This work presents the first application of the Thru-scan framework to a range of ultrasound images across frequency bands, from 3 MHz human abdominal scans to high frequency preclinical scans. The Thru-scan is a constrained reconstruction of the subresolved scatterers based on a power law distribution and enforced by appropriate selection of power law filters. The resulting reconstructions mitigate the traditional speckle "noise" pattern, with substantially increased resolution at high spatial frequencies. Improvements in contrast and apparent resolution are quantified using the generalized contrast-to-noise ratio (gCNR): Thru-scan increases gCNR by approximately 0.07 to 0.10 units, with p-values of less than 0.001. The Thru-scan processing steps also modify the amplitude distribution of the traditional B-scan, and across all frequency bands and anatomical targets the results are well modeled as a Burr distribution with power law exponents near 2.
Diffuse reverberation noise in ultrasound imaging arises from multiple reflections or secondary scattering of an echo, such as when a strong echo reflects multiple times between a fascial layer and the transducer. Unlike coherent reverberation artifacts, such as multiple reflections within an arterial wall that produce obvious ringdown in the image, these multiple reflections produce speckle-like artifacts that overlay and obscure anatomical targets and are difficult to distinguish from tissue speckle. This noise also degrades image reconstruction and interferes with imaging techniques that rely on displacement or time shifts in the ultrasonic echoes. This work introduces a permuted 2D convolutional neural network (2DCNN) for real-time reverberation suppression in ultrasound channel signals. This technique can be used to improve B-mode image quality or can be used as a pre-processing filter for techniques that require channel or beamsummed signals. The proposed architecture offers significant computational advantages over the previously implementations using 3D convolutional networks, enabling real-time implementation on existing hardware at 15 fps. The 2DCNN was trained on an enhanced dataset that combines Field II and Fullwave simulations, incorporating a broad range of acoustic affects, including reverberation noise, aberration, and attenuation. Validation on liver and kidney scans from 15 volunteers demonstrated improvements in image quality metrics related to the removal of diffuse reverberation noise, including increasing contrast, generalized contrast-to-noise ratio (GCNR), and lag-one coherence (LOC).
Abdominal trauma with bleeding is a leading cause of post-traumatic death, and detecting free fluid in the abdomen or hemoperitoneum can provide critical guidance for clinical management. Rapid and accurate diagnosis of abdominal bleeding using ultrasound is significant for making decisions regarding the need for surgical intervention. This study introduces a multi-task network for the segmentation and classification of ascites in ultrasound images. The network utilizes a U-Net backbone with a ResNext encoder as the basic architecture for the segmentation and classification models. The segmentation network includes a Frequency Channel Attention (FCA) attention module, which effectively broadens the range of captured information and enhances the robustness of channel representation. Furthermore, an Enhanced Channel Attention Multi Feature Fusion (EMFF) was used to extract the interdependencies between feature channels by combining high-order and low-order feature mappings, thereby improving segmentation accuracy. Lastly, a classification branch was created to classify ascites by sharing encoder features. Experiments on the collected ascites ultrasound dataset demonstrated that the proposed method achieved a segmentation Dice of 85.28% and a classification accuracy of 86.18%. It outperformed the leading multi-task SOTA method by 0.7% in Dice and 2.03% in accuracy, establishing a new benchmark for simultaneous ascites assessment. This study showed that the proposed network is valuable for the preliminary diagnosis of ascites in ultrasound and can serve as a potential auxiliary tool for clinical ascites examination in emergency situations.
Ultrasound imaging is widely used in clinical practice due to its non-invasive, real-time, and cost-effective nature. However, speckle noise often degrades image quality, obscuring fine anatomical structures and reducing diagnostic confidence. Existing denoising methods struggle to remove noise effectively while preserving critical details, limiting their clinical utility. Although recent deep learning architectures excel at capturing both local details and global structure, they remain inherently limited in handling speckle noise, as its physical characteristics are not explicitly incorporated. To address this limitation, a Physics-Regularized Self-Supervised Denoising U-Net (PR-SSD-Net) is introduced to reinforce the U-Net's capability for high-quality image restoration. The physics-based constraint guides the network to produce residual noise patterns that align with expected statistical behavior, enhancing image clarity and preserving critical structures. Comprehensive evaluations were conducted on six diverse ultrasound datasets. Significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) were observed, accompanied by reduced variability, as reflected in their standard deviations (SD). An ablation study confirmed the pivotal role of physics-guided regularization, and expert assessments demonstrated high inter-rater agreement (Fleiss), supporting the clinical relevance of the approach. These results highlight the proposed PR-SSD-Net approach as a robust, physically grounded solution for speckle noise reduction, enhancing both the reliability and clinical utility of ultrasound imaging.
This study evaluated the utility of super-resolution ultrasound contrast imaging for differentiating benign from malignant breast tumors. In this retrospective study, 60 patients underwent contrast-enhanced ultrasound acquisition before biopsy or surgery excision at The Third Affiliated Hospital of Nanjing Medical University between March and November 2025. Super-resolution contrast-enhanced ultrasound (SRUS) reconstruction and quantitative analysis were then performed from contrast-enhanced ultrasound cine loops using microbubble localization and tracking software. Using histopathology as the reference standard, patients were classified into malignant and benign groups. The discriminatory value of each parameter for benign versus malignant breast tumors was assessed. Diagnostic performance was quantified using the area under the receiver operating characteristic curve (AUC). The diagnostic performance of each SRUS-derived parameter was evaluated for differentiating benign from malignant breast tumors. On final pathology, SRUS-derived parameters showed good performance for differentiating benign from malignant breast tumors. Compared with benign lesions, malignant tumors exhibited significantly higher FD, number of branching points per area maximum curvature, mean curvature, maximum vessel velocity, mean vessel velocity, maximum diameter, mean diameter, and microvasculature density (all p < .050). Among all parameters, maximum curvature achieved the highest AUC (0.933), with 88.0% sensitivity and 80.0% specificity. Intra- and inter-operator reliability were high, with intraclass correlation coefficients >.85. SRUS-derived quantitative parameters showed diagnostic value for differentiating benign from malignant breast masses and enable clear visualization of hemodynamic alterations, suggesting potential value for preoperative malignant-risk assessment.
The intima media thickness (IMT) of the common carotid artery (CCA) is helpful for the diagnosis of atherosclerosis. The CCA ultrasound image segmentation methods can be used for the IMT measurements. However, the speckle noise and the blurred edges can reduce the accuracy of the IMT measurements. To address this issue, a preprocessing method based on non-subsampled shearlet transform (NSST) and Phase Asymmetry Metric is proposed for the CCA ultrasound images. First, the CCA ultrasound image is decomposed into the NSST domain with a low-frequency sub-band and several high-frequency sub-bands. Next, the high frequency sub-band image is despeckling using an adaptive threshold method. Then, the processed image is reconstructed through NSST. Finally, an edge enhancement method based on the phase asymmetry (PAS) metric is used for enhancing the edges in the reconstructed CCA ultrasound images. In the simulated CCA ultrasound image experiments, the CNR value of proposed method is 1.8191 dB, which is the highest among four state-of-the-art methods. In the clinical CCA ultrasound image experiments, the average CNR values of proposed method is 1.5457 ± 0.6595 (mean ± std in dB), which is the best among four advanced methods. In the real application of IMT measurements, the average absolute error of intima-media thickness measurements of proposed method is 0.0790 ± 0.0588 (mean ± std in mm), which is the lowest among four advanced methods. In conclusion, the proposed approach has improved performance in suppressing the speckle noise and enhancing the intima media complex (IMC) regions, and it is a potential method for preprocessing of the CCA ultrasound images in clinical application.
Poor spatial resolution and contrast remain major challenges in ultrafast ultrasound imaging. Null subtraction imaging (NSI) improves lateral resolution but often degrades speckle quality and contrast. Its extension, dynamic DC-biased NSI (dDC-NSI), mitigates this trade-off by introducing a dynamic DC bias; however, slight speckle suppression may still occur in homogeneous regions, leading to dark-region artifacts. In this work, a generalized null subtraction factor (gNSF) is proposed as a post-processing framework. gNSF applies multiple apodizations, followed by a mirror-flipping and symmetric summation operation, and defines a weighting factor based on the energy ratio between a bias term and a zero-mean sequence. By incorporating the dynamic DC bias, coherent echoes are enhanced while incoherent noise is suppressed. Phantom experiments show that gNSF achieves a contrast performance (gCNR close to 1) comparable to GCF and dDC-NSI, and superior to DAS and NSI. In addition, gNSF improves CR and sSNR by 20% and 21% compared with dDC-NSI, indicating reduced speckle over-suppression and a better balance between contrast and speckle preservation.
Synthetic aperture transmit sequences can be used in medical ultrasound to increase image resolution without sacrificing frame rate. However, beamforming the large amount of collected data from the sequence is computationally costly for traditional delay-and-sum (DAS) beamforming, and the sequence has low SNR and limited penetration depth. These problems are especially apparent for deeper targets, when more data is collected and the low SNR results in poor visibility. Transmitting a chirp coded excitation can greatly improve the SNR and penetration depth, at the cost of some computational efficiency during beamforming, although frequency-domain beamforming can reduce the computations required for image reconstruction. This paper presents the chirp scaling algorithm (CSA), a frequency-domain beamformer originally developed for radar, that avoids the computational costs of interpolation and can account inherently for chirp excitation pulse compression for chirp transmit sequences. First, theory is presented to derive the beamforming steps for ultrasound multistatic synthetic aperture data. Then, comparative imaging with DAS and the range-Doppler algorithm (RDA, a related frequency-domain beamformer) are shown via Field II simulations and in vitro with a CIRS phantom imaged using a Verasonics Vantage 256 system. The results demonstrate similar lateral sidelobe levels (averaging) within 6 dB and resolution within 0.1 mm for the three beamformers for all sources of data. However, CSA has consistently faster median baseline runtime (at least 2.6 times faster compared to DAS), and a significant 6.5-fold runtime decrease from via precomputation, which reduces its runtime below even that of RDA. Together, our results demonstrate the feasibility for CSA to generate high-quality ultrasound images, particularly for resource-constrained devices.
Ultrafast Doppler imaging provides critical insights into tissue perfusion but traditionally requires long acquisitions and computationally expensive filtering, such as singular value decomposition (SVD). In this work, we propose SONIC, a real-time, deep learning framework that reconstructs high-quality vascular images from limited Doppler frames using a teacher-student paradigm. The student model, designed for fast inference, is trained under the guidance of a teacher network pretrained on full-length sequences. To further enhance performance under sparse data conditions, we introduce a dual-loss strategy combining deep supervision and knowledge distillation. The deep supervision loss aids in learning clutter-suppressed intermediate features, while the knowledge distillation loss transfers high-level spatiotemporal knowledge from the teacher to the student model. Experiments on in vivo datasets demonstrate that SONIC achieves superior performance compared to SVD filtering when operating on fewer frames. Our ablation study confirms that the combination of deep supervision and knowledge distillation provides synergistic benefits, significantly improving segmentation accuracy and signal fidelity. Furthermore, SONIC achieves real-time inference speeds on GPU hardware, supporting its integration into time-constrained clinical workflows. Finally, we demonstrate the applicability of SONIC to free-hand 3D microvascular imaging by stacking high-quality 2D Doppler slices acquired during handheld scanning. This capability highlights the framework's potential for extending microvascular ultrasound imaging into portable and low-data clinical environments.
To develop a logistic prediction model based on multimodal ultrasound to enhance the diagnostic performance for non-microcalcified BI-RADS 4 breast lesions. We retrospectively analyzed ultrasound data from 334 patients with BI-RADS 4 breast lesions, incorporating 10 multimodal features. Model 1 was constructed using the entire cohort, while Model 2 focused on a subset of 225 non-microcalcified cases, with features selected via Lasso regularization and performance evaluated through 10-fold cross-validation. Model 1 identified lesion size >2 cm (OR = 1.65, p = .041), microcalcification (OR = 3.62, p < .001), and Emax (OR = 1.02, p = .001) as independent predictors, with an AUC of 0.85 (95%CI: 0.78-0.91). Model 2 selected lesion size, Adler grade, and Emax as significant features, achieving an AUC of 0.88 (95%CI: 0.81-0.92), with a 10-fold cross-validated accuracy of 0.81, Kappa of .57, and Hosmer-Lemeshow test (χ2 = 5.23, p = .850) for calibration. The multimodal ultrasound-based logistic model significantly improves the diagnosis of non-microcalcified BI-RADS 4 breast lesions (AUC = 0.88), with lesion size, Adler grade, and Emax as key predictors, offering a cost-effective tool to reduce unnecessary biopsies in clinical practice.
Tissue harmonic imaging has superior spatial and contrast resolution compared to conventional linear imaging but suffers from low signal-to-noise ratio (SNR). While phase-encoded excitation can be used to improve the harmonic SNR, distortion of the harmonic signal may compromise the accuracy of bipolar code sequence, leading to axial artifacts in tissue harmonic imaging after decoding. In this study, phase-encoded tissue harmonic imaging with multiplane wave (MW) transmission is compared among coding matrices (i.e., Hadamard, S-sequence and orthogonal Golay) as well as different design of bit waveform. Both simulations and experiments are conducted to validate our analysis on the coding schemes and bit waveforms. Results demonstrate that Hadamard and Golay are affected by phase distortion of harmonic waveform due to their bipolar nature. However, Hadamard can avoid these axial artifacts by sacrificing the first plane wave (PW) angle in the angular compounding. In contrast, the unipolar S-sequence is not affected by phase distortion but suffers from the reduced SNR gain compared to Hadamard. Regarding the bit waveform, the rectangular waveform provides the higher SNR but induces severe spectral distortion of the transmit phase due to its discontinuities in the envelope. This distortion becomes prominent when combined with Golay, leading to severe axial artifacts and a noticeable reduction in image contrast. It is concluded that the Hadamard with rectangular waveform and selective compounding is the optimal configuration for phase-encoded MW tissue harmonic imaging due to its higher SNR than the S-sequence and higher image quality than the orthogonal Golay.
Coherent plane wave compounding (CPWC) is a widely used technique for ultrafast ultrasound imaging. However, the unfocused beams limit its image quality. The null subtraction imaging (NSI) has been proposed to improve its image quality. However, the image's contrast, resolution, and speckle quality depend on the variable DC offset parameter. Since NSI employs a fixed offset in a single image, a trade-off arises among these three aspects. To address this issue, a region-adaptive NSI (raNSI) is proposed in this work. In raNSI, a modified generalized coherence factor (GCF) is used to identify different regions within an image. raNSI then applies different offset to points in the identified different regions. The neighborhood statistics-based cleaning (NSBC) algorithm is applied to eliminate unexpected outliers in the selected offsets. The effectiveness of raNSI is demonstrated through simulated, experimental and in vivo datasets. The phantom experimental results show that comparing with NSI with an offset of 1, the contrast ratio (CR), speckle signal-to-noise ratio (sSNR) and contrast-to-noise ratio (gCNR) of the proposed raNSI are improved by 57.94 dB, 0.19 and 0.0327, respectively, while passing the Kolmogorov-Smirnov test-confirming that its speckle pattern remains intact. Furthermore, the lateral resolution is enhanced by 6.9%. It indicates that raNSI can achieve high resolution and high contrast while preserving the speckle pattern well. In addition, raNSI has shown the potential to reduce the number of required plane waves by a factor of five.
Ultrafast imaging with coherent compounding has revolutionized medical diagnostics by achieving high frame rates and facilitating advanced applications such as Doppler imaging and shear wave elastography. Among ultrafast techniques, diverging wave imaging (DWI) offers distinct advantages over plane wave imaging (PWI), including wider field-of-view coverage. In ultrafast imaging, either using PWI or DWI, transmit apodization cannot be set in the conventional way by applying different voltages to each transmit element as the beam is formed synthetically during coherent compounding. For DWI, the beam is formed by coherent compounding for a set of spherical waves generated from virtual sources (VSs) placed behind the probe, where applying weights in the compound phase is possible. While several studies have addressed this challenge for PWI, the optimization of those weights for DWI remains unexplored. In our earlier work, we introduced a closed-form approach, under suitable hypotheses, that maps transmit apodization weights from synthetic aperture imaging (SAI) to weights applied during coherent compounding for DWI, and we refer to that set of weights as a compound mask. The approach works for both linear and convex geometries with different arrangements of virtual sources, f-numbers, and apodization windows. Here, we present the real-time implementation of this approach on a Verasonics scanner, validating its efficacy across three VSs configurations (linear, curvilinear, and tilted distributions). Experimental results demonstrate that the compound mask improves the quality of B-mode images with all distributions of VSs for linear and convex arrays, all without compromising real-time performance.
Polycystic Ovary Syndrome (PCOS) is a leading cause of female infertility and is associated with various health complications, including preterm abortions, anovulation, and ovarian cancer. It affects approximately 5% to 10% of women in their reproductive years. PCOS diagnosis often relies on ultrasound imaging to assess ovarian follicle size, count and arrangement. Accurately diagnosing PCOS in clinical practice poses significant challenges for radiologists due to the variability in follicle sizes and their complex relationships with surrounding blood vessels and tissues. This process is labor-intensive, prone to errors, and time-consuming. To address these challenges, numerous research efforts have focused on automating the detection of PCOS-affected ovaries. While advancements have been made, further improvements are needed to enhance diagnostic accuracy. Convolutional Neural Networks (CNNs) have shown promise in PCOS classification, but models relying solely on global features may achieve suboptimal results, as regional features are often overlooked. This paper introduces a feature fusion model named PCOSFusionNet designed to improve the accuracy of PCOS classification. The proposed system combines handcrafted features extracted using the Histogram of Oriented Gradients (HOG) descriptor with global features obtained from the VGG19 deep learning model. Additionally, Contrast Limited Adaptive Histogram Equalization (CLAHE) is applied during preprocessing to enhance image quality and improve feature extraction. The watershed method is employed for segmentation before classification. By integrating deep features with handcrafted features, the system achieves superior classification performance across multiple metrics, including accuracy, precision, recall, and F1-score, using five-fold cross-validation. The performance of the proposed PCOSFusionNet model was evaluated on two publicly available datasets. The first dataset (Dataset_1) contains 3856 ultrasound images and the second dataset (Dataset_2) comprises 12,680 ultrasound images. On these datasets, PCOSFusionNet achieved accuracies of 98.49% and 98.30%, respectively, surpassing existing state-of-the-art methods and demonstrating its effectiveness in PCOS diagnosis.
Kidney stone disease is a prevalent urological disorder that can result in severe pain, obstruction, and long-term complications if not detected and managed promptly. Traditional diagnostic approaches, particularly those relying on manual assessment of ultrasound images, often suffer from limitations such as subjective interpretation, dependency on radiologist expertise, and challenges in identifying small or complex stones. These constraints can lead to diagnostic delays and inconsistencies, especially in time-sensitive or resource-limited clinical settings. Therefore, the need for an intelligent, automated solution that enhances diagnostic accuracy and efficiency is more critical than ever. To address these issues, we propose a novel deep learning-based model called the Kronecker Self-Organizing Map Forward Harmonic Network (KSOMFHNet) for kidney stone classification using ultrasound imagery. The model begins with an image preprocessing phase, where a double bilateral filter is applied to effectively denoise the ultrasound images. Following this, the Deep Recursive Residual Network (DRRN) is employed to segment the kidney region accurately. Feature extraction is then performed using a combination of Binary Robust Independent Elementary Features (BRIEF), shape-based features, and Gray Level Co-Occurrence Matrix (GLCM) texture descriptors. These features are then used for classification via the KSOMFHNet, a hybrid architecture integrating the Deep Kronecker Neural Network (DKN) and Self-Organizing Map Network (SOMNet). This fusion enhances the model's learning capacity and spatial representation abilities. Experimental results demonstrate that KSOMFHNet achieves high performance, with an accuracy of 91.984%, a True Positive Rate (TPR) of 90.543%, a True Negative Rate (TNR) of 92.248%, a precision of 90.179%, and an F1-score of 90.360% for training data is 90%, highlighting its potential for clinical deployment.
Passive stretching is commonly used in exercise rehabilitation, and the aim of this study was to quantitatively characterize the effect of passive stretching force on the anisotropic viscoelastic properties of bovine muscle tissues in vitro, so as to clarify the effects of different stretching modes and intensities on the muscles. Graded stretching forces (0-30 N) were applied along the fiber direction of three bovine tenderloin samples (N = 3). Multi-frequency shear waves (100-300 Hz) were generated using an external mechanical vibration, and the resulting shear wave velocity dispersion was measured in directions parallel and perpendicular to the fibers. To ensure measurement stability, three acquisitions were performed for each experimental condition and the results were averaged for analysis (n = 3). The dispersion data were fitted to the Kelvin-Voigt model to estimate the shear elastic modulus and shear viscous coefficient. With applied stretching force, both the shear elastic modulus and shear viscous coefficient exhibited significant, non-linear increases in both measurement directions. This enhancement was particularly pronounced in the parallel fiber direction: as stretching force increased from 0 to 30N, the shear elastic modulus increased from 4.67±0.33kPa to 10.07±0.59kPa (an increase of 116%±15%), and the shear viscous coefficient increased from 5.28±0.38Pa·s to 10.82±0.47Pa·s (an increase of 105%±12%), thereby amplifying the tissue's mechanical anisotropy. A two-way repeated measures ANOVA confirmed that the effects of stretching force, measurement direction, and their interaction were all highly significant (p<0.005). Passive stretching is a primary modulator of the anisotropic viscoelasticity in muscle tissue. This study systematically reveals the direction-specific, force-dependent evolutionary patterns of both elastic and viscous parameters, providing a critical experimental foundation for advancing the understanding of passive muscle mechanics and for the validation and refinement of biomechanical constitutive models. Furthermore, in the field of sports rehabilitation, these findings can inform the development of more scientific muscle rehabilitation protocols.
In medical imaging, segmentation is a critical task for analysis and diagnosis. Deep learning-based segmentation has been actively studied and has shown remarkable performance. Building high-accuracy segmentation models requires a large amount of high-quality labeled data, but the cost of collecting such data is extremely high in medical imaging. In ultrasound imaging, the differences in image features depending on the equipment are significantly greater compared to other medical imaging modalities. Consequently, models need to be trained for each specific device, which entails substantial costs and time, leading to various practical challenges. To address these challenges, we propose a robust and accurate segmentation network that can operate independently of the ultrasound equipment. We integrated the Deep Frequency Filtering (DFF) module into a U-Net-based model. The proposed model retains the U-Net's encoder-decoder structure but applies frequency filtering within the latent space of each encoder layer, enabling adaptive selection of frequency components for breast tumor detection. Moreover, batch normalization was replaced with instance normalization to remove stylish features. We evaluated the model using three public datasets acquired from different scanners, achieving superior performance on unseen testing datasets compared to existing models. Notably, when tested on the unseen BUS-BRA dataset, DAUS-Net achieved a Dice score of 0.76, compared to 0.61 by the conventional U-Net. This improvement is attributed to the synergy between the DFF module and instance normalization. Our results demonstrate that the proposed model consistently detects and segments breast tumors, highlighting its potential for generalized clinical segmentation task. The source code for implementing DAUS-Net is publicly available at https://github.com/shlee8638/DAUS-Net.
In medical ultrasound imaging, achieving high-quality reconstructed images while avoiding a huge computational burden is an important challenge. The Null subtraction imaging (NSI) algorithm results in a high-resolution reconstructed image. However, this method is not successful in recovering the background speckle information. In this paper, a novel algorithm, known as NSI-based generalized coherence factor (GCF)-along with delay-and-sum (DAS), which is abbreviated as NSG-DAS, is developed to overcome this limitation. In the proposed method, by using a hybrid technique, the desired resolution and effective noise suppression of the NSI algorithm, as well as the background speckle information of the conventional DAS beamformer are recovered simultaneously. More precisely, by using the GCF method, a new weighing factor is introduced that enhances the coherent regions of the image and suppresses the off-axis signals. Evaluations prove the favorable performance of the suggested technique; in particular, by using the proposed NSG-DAS method, a resolution comparable to the NSI algorithm is achieved for the geabr0 dataset, which is improved by about 42% compared to DAS. Also, the contrast evaluation parameter of the suggested technique is comparable to the DAS algorithm and is improved by about 63% compared to the NSI method. This indicates the ability of the suggested technique to improve either resolution or contrast simultaneously.
Ultrasound array probes can transmit diverging wavefronts from virtual source (VS) locations behind the array to obtain ultrafast compounded images with a broad field-of-view, but determining a practical set of diverging-wave VS locations is non-trivial, given the infinite half-plane of possibilities. In this work, we propose VS placement at a constant radial distance r from the array origin, and we compare this to a previous (and less direct) method of VS placement at a constant opening angle β relative to the ends of the array. Each method was implemented in Field II with a 64 element, 2.7 MHz phased-array geometry to simulate point-spread functions (PSFs) at regular 10 mm intervals over the field-of-view; the lateral and axial resolution, peak side-to-main lobe amplitude ratio (PSMR), and maximum amplitude of each PSF were measured. Each method was also implemented on a research scanner with a corresponding probe to acquire images of a tissue-mimicking phantom for comparison. Results from both methods in simulation and phantom experiments showed that the increase in PSF lateral resolution with range was consistent (≈38 µm/mm) and the mean axial resolution agreed within 0.01 mm; mean differences in PSMR and amplitude were <5% and <4%, respectively. Generalized contrast-to-noise ratio (gCNR) was highest for the constant-β 2 method, with differences between methods within ±1%. These results indicate that, relative to the constant-β method, comparable image quality can be achieved with a streamlined constant- r method of VS placement for diverging-wave ultrafast imaging.
Speckle noise in ultrasound imaging remains a major obstacle to accurate clinical interpretation and reliable anatomical segmentation. Existing enhancement methods often compromise anatomical details while reducing noise, particularly under challenging imaging conditions. To address this, we introduce an innovative hybrid framework combining the Smart Adaptive Framework for Image Enhancement (SAFIE), a denoising engine based on adaptive fractional convolutions and gradient-based refinement, with a segmentation strategy integrating superpixel-based hypergraph modeling and neural ordinary differential equations. This framework enables effective noise suppression and precise segmentation of anatomical structures by capturing both spatial coherence and temporal feature dynamics. The enhanced images reveal improved visibility of anatomical structures and boundaries. Qualitative evaluation by four experienced radiologists confirmed this improvement, with strong inter-observer agreement measured by Fleiss' kappa, highlighting the robustness and clinical relevance of the approach. Quantitative results corroborate these observations, demonstrating performance substantially superior to several state-of-the-art methods. Ablation studies further indicate that each component contributes significantly to overall improvement. These findings suggest that the proposed framework enhances segmentation reliability and provides robust support for diagnostic interpretation in ultrasound imaging.
