Ultrasonic Imaging最新文献

筛选
英文 中文
Development and Evaluation of a Transformer-Based Multi-Scale Feature Model for the Classification of Benign and Malignant Breast Lesions in Ultrasound Image. 基于变压器的乳腺超声图像良恶性病灶多尺度特征模型的建立与评价。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-09 DOI: 10.1177/01617346261501087
Jiaqi Zhu, Guoxin Huang, Mingming Yuan, Zhe Zhang, Chunjin Xiong, Weiyu Pu
{"title":"Development and Evaluation of a Transformer-Based Multi-Scale Feature Model for the Classification of Benign and Malignant Breast Lesions in Ultrasound Image.","authors":"Jiaqi Zhu, Guoxin Huang, Mingming Yuan, Zhe Zhang, Chunjin Xiong, Weiyu Pu","doi":"10.1177/01617346261501087","DOIUrl":"https://doi.org/10.1177/01617346261501087","url":null,"abstract":"<p><p>This study introduces MSF-US, a novel deep learning framework integrating multi-scale feature fusion and attention mechanisms. It aims to enhance early breast cancer detection and improve diagnostic accuracy in ultrasound images, particularly addressing the challenges of capturing global and local features in dense breast tissue. The MSF-US model combines hierarchical multi-scale feature extraction with attention mechanisms to selectively focus on diagnostically relevant regions. The framework was rigorously validated on a multi-center dataset of breast ultrasound images. Its performance was compared against state-of-the-art models, such as ResNet-50, Vision Transformer (ViT), and Swin Transformer, evaluating accuracy, sensitivity, specificity, and area under the curve (AUC). In 5-fold cross-validation, MSF-US yielded an average accuracy of 0.9057, sensitivity of 0.9075, and AUC of 0.9212 with high net clinical benefit. On the independent C3 test set, it surpassed 8 SOTA baselines with a peak accuracy of 0.9406, <i>F</i>1 score of 0.9483, and AUC of 0.9391. Evaluation on 3 diverse public cohorts (BUSI, BUS-BRA, and BrEaST) confirmed excellent cross-center generalizability, achieving AUCs up to 0.9519. Ablation analysis validated that the synergy of multi-scale feature fusion and attention mechanisms significantly boosted diagnostic precision over single-scale baselines. MSF-US delivers state-of-the-art performance in breast ultrasound imaging, offering a highly reliable tool for early breast cancer detection. Its innovative design successfully addresses the limitations of existing methods, presenting significant clinical potential to improve diagnostic accuracy and patient outcomes.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"1617346261501087"},"PeriodicalIF":1.7,"publicationDate":"2026-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149381461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ultrasonic Characterization of the Layered Structure of Human Scalp. 人体头皮层状结构的超声表征。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-09 DOI: 10.1177/01617346261498895
Ann M Viano, Catherine N Prabish, Blake C Lawler, Thomas H Conroy, Brayden S Pallera, Cecille Labuda, Brent K Hoffmeister
{"title":"Ultrasonic Characterization of the Layered Structure of Human Scalp.","authors":"Ann M Viano, Catherine N Prabish, Blake C Lawler, Thomas H Conroy, Brayden S Pallera, Cecille Labuda, Brent K Hoffmeister","doi":"10.1177/01617346261498895","DOIUrl":"https://doi.org/10.1177/01617346261498895","url":null,"abstract":"<p><p>Interest in transcranial ultrasound has motivated numerous ultrasonic studies of the skull and brain; however, the ultrasonic properties of the scalp are relatively unknown. The goal of this study was to ultrasonically characterize the transmural tissue structure of the scalp. Sixty-four formalin-fixed specimens were prepared from 4 human donors and scanned in a water tank with a 25 MHz transducer to create parametric images of the speed of sound (SOS), frequency slope of attenuation (FSA), integrated attenuation coefficient (IAC), integrated backscatter coefficient (IBC), and apparent integrated backscatter (AIB). Parametric images revealed a layered structure of which the 3 thickest (>1 mm) layers were analyzed: dermal, subcutaneous and subgaleal. Measured values for these 3 layers, respectively, were SOS = 1560 ± 29 m/s, 1510 ± 19 m/s, and 1520 ± 21 m/s; FSA = 2.75 ± 0.77 dB/cm/MHz, 2.51 ± 0.60 dB/cm/MHz, and 0.83 ± 0.47 dB/cm/MHz; IAC = 56 ± 11 dB/cm, 29.7 ± 6.1 dB/cm, and 20.3 ± 7.1 dB/cm; IBC = 0.14 ± 0.13 cm<sup>-1</sup>sr<sup>-1</sup>, 0.072 ± 0.056 cm<sup>-1</sup>sr<sup>-1</sup> and 0.07 ± 0.15 cm<sup>-1</sup>sr<sup>-1</sup>; AIB = -45.1 ± 3.1 dB, -46.9 ± 3.2 dB and -50.2 ± 5.0 dB. All 5 measured parameters were significantly different between the dermal and subcutaneous layers and between the dermal and subgaleal layers. AIB, IAC, and FSA were significantly different between the subcutaneous and subgaleal tissue layers. These findings demonstrate that the ultrasonic properties of the scalp vary by layer.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"1617346261498895"},"PeriodicalIF":1.7,"publicationDate":"2026-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149381462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Uncertainty-Guided Steering Vector Test-Time Adaptation for the Classification of Breast Ultrasound Images. 乳腺超声图像分类的不确定性导向导向矢量测试时间自适应。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-08 DOI: 10.1177/01617346261495108
Woo Sik Cho, Jun Hyeong Park, Seonhwa Kim, Jaesung Heo
{"title":"Uncertainty-Guided Steering Vector Test-Time Adaptation for the Classification of Breast Ultrasound Images.","authors":"Woo Sik Cho, Jun Hyeong Park, Seonhwa Kim, Jaesung Heo","doi":"10.1177/01617346261495108","DOIUrl":"https://doi.org/10.1177/01617346261495108","url":null,"abstract":"<p><p>Deep learning models for breast ultrasound classification frequently suffer from performance degradation due to domain shifts caused by differences in imaging equipment, acquisition protocols, and preprocessing across institutions. Although test-time adaptation (TTA) has been proposed to mitigate this problem, conventional gradient-based methods may be unstable in medical imaging settings and can even degrade performance under severe target-domain shifts. We propose Uncertainty-guided Steering Vector Test-Time Adaptation (USV-TTA), a gradient-optimization-free TTA method that performs feature correction at test time without updating model parameters. USV-TTA uses frozen source batch-normalization statistics to estimate target-sample uncertainty and derive steering vectors that represent the direction of domain shift, then corrects high-uncertainty samples by suppressing projections along this direction. USV-TTA was evaluated on 4 external breast ultrasound datasets comprising 6267 images included in the binary benign/malignant evaluation. On the class-imbalanced GDPH dataset, USV-TTA achieved the highest AUROC of 0.813, outperforming the source model and preventing the degradation observed with TENT (0.711). On the heterogeneous AJMC dataset, which included images acquired from 11 ultrasound systems, USV-TTA also achieved the highest AUROC of 0.773. On BrEaST and BUS-BRA, USV-TTA maintained competitive discrimination performance, although DLTTA achieved the highest AUROC on BrEaST and SAR achieved the highest AUROC on BUS-BRA. Across target datasets, USV-TTA reduced expected calibration error in the most challenging domains without incurring the instability observed in several gradient-based TTA methods. These findings suggest that effective and stable test-time adaptation for breast ultrasound classification can be achieved without gradient-based optimization, supporting safer deployment under domain shift.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"1617346261495108"},"PeriodicalIF":1.7,"publicationDate":"2026-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149381463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ultrasound Microvascular Imaging Using Deep Knowledge Distillation. 基于深度知识蒸馏的超声微血管成像。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-01 Epub Date: 2026-05-04 DOI: 10.1177/01617346261437268
Seonho Kim, Chunsu Park, Yubin Cho, MinWoo Kim
{"title":"Ultrasound Microvascular Imaging Using Deep Knowledge Distillation.","authors":"Seonho Kim, Chunsu Park, Yubin Cho, MinWoo Kim","doi":"10.1177/01617346261437268","DOIUrl":"10.1177/01617346261437268","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"436-448"},"PeriodicalIF":1.7,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimization of Ultrasound Phase-Encoded Multiplane Wave Tissue Harmonic Imaging. 超声相位编码多平面波组织谐波成像的优化。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-01 Epub Date: 2026-03-30 DOI: 10.1177/01617346261436047
Che-Chou Shen, Ching-Che Chiu, You-Lin Chu
{"title":"Optimization of Ultrasound Phase-Encoded Multiplane Wave Tissue Harmonic Imaging.","authors":"Che-Chou Shen, Ching-Che Chiu, You-Lin Chu","doi":"10.1177/01617346261436047","DOIUrl":"10.1177/01617346261436047","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"414-424"},"PeriodicalIF":1.7,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147582119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimizing Diagnosis of Non-Microcalcified BI-RADS 4 Breast Lesions Using Multimodal Ultrasound Logistic Regression. 多模态超声Logistic回归对非微钙化BI-RADS 4型乳腺病变的优化诊断
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-01 Epub Date: 2026-04-07 DOI: 10.1177/01617346261434982
Yuqing He, Shuai Guo, Zizheng Wu, Qingzhuang Gao, Hui Li, Shanbing Gao
{"title":"Optimizing Diagnosis of Non-Microcalcified BI-RADS 4 Breast Lesions Using Multimodal Ultrasound Logistic Regression.","authors":"Yuqing He, Shuai Guo, Zizheng Wu, Qingzhuang Gao, Hui Li, Shanbing Gao","doi":"10.1177/01617346261434982","DOIUrl":"10.1177/01617346261434982","url":null,"abstract":"<p><p>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 (<i>OR</i> = 1.65, <i>p</i> = .041), microcalcification (<i>OR</i> = 3.62, <i>p</i> < .001), and <i>E</i>max (<i>OR</i> = 1.02, <i>p</i> = .001) as independent predictors, with an AUC of 0.85 (95%<i>CI</i>: 0.78-0.91). Model 2 selected lesion size, Adler grade, and <i>E</i>max as significant features, achieving an AUC of 0.88 (95%<i>CI</i>: 0.81-0.92), with a 10-fold cross-validated accuracy of 0.81, Kappa of .57, and Hosmer-Lemeshow test (<i>χ</i><sup>2</sup> = 5.23, <i>p</i> = .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 <i>E</i>max as key predictors, offering a cost-effective tool to reduce unnecessary biopsies in clinical practice.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"425-435"},"PeriodicalIF":1.7,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147628822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Region-Adaptive Null Subtraction Imaging Using Generalized Coherence Factor for Coherent Plane Wave Compounding. 基于广义相干因子的相干平面波合成区域自适应零差成像。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-01 Epub Date: 2026-03-03 DOI: 10.1177/01617346261421141
Yijun Xu, Yaoting Yue, Hao Wang, Wenting Gu, Boyi Li, Lingxiao Liu, Xin Liu
{"title":"Region-Adaptive Null Subtraction Imaging Using Generalized Coherence Factor for Coherent Plane Wave Compounding.","authors":"Yijun Xu, Yaoting Yue, Hao Wang, Wenting Gu, Boyi Li, Lingxiao Liu, Xin Liu","doi":"10.1177/01617346261421141","DOIUrl":"10.1177/01617346261421141","url":null,"abstract":"<p><p>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.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"399-413"},"PeriodicalIF":1.7,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147349464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Fourier Beamforming of Ultrasound Signals From Chirp Transmits Using the Chirp Scaling Algorithm. 利用啁啾缩放算法对啁啾传输的超声信号进行傅立叶波束形成。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-11-01 Epub Date: 2026-05-06 DOI: 10.1177/01617346261441787
Louise Zhuang, Scott Schoen, Jeremy Dahl, Marko Jakovljevic
{"title":"Fourier Beamforming of Ultrasound Signals From Chirp Transmits Using the Chirp Scaling Algorithm.","authors":"Louise Zhuang, Scott Schoen, Jeremy Dahl, Marko Jakovljevic","doi":"10.1177/01617346261441787","DOIUrl":"10.1177/01617346261441787","url":null,"abstract":"<p><p>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 <i>in vitro</i> 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.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"449-470"},"PeriodicalIF":1.7,"publicationDate":"2026-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147845069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Ultrasonic Nonlinear Contrast-Enhanced Imaging Using Chirp-Coded Excitation and Volterra Filtering. 利用啁啾编码激励和Volterra滤波的超声非线性对比度增强成像。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-10-27 DOI: 10.1177/01617346261489714
Ruchika Dhawan, Vishwas Trivedi, Halak Shukla, Karla P Mercado-Shekhar, Kenneth B Bader, Himanshu Shekhar
{"title":"Ultrasonic Nonlinear Contrast-Enhanced Imaging Using Chirp-Coded Excitation and Volterra Filtering.","authors":"Ruchika Dhawan, Vishwas Trivedi, Halak Shukla, Karla P Mercado-Shekhar, Kenneth B Bader, Himanshu Shekhar","doi":"10.1177/01617346261489714","DOIUrl":"10.1177/01617346261489714","url":null,"abstract":"<p><p>Contrast-enhanced ultrasound imaging relies on nonlinear microbubble signatures for improved visualization of perfused regions. This study aims to enhance the detection of ultrasound contrast agent perfused regions by integrating chirp-coded excitation with nonlinear signal processing. In vitro experiments were conducted in a flow phantom and ex ovo in a chicken embryo using the commercial contrast agent SonoVue. Data were acquired across a range of agent concentrations, excitation pressures, and imaging depths. Radio frequency data were processed using fundamental and subharmonic matched filtering, followed by beamforming, singular value decomposition (SVD)-based clutter suppression, and cubic Volterra filtering. Imaging performance was quantified using contrast-to-tissue ratio (CTR) and axial width measurements. The combined approach of subharmonic matched filtering, SVD, and cubic Volterra filtering resulted in substantial improvements in CTR, with gains of up to 50 dB compared to SVD-enhanced subharmonic imaging across experimental conditions. Improvements were maintained at increased imaging depths, demonstrating robustness to attenuation. Experiments in the chicken embryo model showed an enhanced visualization of perfused structures. The integration of chirp-coded subharmonic excitation with SVD and Volterra filtering improves ultrasound contrast agent imaging performance. Significance: The proposed framework offers potential for advancing contrast-enhanced ultrasound imaging, including for deep targets and low signal-to-noise conditions.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"1617346261489714"},"PeriodicalIF":1.7,"publicationDate":"2026-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149289565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
MTL-LymphNet: A Lightweight Multi-Task Learning Framework for Simultaneous Lymph Node Segmentation and Metastasis Classification in Thyroid Cancer Ultrasound. mtl -淋巴网:一个轻量级的多任务学习框架,用于甲状腺癌超声同时淋巴结分割和转移分类。
IF 1.7 4区 医学
Ultrasonic Imaging Pub Date : 2026-10-18 DOI: 10.1177/01617346261488317
Muhammad Thahiruddin, Imam Wahyudi, Alfie Nuril Mustofa
{"title":"MTL-LymphNet: A Lightweight Multi-Task Learning Framework for Simultaneous Lymph Node Segmentation and Metastasis Classification in Thyroid Cancer Ultrasound.","authors":"Muhammad Thahiruddin, Imam Wahyudi, Alfie Nuril Mustofa","doi":"10.1177/01617346261488317","DOIUrl":"https://doi.org/10.1177/01617346261488317","url":null,"abstract":"<p><p>Ultrasound assessment of cervical lymph node metastasis in papillary thyroid carcinoma is crucial but suffers from inter-observer variability. Existing deep learning solutions typically use separate single-task pipelines, resulting in parameter redundancy. We propose MTL-LymphNet, a lightweight, backbone-agnostic multi-task learning framework that simultaneously segments lymph nodes and classifies metastasis within a single forward pass, evaluated across 3 backbones and 4 loss weighting strategies. On 338 images from 2 independent clinical centers, MTL-LymphNet achieved an internal cross-validation Dice coefficient of 0.891 ± 0.022 and AUC of 0.948 ± 0.027. Bidirectional external validation revealed substantial domain shift, with cross-center Dice of 0.865 and 0.779, and AUC of 0.733 and 0.830. The multi-task configuration offered a favorable efficiency-performance trade-off (∆Dice = <math><mrow><mi>Δ</mi></mrow></math>, <math><mrow><mo>-</mo><mn>0</mn><mo>.</mo><mn>014</mn></mrow></math>, P < .0001) for 40% fewer parameters than separate models. No backbone or weighting strategy consistently dominated, and calibration degraded substantially under domain shift (ECE: 0.049 internally vs 0.178-0.304 externally), requiring center-specific recalibration before clinical use. To our knowledge, this is the first MTL framework for cervical lymph node analysis with bidirectional multi-center validation and systematic ablation. With a compact size of 22.6 to 29.1 MB and CPU inference of 81 to 131 ms, MTL-LymphNet demonstrates technical feasibility as a CAD tool warranting prospective validation.</p>","PeriodicalId":49401,"journal":{"name":"Ultrasonic Imaging","volume":" ","pages":"1617346261488317"},"PeriodicalIF":1.7,"publicationDate":"2026-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149221034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书