B-mode Images Research Articles

Super-Resolution Ultrasound Imaging for Analysis of Microbubbles Cluster by Acoustic Vortex Tweezers.

Using acoustic vortex tweezers (AVT) to spatially accumulate microbubbles (MBs) shows promise for enhancing drug delivery efficiency and reducing off-target effects. The strong echogenicity of accumulated MBs also improves diagnostics via conventional ultrasound (US) B-mode imaging. However, the annular high-pressure distribution of AVT inhibits MBs inflow at the inlet, reducing MBs collection. The spatial resolution of US B-mode imaging further limits theranostic applications of AVT-mediated MBs accumulation. To address these challenges, we integrated an AVT waveform with volumetric super-resolution imaging (VSRI) to monitor the dynamic growth of MBs cluster during accumulation. We used a 5-MHz 2D array transducer for VSRI, employing plane wave pulses interleaved with accumulating pulses to retain MBs at a flow rate of 0.023-0.047 mL/s in a 3-mm vessel phantom. An asymmetrical AVT waveform (AVT*) was produced by modulating the pressure at the MBs inlet compared to the outlet. The effectiveness was validated in rat cerebral vessels for real-time volumetric tracking of MBs clusters. Microscopy observations showed that AVT* could quickly gather flowing MBs into cluster without repelling them at a flow rate of 0.023 mL/s. Statistical results indicated that microscopic data correlated better with VSRI than with B-mode images, suggesting VSRI suffices to detect the dynamics of AVT*-actuated MBs accumulation in real-time. Additionally, VSRI detected a significant increase in MBs cluster size over time during AVT* in the superior sagittal sinus of the rat brain. These findings demonstrate that the proposed strategy can accumulate the flowing MBs at a desired location and simultaneously observe this phenomenon.

Application and visualization study of an intelligence-assisted classification model for common eye diseases using B-mode ultrasound images.

Conventional approaches to diagnosing common eye diseases using B-mode ultrasonography are labor-intensive and time-consuming, must requiring expert intervention for accuracy. This study aims to address these challenges by proposing an intelligence-assisted analysis five-classification model for diagnosing common eye diseases using B-mode ultrasound images. This research utilizes 2064 B-mode ultrasound images of the eye to train a novel model integrating artificial intelligence technology. The ConvNeXt-L model achieved outstanding performance with an accuracy rate of 84.3% and a Kappa value of 80.3%. Across five classifications (no obvious abnormality, vitreous opacity, posterior vitreous detachment, retinal detachment, and choroidal detachment), the model demonstrated sensitivity values of 93.2%, 67.6%, 86.1%, 89.4%, and 81.4%, respectively, and specificity values ranging from 94.6% to 98.1%. F1 scores ranged from 71% to 92%, while AUC values ranged from 89.7% to 97.8%. Among various models compared, the ConvNeXt-L model exhibited superior performance. It effectively categorizes and visualizes pathological changes, providing essential assisted information for ophthalmologists and enhancing diagnostic accuracy and efficiency.

Non-invasive Deep-Brain Imaging with 3D Integrated Photoacoustic Tomography and Ultrasound Localization Microscopy (3D-PAULM).

Photoacoustic computed tomography (PACT) is a proven technology for imaging hemodynamics in deep brain of small animal models. PACT is inherently compatible with ultrasound (US) imaging, providing complementary contrast mechanisms. While PACT can quantify the brain's oxygen saturation of hemoglobin (sO2), US imaging can probe the blood flow based on the Doppler effect. Further, by tracking gas-filled microbubbles, ultrasound localization microscopy (ULM) can map the blood flow velocity with sub-diffraction spatial resolution. In this work, we present a 3D deep-brain imaging system that seamlessly integrates PACT and ULM into a single device, 3D-PAULM. Using a low ultrasound frequency of 4 MHz, 3D-PAULM is capable of imaging the brain hemodynamic functions with intact scalp and skull in a totally non-invasive manner. Using 3D-PAULM, we studied the mouse brain functions with ischemic stroke. Multi-spectral PACT, US B-mode imaging, microbubble-enhanced power Doppler (PD), and ULM were performed on the same mouse brain with intrinsic image co-registration. From the multi-modality measurements, we further quantified blood perfusion, sO2, vessel density, and flow velocity of the mouse brain, showing stroke-induced ischemia, hypoxia, and reduced blood flow. We expect that 3D-PAULM can find broad applications in studying deep brain functions on small animal models.

High-Frequency, 2-mm-Diameter Forward-Viewing 2-D Array for 3-D Intracoronary Blood Flow Imaging.

Coronary artery disease (CAD) is one of the leading causes of death globally. Currently, diagnosis and intervention in CAD are typically performed via minimally invasive cardiac catheterization procedures. Using current diagnostic technology, such as angiography and fractional flow reserve (FFR), interventional cardiologists must decide which patients require intervention and which can be deferred; 10% of patients with stable CAD are incorrectly deferred using current diagnostic best practices. By developing a forward-viewing intravascular ultrasound (FV-IVUS) 2-D array capable of simultaneously evaluating morphology, hemodynamics, and plaque composition, physicians would be better able to stratify risk of major adverse cardiac events in patients with intermediate stenosis. For this application, a forward-viewing, 16-MHz 2-D array transducer was designed and fabricated. A 2-mm-diameter aperture consisting of 140 elements, with element dimensions of 98×98×70 μ m ( w×h×t ) and a nominal interelement spacing of 120 μ m, was designed for this application based on simulations. The acoustic stack for this array was developed with a designed center frequency of 16 MHz. A novel via-less interconnect was developed to enable electrical connections to fan-out from a 140-element 2-D array with 120- μ m interelement spacing. The fabricated array transducer had 96/140 functioning elements operating at a center frequency of 16 MHz with a -6-dB fractional bandwidth of 62% ± 7 %. Single-element SNR was 23 ± 3 dB, and the measured electrical crosstalk was - 33 ± 3 dB. In imaging experiments, the measured lateral resolution was 0.231 mm and the measured axial resolution was 0.244 mm at a depth of 5 mm. Finally, the transducer was used to perform 3-D B-mode imaging of a 3-mm-diameter spring and 3-D B-mode and power Doppler imaging of a tissue-mimicking phantom.

Quantification of Cervical Elasticity During Pregnancy Based on Transvaginal Ultrasound Imaging and Stress Measurement.

To overcome these limitations, we develop a quantitative cervical elastography system by adding a stress sensor to a clinically used transvaginal ultrasound imaging system. We record the cervical deformation in B-mode images and measure the probe-surface stress through the sensor. Then we quantify the strain using a customized algorithm and estimate the cervical Young's modulus through stress-strain linear regression. In phantom experiments, we demonstrate the system's high accuracy (alignment with the quasi-static compression method, p-value = 0.369 > 0.05), robustness (alignment between 60°- and 90°-contact measurements, p-value = 0.638 > 0.05), repeatability (consistency of single sonographers' measurements, coefficient of variation < 0.06), and reproducibility (alignment between two sonographers' measurements, Pearson correlation coefficient = 0.981). Applying it to pregnant participants, we observe significant cervical softening (p-value < 0.001): Young's modulus decreases 3.95% weekly and its geometric mean value during the first (11 to 13 weeks), second, and third trimesters are 13.07 kPa, 7.59 kPa, and 4.40 kPa, respectively. The proposed system is accurate, robust, and safe, and enables longitudinal and inter-examiner comparisons. The system applies to different ultrasound machines with minor software updates, which allows for studies of cervical softening patterns in pregnancy for larger populations, facilitating insights into conditions such as preterm birth.

Carotid plaque characteristics in the CREST-2 trial

BackgroundThe modest stroke prevention from surgery for asymptomatic carotid disease has prompted a search for predictors that may improve risk stratification beyond luminal stenosis. Plaque disruption and atheroembolization are associated with unique anatomical and histological changes. The Carotid Revascularization and Medical Management for Asymptomatic Carotid Stenosis Trial (CREST-2) collects information on duplex ultrasound (DUS) plaque biomarkers with the goal of evaluating their relationship to the periprocedural and long-term risks of stroke. In this study, we examine the reliability with which carotid plaque features can be measured from DUS images, and report baseline carotid DUS-derived stenosis and plaque features using semiautomated digital image analysis of patients enrolled in CREST-2. MethodsWe studied the first 503 patients in CREST-2. Patients underwent standardized carotid DUS evaluation pre-enrollment. B-Mode images were scaled linearly to normalize brightness. Plaques were outlined manually. Dedicated software automatically measured the longitudinal sectional area (mm2), grayscale median (GSM), Gray-Weale classification, and tissue composition (mm2) of intraplaque hemorrhage (IPH), lipid, fibrous tissue, muscle, and calcium. We present the mean, standard deviation, median, interquartile range, minimum and maximum range, and proportions of carotid peak systolic velocities (PSVs) and plaque morphological features. We tested for autocorrelation among plaque features and computed the proportion of potentially unstable plaques in the cohort. Reliability of the image analysis techniques was tested in 100 patients using Bland-Altman plots and intraclass and interclass correlation coefficients. ResultsMost patients were male (58.4%), older (mean age of 69.3 years), White (87.5%), and had a PSV of ≥230 cm/s (98.6%); the 1.4% with a PSV of <230 cm/s were enrolled based on catheter angiography. Plaques in this study were large; the mean longitudinal sectional area was 62 ± 37 mm2 (range, 6.2–256.5 mm2). The mean GSM was 58 ± 30 (unitless) (range, 0–168) and Gray-Weale classification was 3.5 ± 0.9 (range, 1–5). The mean areas of tissue types were IPH 5.3 ± 8.9 mm2, lipid 9.3 ± 8.6 mm2, fibrous tissue 10 ± 10 mm2, muscle 17 ± 12 mm2, and calcium 1.6 ± 4.1 mm2. The PSV of patients showed poor correlation with plaque features. The proportion of plaques with a GSM of ≤35 was 22.8%, IPH of ≥5 mm2 was 30.0%, and a lipid-rich necrotic core of ≥40% was 3.0% of the cohort. Plaque measurements could be performed with high reliability with good interobserver and intraobserver correlations. ConclusionsSite-generated, core laboratory-interpreted ultrasound examination provides a reliable way of characterizing carotid plaque morphological features across studies performed at many CREST-2 sites. The initial cohort of patients randomized in CREST-2 had heterogeneity of plaque features despite causing high-grade stenosis. Completion of the trial will provide an opportunity to assess whether plaque heterogeneity interacts with response to revascularization and medical management.

Passive Acoustic Mapping for Convex Arrays With the Helical Wave Spectrum Method.

Passive acoustic mapping (PAM) has emerged as a valuable imaging modality for monitoring the cavitation activity in focused ultrasound therapies. When it comes to imaging in the human abdomen, convex arrays are preferred due to their large acoustic window. However, existing PAM methods for convex arrays rely on the computationally expensive delay-and-sum (DAS) operation limiting the image reconstruction speed when the field-of-view (FOV) is large. In this work, we propose an efficient and frequency-selective PAM method for convex arrays. This method is based on projecting the helical wave spectrum (HWS) between cylindrical surfaces in the imaging field. Both the in silico and in vitro experiments showed that the HWS method has comparable image quality and similar acoustic cavitation source localization accuracy as the DAS-based methods. Compared to the frequency-domain and time-domain DAS methods, the time-complexity of the HWS method is reduced by one order and two orders of magnitude, respectively. A parallel implementation of the HWS method realized millisecond-level image reconstruction speed. We also show that the HWS method is inherently capable of mapping microbubble (MB) cavitation activity of different status, i.e., no cavitation, stable cavitation, or inertial cavitation. After compensating for the lens effects of the convex array, we further combined PAM formed by the HWS method and B-mode imaging as a real-time dual-mode imaging approach to map the anatomical location where MBs cavitate in a liver phantom experiment. This method may find use in applications where convex arrays are required for cavitation activity monitoring in real time.

Spatial Coherence Approaches to Distinguish Suspicious Mass Contents in Fundamental and Harmonic Breast Ultrasound Images.

When compared to fundamental B-mode imaging, coherence-based beamforming, and harmonic imaging are independently known to reduce acoustic clutter, distinguish solid from fluid content in indeterminate breast masses, and thereby reduce unnecessary biopsies during a breast cancer diagnosis. However, a systematic investigation of independent and combined coherence beamforming and harmonic imaging approaches is necessary for the clinical deployment of the most optimal approach. Therefore, we compare the performance of fundamental and harmonic images created with short-lag spatial coherence (SLSC), M-weighted SLSC (M-SLSC), SLSC combined with robust principal component analysis with no M-weighting (r-SLSC), and r-SLSC with M-weighting (R-SLSC), relative to traditional fundamental and harmonic B-mode images, when distinguishing solid from fluid breast masses. Raw channel data acquired from 40 total breast masses (28 solid, 7 fluid, 5 mixed) were beamformed and analyzed. The contrast of fluid masses was better with fundamental rather than harmonic coherence imaging, due to the lower spatial coherence within the fluid masses in the fundamental coherence images. Relative to SLSC imaging, M-SLSC, r-SLSC, and R-SLSC imaging provided similar contrast across multiple masses (with the exception of clinically challenging complicated cysts) and minimized the range of generalized contrast-to-noise ratios (gCNRs) of fluid masses, yet required additional computational resources. Among the eight coherence imaging modes compared, fundamental SLSC imaging best identified fluid versus solid breast mass contents, outperforming fundamental and harmonic B-mode imaging. With fundamental SLSC images, the specificity and sensitivity to identify fluid masses using the reader-independent metrics of contrast difference, mean lag one coherence (LOC), and gCNR were 0.86 and 1, 1 and 0.89, and 1 and 1, respectively. Results demonstrate that fundamental SLSC imaging and gCNR (or LOC if no coherence image or background region of interest is introduced) have the greatest potential to impact clinical decisions and improve the diagnostic certainty of breast mass contents. These observations are additionally anticipated to extend to masses in other organs.

Evaluation of ARFI elastography for detecting active mastitis in sheep with previous fibrous lesions: a study of mammary parenchyma and supramammary lymph nodes.

The aim of the study was to evaluate the use of Acustic Radiation Force Impulse (ARFI) elastography in mammary parenchyma and supramammary lymph nodes, for detection of active mastitis in sheep with naturally infected chronic fibrous lesions. 27 female sheep were included and B-mode ultrasound and ARFI elastography images were obtained, acquiring qualitative (echogenicity and echotexture) and quantitative (shear rate, depth and short/long axis ratio) variables of 48 mammary glands. The glands were divided into three experimental groups: control group (CG) - healthy animals; LSCC- animals that presented fibrous lesions and SCC (somatic cell count) less than 500 x 103 cls/mL; HSCC: animals that presented fibrous lesions and SCC (somatic cell count) more than 500 x 103 cls/mL; The qualitative variables using B-mode ultrasonography, including echotexture and echogenicity, showed no significant differences between the evaluated groups and tissues (p = 0.9336 and p = 0.233, respectively) .In healthy areas of the gland, it was an increasing in shear wave velocity (SWV) in LSCC than in HSCC (p=0.04). When comparing the fibrosis in the LSCC and HSCC groups with their respective normal areas, the velocity increased in both groups: LSCC (p= 0,0007) and HSCC (p= 0,0001). When comparing the areas of fibrosis in LSCC and HSCC with the CG parenchyma, there was an increase in LSCC (p=0.001) and HSCC (p=0.0001). B-mode ultrasound indicate predominance of hypoechoic echogenicity in lymph nodes and reduced short/long axis ratio in cases of active subclinical mastitis. The supramammary lymph node showed increased SWV when comparing the CG with HSCC groups (p=0.02) and GC with LSCC (p=0.04). B-mode ultrasonography is useful for evaluating the mammary parenchyma, however, its application as a standalone diagnostic technique is not recommended. ARFI elastography indicates potential cutoff points for differentiating subclinical mastitis from healed mastitis, highlighting its importance as a tool for distinguishing normal areas from fibrous parenchymal areas. While this study did not establish specific cutoff points due to sample size limitations, further research with larger sample sizes could explore and define these critical thresholds.

ADMNet: Adaptive-Weighting Dual Mapping for Online Tracking With Respiratory Motion Estimation in Contrast-Enhanced Ultrasound.

Lesion localization and tracking are critical for accurate, automated medical imaging analysis. Contrast-enhanced ultrasound (CEUS) significantly enriches traditional B-mode ultrasound with contrast agents to provide high-resolution, real-time images of blood flow in tissues and organs. However, many trackers, designed primarily for natural RGB or B-mode ultrasound images, underutilize the extensive data from dual-screen enhanced images and fail to account for respiratory motion, thus facing challenges in achieving accurate target tracking. To address the existing challenges, we propose an adaptive-weighted dual mapping (ADMNet), an online tracking framework tailored for CEUS. Firstly, we introduced a novel Multimodal Atrous Attention Fusion (MAAF) module, innovatively designed to adapt the weightage between B-mode and enhanced images in dual-screen CEUS, reflecting the clinician's dynamic focus shifts between screens. Secondly, we proposed a Respiratory Motion Compensation (RMC) module to correct motion trajectory interferences due to respiratory motion, effectively leveraging temporal information. We utilized two newly established CEUS datasets, totaling 35,082 frames, to benchmark the ADMNet against various advanced B-mode ultrasound trackers. Our extensive experiments revealed that ADMNet achieves new state-of-the-art performance in CEUS tracking. Ablation studies and visualizations further underline the effectiveness of MAAF and RMC modules, demonstrating the promising potential of ADMNet in clinical CEUS tracing, thus providing novel research avenues in this field.

B-Mode ultrasound imaging in diagnosing carpal tunnel syndrome: an auxiliary diagnostic tool for hand surgeons.

The purpose of this article is to explore the effectiveness of B-Mode ultrasound as an auxiliary diagnostic tool for carpal tunnel syndrome (CTS). It aims to demonstrate the advantages of B-Mode ultrasound, including its non-invasive nature and its ability to provide real-time imaging, in localizing nerve compression and predicting postoperative outcomes. The study included 40 patients who were subjected to preoperative B-ultrasonography. The approach focused on evaluating the consistency of B-Mode ultrasound results with intraoperative findings. It also assessed the importance of employing standardized imaging techniques and emphasized the need for cooperation between hand surgeons and sonographers for accurate diagnosis. B-Mode ultrasound findings in the study were consistent with intraoperative observations, indicating its reliability. Additionally, B-Mode ultrasound was able to identify other anatomical abnormalities within the carpal canal that may contribute to CTS symptoms, such as persistent median arteries, median nerve bifurcation, and space-occupying lesions like cysts and tumors. The article concludes that B-Mode ultrasound should be considered a valuable supplementary diagnostic tool for CTS, particularly in instances where clinical signs and electrophysiological studies do not offer clear results. However, it should not replace established diagnostic methods for CTS.

FAMF-Net: Feature Alignment Mutual Attention Fusion with Region Awareness for Breast Cancer Diagnosis via Imbalanced Data.

Automatic and accurate classification of breast cancer in multimodal ultrasound images is crucial to improve patients' diagnosis and treatment effect and save medical resources. Methodologically, the fusion of multimodal ultrasound images often encounters challenges such as misalignment, limited utilization of complementary information, poor interpretability in feature fusion, and imbalances in sample categories. To solve these problems, we propose a feature alignment mutual attention fusion method (FAMF-Net), which consists of a region awareness alignment (RAA) block, a mutual attention fusion (MAF) block, and a reinforcement learning-based dynamic optimization strategy(RDO). Specifically, RAA achieves region awareness through class activation mapping and performs translation transformation to achieve feature alignment. When MAF utilizes a mutual attention mechanism for feature interaction fusion, it mines edge and color features separately in B-mode and shear wave elastography images, enhancing the complementarity of features and improving interpretability. Finally, RDO uses the distribution of samples and prediction probabilities during training as the state of reinforcement learning to dynamically optimize the weights of the loss function, thereby solving the problem of class imbalance. The experimental results based on our clinically obtained dataset demonstrate the effectiveness of the proposed method. Our code will be available at: https://github.com/Magnety/Multi_modal_Image.

DopUS-Net: Quality-Aware Robotic Ultrasound Imaging Based on Doppler Signal

Medical ultrasound (US) is widely used to evaluate and stage vascular diseases, in particular for the preliminary screening program, due to the advantage of being radiation-free. However, automatic segmentation of small tubular structures (e.g., the ulnar artery) from cross-sectional US images is still challenging. To address this challenge, this paper proposes the DopUS-Net and a vessel re-identification module that leverage the Doppler effect to enhance the final segmentation result. Firstly, the DopUS-Net combines the Doppler images with B-mode images to increase the segmentation accuracy and robustness of small blood vessels. It incorporates two encoders to exploit the maximum potential of the Doppler signal and recurrent neural network modules to preserve sequential information. Input to the first encoder is a two-channel duplex image representing the combination of the grey-scale Doppler and B-mode images to ensure anatomical spatial correctness. The second encoder operates on the pure Doppler images to provide a region proposal. Secondly, benefiting from the Doppler signal, this work first introduces an online artery re-identification module to qualitatively evaluate the real-time segmentation results and automatically optimize the probe pose for enhanced Doppler images. This quality-aware module enables the closed-loop control of robotic screening to further improve the confidence and robustness of image segmentation. The experimental results demonstrate that the proposed approach with the re-identification process can significantly improve the accuracy and robustness of the segmentation results (Dice score: from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.54$</tex-math> </inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.86$</tex-math> </inline-formula> ; intersection over union: from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.47$</tex-math> </inline-formula> to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$0.78$</tex-math> </inline-formula> ). <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The Doppler signal is important for the diagnosis of vascular disease, e.g., peripheral arterial disease, in clinical practices, nevertheless it is not of similar significance for state-of-the-art robotic ultrasound (US) examination systems yet. This paper explores various neural network structures to effectively extract the blood vessels from US images by incorporating the Doppler signal into the segmentation process. The final DopUS structure with two encoders extracting differentiated information from two different inputs and fusing the latent feature representations in the bottleneck layer can also inspire other tasks like multi-senor fusion. In addition, this work developed a Doppler-based tracker to assess the quality of the segmentation results in real-time. The assessment is subsequently used for a quality-aware module that enables closed-loop control of the robotic screening. Preliminary physical experiments suggest that the quality-aware robotic screening system can improve the confidence and robustness of autonomous US examination results. In the future, the Doppler signal could also be used to support clinical diagnosis. We believe the proposed quality-aware autonomous screening system is important for the development of large-scale robotic US screening programs. It will not only benefit the examination of limb arteries but also other vascular structures, e.g., carotid or aorta.

High-frequency wearable ultrasound array belt for small animal echocardiography.

Wearable ultrasound has been widely developed for long-term, continuous imaging without the need for bulky system manipulation and repeated manual locating. To potentially lead to more accurate and reliable imaging monitoring, this work presents the design, fabrication, and evaluation of a novel high-frequency wearable ultrasound array belt (WUAB) for small animal echocardiography. The fabrication process involved precise dicing technology for a λ-pitch design. The 20 MHz WUAB consists of two matching layers, piezoelectric composite with 128 channels, customized flexible circuit substrate, acoustic backing layer, and customized belt structure with designed end tip and insertion point for wearability. The resulting WUAB demonstrates sensitivity of -5.69 ± 2.5 dB and fractional bandwidth of 57 ± 5 %. In vivo experiments on rat model showed expected echocardiography and B-mode images of rat heart. These results represent significant promise for future longitudinal studies in small animals and real-time physiological monitoring.

Quantitative ultrasound parameters from scattering and propagation may reduce the biopsy rate for breast tumor

Breast cancer has become the most common cancer worldwide, and early screening improves the patient’s survival rate significantly. Although pathology with needle-based biopsy is the gold standard for breast cancer diagnosis, it is invasive, painful, and expensive. Meanwhile it makes patients suffer from misplacement of the needle, resulting in misdiagnosis and further assessment. Ultrasound imaging is non-invasive and real-time, however, benign and malignant tumors are hard to differentiate in grayscale B-mode images. We hypothesis that breast tumors exhibit characteristic properties, which generates distinctive spectral patterns not only in scattering, but also during propagation. In this paper, we propose a breast tumor classification method that evaluates the spectral pattern of the tissues both inside the tumor and beneath it. First, quantitative ultrasonic parameters of these spectral patterns were calculated as the representation of the corresponding tissues. Second, parameters were classified by the K-Nearest Neighbor machine learning model. This method was verified with an open access dataset as a reference, and applied to our own dataset to evaluate the potential for tumors assessment. With both datasets, the proposed method demonstrates accurate classification of the tumors, which potentially makes it unnecessary for certain patients to take the biopsy, reducing the rate of the painful and expensive procedure.

The development of a 1.25 MHz 1024-channel sparse array for human transcranial imaging: in vitro characterization

Ultrasound imaging is overwhelmingly used as 2D modality even though 3D imaging capabilities have existed for decades. Recent generational shifts toward super-resolution ultrasound imaging and functional ultrasound imaging, especially in the brain, have generated renewed and sustained interest in acquiring truly volumetric, 4D data. However, volumetric imaging approaches are currently limited to small animals, due in part to the difficulty of imaging transcranially in humans and due to a lack of imaging arrays designed for this purpose. Clinical translation of these recent techniques as well as conventional diagnostic B-mode imaging may thus benefit from array designs that capitalize on large channel count imaging systems. We have designed and developed a 1024-channel sparse array with a 65 mm circular aperture and a 1–2 MHz bandwidth. This unique transducer achieves an aperture that is far larger than conventional matrix probes using a sparse arrangement of elements ordered in a density-tapered spiral design. This design has significantly decreased grating lobes compared to a matrix array probe. The large aperture of this probe also enables acquisition over a large field of view with a significant depth of more than 100 mm. Simulations, acoustic characterization, and in vitro tests demonstrate that this transducer achieves a high focal gain that enables ultrasonic visualization beneath the human skull and at large depths due to its low F-number capabilities. Furthermore, we show that this transducer is capable of high point target contrast and high soft tissue contrast, with contrast-to-noise ratios up to 1.9 when imaging transcranially through a 3 mm thick section of human skull. Because of the large surface area of this probe, it can capture over 3 coherence lengths in each dimension and is, therefore, able to able to ‘average out’ the aberration over a large surface area. This transducer is poised to have a significant clinical impact in transcranial human imaging.

Automated 3-D Ultrasound Elastography of the Breast: An In Vivo Validation Study

Studies have indicated that adding 2-D quasi-static elastography to B-mode ultrasound imaging improved the specificity for malignant lesion detection, as malignant lesions are often stiffer (increased strain ratio) compared with benign lesions. This method is limited by its user dependency and so unsuitable for breast screening. To overcome this limitation, we implemented quasi-static elastography in an automated breast volume scanner (ABVS), which is an operator-independent 3-D ultrasound system and is especially useful for screening women with dense breasts. The study aim was to investigate if 3-D quasi-static elastography implemented in a clinically used ABVS can discriminate between benign and malignant breast lesions. Volumetric breast ultrasound radiofrequency data sets of 82 patients were acquired before and after automated transducer lifting. Lesions were annotated and strain was calculated using an in-house-developed strain algorithm. Two strain ratio types were calculated per lesion: using axial and maximal principal strain (i.e., strain in dominant direction). Forty-four lesions were detected: 9 carcinomas, 23 cysts and 12 other benign lesions. A significant difference was found between malignant (median: 1.7, range: [1.0-3.2]) and benign (1.0, [0.6-1.9]) using maximal principal strain ratios. Axial strain ratio did not reveal a significant difference between benign (0.6, [-12.7 to 4.9]) and malignant lesions (0.8, [-3.5 to 5.1]). Three-dimensional strain imaging was successfully implemented on a clinically used ABVS to obtain, visualize and analyze in vivo strain images in three dimensions. Results revealed that maximal principal strain ratios are significantly increased in malignant compared with benign lesions.

Deep learning approach for discrimination of liver lesions using nine time-phase images of contrast-enhanced ultrasound.

Contrast-enhanced ultrasound (CEUS) shows different enhancement patterns depending on the time after administration of the contrast agent. The aim of this study was to evaluate the diagnostic performance of liver nodule characterization using our proposed deep learning model with input of nine CEUS images. A total of 181 liver lesions (48 benign, 78 hepatocellular carcinoma (HCC), and 55 non-HCC malignant) were included in this prospective study. CEUS were performed using the contrast agent Sonazoid, and in addition to B-mode images before injection, image clips were stored every minute up to 10min. A deep learning model was developed by arranging three ResNet50 transfer learning models in parallel. This proposed model allowed inputting up to nine datasets of different phases of CEUS and performing image augmentation of nine images synchronously. Using the results, the correct prediction rate, sensitivity, and specificity between "benign" and "malignant" cases were analyzed for each combination of the time phase. These accuracy values were also compared with the washout score judged by a human. The proposed model showed performance superior to the referential standard model when the dataset from B-mode to the 10-min images were used (sensitivity: 93.2%, specificity: 65.3%, average correct answer rate: 60.1%). It also maintained 90.2% sensitivity and 61.2% specificity even when the dataset was limited to 2min after injection, and this accuracy was equivalent to or better than human scoring by experts. Our proposed model has the potential to identify tumor types earlier than the Kupffer phase, but at the same time, machine learning confirmed that Kupffer-phase Sonazoid images contain essential information for the classification of liver nodules.

A model for predicting lymph node metastasis of thyroid carcinoma: a multimodality convolutional neural network study.

Early preoperative evaluation of cervical lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) is critical for further surgical treatment. However, insufficient accuracy in predicting LNM status for PTC based on ultrasound images is a problem that needs to be urgently resolved. This study aimed to clarify the role of convolutional neural networks (CNNs) in predicting LNM for PTC based on multimodality ultrasound. In this study, the data of 308 patients who were clinically diagnosed with PTC and had confirmed LNM status via postoperative pathology at Beijing Tiantan Hospital, Capital Medical University, from August 2018 to April 2022 were incorporated into CNN algorithm development and evaluation. Of these patients, 80% were randomly included into the training set and 20% into the test set. The ultrasound examination of cervical LNM was performed to assess possible metastasis. Residual network 50 (Resnet50) was employed for feature extraction from the B-mode and contrast-enhanced ultrasound (CEUS) images. For each case, all of features were extracted from B-mode ultrasound images and CEUS images separately, and the ultrasound examination data of cervical LNM information were concatenated together to produce a final multimodality LNM prediction. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of the predictive model. Heatmaps were further developed for visualizing the attention region of the images of the best-working model. Of the 308 patients with PTC included in the analysis, 158 (51.3%) were diagnosed as LNM and 150 (48.7%) as non-LNM. In the test set, when a triple-modality method (i.e., B-mode image, CEUS image, and ultrasound examination of cervical LNM) was used, accuracy was maximized at 80.65% (AUC =0.831; sensitivity =80.65%; specificity =82.26%), which showed an expected increased performance over B-mode alone (accuracy =69.00%; AUC =0.720; sensitivity =70.00%; specificity =73.00%) and a dual-modality method (B-mode image plus CEUS image: accuracy =75.81%; AUC =0.742; sensitivity =74.19%; specificity =77.42%). The heatmaps of our triple-modality model demonstrated a possible focus area and revealed the model's flaws. The PTC lymph node prediction model based on the triple-modality features significantly outperformed all the other feature configurations. This deep learning model mimics the workflow of a human expert and leverages multimodal data from patients with PTC, thus further supporting clinical decision-making.

A Data-Driven Approach for Estimating Temperature Variations Based on B-mode Ultrasound Images and Changes in Backscattered Energy.

Thermal treatments that use ultrasound devices as a tool have as a key point the temperature control to be applied in a specific region of the patient's body. This kind of procedure requires caution because the wrong regulation can either limit the treatment or aggravate an existing injury. Therefore, determining the temperature in a region of interest in real-time is a subject of high interest. Although this is still an open problem, in the field of ultrasound analysis, the use of machine learning as a tool for both imaging and automated diagnostics are application trends. In this work, a data-driven approach is proposed to address the problem of estimating the temperature in regions of a B-mode ultrasound image as a supervised learning problem. The proposal consists in presenting a novel data modeling for the problem that includes information retrieved from conventional B-mode ultrasound images and a parametric image built based on changes in backscattered energy (CBE). Then, we compare the performance of classic models in the literature. The computational results presented that, in a simulated scenario, the proposed approach that a Gradient Boosting model would be able to estimate the temperature with a mean absolute error of around 0.5°C, which is acceptable in practical environments both in physiotherapic treatments and high intensity focused ultrasound (HIFU).