Fisher score, we were able to classify MS patients from HCs using linear support vector machine (SVM) with an accuracy of 95%. With regard to the few existing studies on brain network of MS patients, especially during a cognitive task execution, our findings showed that the selected graph measures by Wilcoxon rank-sum test and Fisher score from the GCA-based brain networks resulted in a promising classification accuracy.

Analysis of brain functional connectivity network in MS patients constructed by modular structure of sparse weights from cognitive task-related fMRI.

Cognitive dysfunction in multiple sclerosis (MS) seems to be the result of neural disconnections, leading to a wide range of brain functional network alterations. It is assumed that the analysis of the topological structure of brain connectivity network can be used to assess cognitive impairments in MS disease. We aimed to identify these brain connectivity pattern alterations and detect the significant features for the distinction of MS patients from healthy controls (HC). In this regard, the importance of functional brain networks construction for better exhibition of changes, inducing the improved reflection of functional organization structure should be precisely considered. In this paper, we strove to introduce a framework for modeling the functional connectivity network by considering the two most important intrinsic sparse and modular structures of brain. For the proposed approach, we first derived group-wise sparse representation via learning a common over-complete dictionary matrix from the aggregated cognitive task-based functional magnetic resonance imaging (fMRI) data of all subjects of the two groups to be able to investigate between-group differences. We then applied the modularity concept on achieved sparse coefficients to compute the connectivity strength between the two brain regions. We examined the changes in network topological properties between relapsing-remitting MS (RRMS) and matched HC groups by considering the pairwise connections of regions of the resulted weighted networks and extracting graph-based measures. We found that the informative brain regions were related to their important connectivity weights, which could distinguish MS patients from the healthy controls. The experimental findings also proved the discrimination ability of the modularity measure among all the global features. In addition, we identified such local feature subsets as eigenvector centrality, eccentricity, node strength, and within-module degree, which significantly differed between the two groups. Moreover, these nodal graph measures have been served as the detectors of brain regions, affected by different cognitive deficits. In general, our findings illustrated that integration of sparse representation, modular structure, and pairwise connectivity strength in combination with the graph properties could help us with the early diagnosis of cognitive alterations in the case of MS.

High-Intensity Focused Ultrasound Lesion Detection Using Adaptive Compressive Sensing Based on Empirical Mode Decomposition.

BACKGROUND: The main goal of ultrasound therapy is to have clinical effects in the tissue without damage to the intervening and surrounding tissues. Treatments have been developed for both in vitro and in clinical applications. HIFU therapy is one of these. Non-invasive surgeries, such as HIFU, have been developed to treat tumors or to stop bleeding. In this approach, an adequate imaging method for monitoring and controlling the treatment is required. METHODS: In this paper, an adaptive compressive sensing representation of ultrasound RF echo signals is presented based on empirical mode decomposition (EMD). According to the different numbers of intrinsic mode functions (IMFs) produced by the EMD, the ultrasound signals is adaptively compressive sampled in the source and then adaptively reconstructed in the receiver domains. In this paper, a new application of compressive sensing based on EMD (CS-EMD) in the monitoring of high-intensity focused ultrasound (HIFU) treatment is presented. Non-invasive surgeries such as HIFU have been developed for various therapeutic applications. In this technique, a suitable imaging method is necessary for monitoring of the treatment to achieve adequate treatment safety and efficacy. So far, several methods have been proposed, such as ultrasound radiofrequency (RF) signal processing techniques, and imaging methods such as X-ray, MRI, and ultrasound to monitor HIFU lesions. RESULTS: In this paper, a CS-EMD method is used to detect the HIFU thermal lesion dimensions using different types of wavelet transform. The results of the processing on the real data demonstrate the potential for this technique in image-guided HIFU therapy. CONCLUSIONS: In this study, a new application of compressive sensing in the field of monitoring of the HIFU treatment is presented. To the best of our knowledge, so far no studies on compressive sensing have been carried out in the monitoring of the HIFU. Based on the results obtained, it was showed that the number of measurements and Intrinsic Mode Functions have the function of noise reduction. In addition, results were shown that the successful reconstruction of the compressive sensing signals can be gained using a threshold based algorithm. To this end, in this paper it was shown that by selecting an suitable number of measurements, the sparse transform, and a thresholding algorithm, we can achieve a more accurate detection of the HIFU thermal lesion size.

Skull's Photoacoustic Attenuation and Dispersion Modeling with Deterministic Ray-Tracing: Towards Real-Time Aberration Correction.

Although transcranial photoacoustic imaging has been previously investigated by several groups, there are many unknowns about the distorting effects of the skull due to the impedance mismatch between the skull and underlying layers. The current computational methods based on finite-element modeling are slow, especially in the cases where fine grids are defined for a large 3-D volume. We develop a very fast modeling/simulation framework based on deterministic ray-tracing. The framework considers a multilayer model of the medium, taking into account the frequency-dependent attenuation and dispersion effects that occur in wave reflection, refraction, and mode conversion at the skull surface. The speed of the proposed framework is evaluated. We validate the accuracy of the framework using numerical phantoms and compare its results to k-Wave simulation results. Analytical validation is also performed based on the longitudinal and shear wave transmission coefficients. We then simulated, using our method, the major skull-distorting effects including amplitude attenuation, time-domain signal broadening, and time shift, and confirmed the findings by comparing them to several ex vivo experimental results. It is expected that the proposed method speeds up modeling and quantification of skull tissue and allows the development of transcranial photoacoustic brain imaging.

High-Intensity Focused Ultrasound Thermal Lesion Detection Using Entropy Imaging of Ultrasound Radio Frequency Signal Time Series.

BACKGROUND: During the past few decades, high-intensity focused ultrasound (HIFU) modality has been gaining surging interest in various therapeutic applications such as non- or minimally-invasive cancer treatment. Among other attributes, robust and real-time HIFU treatment monitoring and lesion detection have become essential issues for successful clinical acceptance of the modality. More recently, ultrasound radio frequency (RF) time series imaging has been studied by a number of researchers. MATERIALS AND METHODS: The objective of this study is to investigate the applicability of entropy parameter of RF time series of ultrasound backscattered signals, a. k. a. Entropy imaging, toward HIFU thermal lesion detection. To this end, five fresh ex vivo porcine muscle tissue samples were exposed to HIFU exposures with total acoustic powers ranging from 30 to 110 Watts. The contrast-to-speckle ratio (CSR) values of the entropy images and their corresponding B-mode images of pre-, during- and post-HIFU exposure for each acoustic power were calculated. RESULTS: The novelty of this study is the use of Entropy parameter on ultrasound RF time series for the first time. Statistically significant differences were obtained between the CSR values for the B mode and entropy images at various acoustic powers. In case of 110 Watt, a CSR value 3.4 times higher than B-mode images was accomplished using the proposed method. Furthermore, the proposed method is compared with the scaling parameter of Nakagami imaging and same data which are used in this study. CONCLUSION: Entropy has the potential for using as an imaging parameter for differentiating lesions in HIFU surgery.

Toward high-intensity focused ultrasound lesion quantification using compressive sensing theory.

Compressive sensing theory has in recent years been increasingly used in various pattern recognition applications. Compressive sensing theory makes it possible, under certain assumptions, to recover a signal or an image sampled below the Nyquist sampling limit. In this work, a new application of compressive sensing based on the threshold algorithm, in the area of controlling and monitoring of high-intensity focused ultrasound therapy, was investigated. In this work, a new method of high-intensity focused ultrasound lesion detection is presented based on a modified compressive sensing method in combination with the threshold algorithm and the wavelet transforms. In this study, analysis of the suggested method is performed using two sets of data: simulated and experimental ultrasound radio frequency data. The results of processing the data show that the proposed algorithm results in enhancement of the high-intensity focused ultrasound lesion contrast in comparison with the ultrasound B-mode and standard compressive sensing imaging methods. The results of the study show that the modified compressive sensing method could effectively detect thermal lesions in vitro. Comparing the estimated size of the thermal lesion (8.3 mm × 8.4 mm) using the proposed algorithm with the actual size of that from physical examination (10.1 mm × 9 mm) shows that we could detect high-intensity focused ultrasound thermal lesions with the difference of 0.8 mm × 0.5 mm.

Quantification of Left Ventricle Function in Stress Echocardiography Using Endocardial Area Centroid Trajectory.

Coronary artery occlusion has a direct effect on cardiac activity and is a well-known reason for ventricular motion disorder, specifically left ventricle (LV) wall motion dysfunction. In stress echocardiography, wall motion abnormality is exaggerated when stress is applied to the heart, and therefore, it is easier to diagnose abnormality in ventricular motion. In this study, we have presented a new parameter that measures LV function. We have shown that LV function can be measured using a variation of endocard borders during a cardiac cycle in standard stress echocardiography frames. This parameter shows a meaningful difference between ischemic and normal hearts and is calculated at different heart rates (HRs). In conclusion, ischemic hearts cannot keep up with the required increase in activity when reaching peak levels of stress.

Breast cancer detection in automated 3D breast ultrasound using iso-contours and cascaded RUSBoosts.

Automated 3D breast ultrasound (ABUS) is a new popular modality as an adjunct to mammography for detecting cancers in women with dense breasts. In this paper, a multi-stage computer aided detection system is proposed to detect cancers in ABUS images. In the first step, an efficient despeckling method called OBNLM is applied on the images to reduce speckle noise. Afterwards, a new algorithm based on isocontours is applied to detect initial candidates as the boundary of masses is hypo echoic. To reduce false generated isocontours, features such as hypoechoicity, roundness, area and contour strength are used. Consequently, the resulted candidates are further processed by a cascade classifier whose base classifiers are Random Under-Sampling Boosting (RUSBoost) that are introduced to deal with imbalanced datasets. Each base classifier is trained on a group of features like Gabor, LBP, GLCM and other features. Performance of the proposed system was evaluated using 104 volumes from 74 patients, including 112 malignant lesions. According to Free Response Operating Characteristic (FROC) analysis, the proposed system achieved the region-based sensitivity and case-based sensitivity of 68% and 76% at one false positive per image.