Ultrasonic Imaging最新文献

Breast ultrasound images play a pivotal role in assessing the nature of suspicious breast lesions, particularly in patients with dense tissue. Computerized analysis of breast ultrasound images has the potential to assist the physician in the clinical decision-making and improve subjective interpretation. We assess the performance of conventional features, deep learning features and ensemble schemes for discriminating benign versus malignant breast lesions on ultrasound images. A total of 19 individual feature sets (1 morphological, 2 first-order, 10 texture-based, and 6 CNN-based) were included in the analysis. Furthermore, four combined feature sets (Best by class; Top 3, 5, and 7) and four fusion schemes (feature concatenation, majority voting, sum and product rule) were considered to generate ensemble models. The experiments were carried out on three independent open-access datasets respectively containing 252 (154 benign, 98 malignant), 232 (109 benign, 123 malignant), and 281 (187 benign, 94 malignant) lesions. CNN-based features outperformed the other individual descriptors achieving levels of accuracy between 77.4% and 83.6%, followed by morphological features (71.6%-80.8%) and histograms of oriented gradients (71.4%-77.6%). Ensemble models further improved the accuracy to 80.2% to 87.5%. Fusion schemes based on product and sum rule were generally superior to feature concatenation and majority voting. Combining individual feature sets by ensemble schemes demonstrates advantages for discriminating benign versus malignant breast lesions on ultrasound images.

Nowadays, detection and characterization of breast pathologies is an essential issue. Quasi-static ultrasound elastography have been proposed to provide information about the mechanical properties of tissues during the patient examination. However, reconstructing tissue properties is a challenging task as it requires to solve an ill-posed inverse problem, with generally no available boundary information and solely 2D estimated displacements, whereas the problem is inherently three-dimensional. In this paper, a Virtual fields based-method is investigated to reconstruct Young's modulus maps from the knowledge of internal displacements and the force applied. The media examined are assumed to be linear elastic and isotropic, and to overcome the lack of 3D data, the plane stress conditions are considered. The developed method is assessed with plane-stress and 3D simulations, as well as phantoms and patient data. For all the media examined, the reconstructed Young's modulus maps clearly reveal regions with different stiffnesses. The stiffness contrast between regions is accurately estimated for the different plane stress simulations, but underestimated for the 3D simulations. These results can be expected as plane stress conditions are no longer satisfied in the 3D simulations. On the other hand, for all these cases, the size and the position of the different regions are correctly estimated when the region is larger than a pixel. Finally, similar comments can be made for the experimental results. More especially for the in vivo results, the inclusion-to-background Young's modulus ratio is estimated in average around 6.61 for the carcinoma and 4.57 for the fibroedenoma, which is consistent with the literature.

Breast cancer is the leading cancer threatening women's health. In recent years, deep neural networks have outperformed traditional methods in terms of both accuracy and efficiency for breast cancer classification. However, most ultrasound-based breast cancer classification methods rely on single-perspective information, which may lead to higher misdiagnosis rates. In this study, we propose a multi-view knowledge distillation vision transformer architecture (MVKD-Trans) for the classification of benign and malignant breast tumors. We utilize multi-view ultrasound images of the same tumor to capture diverse features. Additionally, we employ a shuffle module for feature fusion, extracting channel and spatial dual-attention information to improve the model's representational capability. Given the limited computational capacity of ultrasound devices, we also utilize knowledge distillation (KD) techniques to compress the multi-view network into a single-view network. The results show that the accuracy, area under the ROC curve (AUC), sensitivity, specificity, precision, and F1 score of the model are 88.15%, 91.23%, 81.41%, 90.73%, 78.29%, and 79.69%, respectively. The superior performance of our approach, compared to several existing models, highlights its potential to significantly enhance the understanding and classification of breast cancer.

Contrast-enhanced ultrasound (CEUS) shows promise in solid organ trauma by identifying areas of disrupted perfusion. In contrast, B-Flow ultrasound offers high fidelity imaging of larger vessels. We hypothesize that contrast-enhanced B-Flow (CEB-Flow) will improve accuracy of hepatic vessel injury delineation, as an adjunct tool to CEUS and future ultrasound-guided therapies. Imaging data was collected using our IACUC approved swine model for traumatic liver injury. All procedures were approved within this IACUC protocol. Sonography was performed using a Logiq E10 scanner with C1-6 probe (GE HealthCare). After ultrasound guided liver trauma, we performed open-abdomen B-Mode ultrasound, CEUS, and CEB-Flow of the injury during infusion of Definity (Lantheus Medical Imaging, N. Billerica, MA). CEUS was performed using coded harmonic imaging and CEB-Flow using a commercial package (GE Healthcare). Twelve swine were used for analysis. Three blinded interpreters were asked to identify injured liver parenchyma and lacerated vessels. Identification rates were compared using ultrasound-guided laceration images and pathology confirmation as a reference standard. Liver injury identification ranged from 88.3% to 100% on CEUS and 50% to 66.7% on CEB-Flow. Consensus identification rates in identifying parenchymal injury were not significantly different (91.7% CEUS vs. 66.7% CEB-Flow, p = .25). Lacerated vessel identification ranged from 41.7% to 58.3% for CEUS and 75.0% to 91.7% for CEB-Flow. Specifically, CEB-Flow demonstrated improved consensus in identifying lacerated vasculature (41.7% CEUS vs. 91.7% CEB-Flow, p = .041). In this swine model study, the combination of CEUS and CEB-Flow could accurately identify and localize traumatic hepatic injury. CEB-Flow may better characterize vessel injury, which in turn may direct and improve bedside management.

To evaluate the ability of fractal parameters based on ultrasonography to distinguish between hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) in patients. This retrospective study was performed to assess the performance of certain ultrasound-based parameters, including fractal dimension (FD), lacunarity (LAC), and FD combined with LAC (FL), in distinguishing HCC from ICC with liver biopsy as the gold standard, information was obtained from 204 eligible patients. Receiver operating characteristic (ROC) curve analysis was conducted, to assess the performance of these parameters in distinguishing between HCC and ICC in patients with or without CLD. The following parameters were significantly different between with and without CLD: the levels of alpha-fetoprotein, abnormal prothrombin, alanine aminotransferase, aspartic acid, total bilirubin and indirect bilirubin (p < .05). The AUC of FL in differentiating HCC from ICC was 0.983 and 0.854 in patients without or with CLD, which were significantly better than that of FD (non-CLD, 0.902 AUC; CLD, 0.647 AUC, p < .05) and LAC (non-CLD, 0.895 AUC; CLD, 0.843 AUC, p < .05). FL can better distinguish between HCC and ICC in patients with or without CLD than FD and LAC. FL may serve as a promising preoperative alternative for distinguishing between the two diseases.Clinical trials:Brief title: Exploration of noninvasive differential diagnosis of benign and malignant liver tumors.URL: https://register.clinicaltrials.govClinicalTrials.gov ID: NCT06524557.

Ultrasound imaging is used to measure the muscle-tendon junction (MTJ) to investigate the mechanical properties of the tendon and the interaction of the muscle-tendon unit in vivo. Although the MTJ can be observed clearly in the resting state, accurate tracking of the MTJ is difficult during muscle contractions due to changes in its morphology. We devised a novel method using an algorithm that extracts and tracks multiple feature points in ultrasound images to automatically measure the MTJ that moves during muscle contraction. Instead of using a single reference image, multiple feature points are used to improve the tracking performance during the deformation of the MTJ. Subsequently, we experimentally evaluated the usefulness of this method. Tests were conducted on 20 healthy participants performing isometric maximal contractions, and ultrasound echo images of the medial gastrocnemius and Achilles tendon junctions were recorded. MTJ excursion was calculated using the developed multiple feature point algorithm and two conventional methods-multi-updating template-matching and modified Lucas-Kanade (LK)-based on automatic and manual analyses. The root mean square error (RMSE) was used to compare the results. The intraclass correlation coefficient (ICC) was used to evaluate the repeatability among examiners. RMSE was 1.57 ± 0.62 for the proposed algorithm and 2.18 ± 0.89 and 1.84 ± 1.13 for the conventional methods. The Bland-Altman plot showed that the proposed method exhibited a lower 95% confidence interval than the two conventional methods. Thus, the proposed algorithm had the smallest error. Furthermore, the ICC values were 0.96, 0.40, and 0.86 for the proposed algorithm, multi-updating template-matching, and the modified LK method, respectively. When tracking an MTJ excursion that flexibly changes its shape, the use of multiple feature points provides robust results and achieves tracking that approximates the manual analysis results.

B-line artifacts in lung ultrasound, pivotal for diagnosing pulmonary conditions, warrant automated recognition to enhance diagnostic accuracy. In this paper, a lung ultrasound B-line vertical artifact identification method based on radio frequency (RF) signal was proposed. B-line regions were distinguished from non-B-line regions by inputting multiple characteristic parameters into nonlinear support vector machine (SVM). Six characteristic parameters were evaluated, including permutation entropy, information entropy, kurtosis, skewness, Nakagami shape factor, and approximate entropy. Following the evaluation that demonstrated the performance differences in parameter recognition, Principal Component Analysis (PCA) was utilized to reduce the dimensionality to a four-dimensional feature set for input into a nonlinear Support Vector Machine (SVM) for classification purposes. Four types of experiments were conducted: a sponge with dripping water model, gelatin phantoms containing either glass beads or gelatin droplets, and in vivo experiments. By employing precise feature selection and analyzing scan lines rather than full images, this approach significantly reduced the dependency on large image datasets without compromising discriminative accuracy. The method exhibited performance comparable to contemporary image-based deep learning approaches, which, while highly effective, typically necessitate extensive data for training and require expert annotation of large datasets to establish ground truth. Owing to the optimized architecture of our model, efficient sample recognition was achieved, with the capability to process between 27,000 and 33,000 scan lines per second (resulting in a frame rate exceeding 100 FPS, with 256 scan lines per frame), thus supporting real-time analysis. The results demonstrate that the accuracy of the method to classify a scan line as belonging to a B-line region was up to 88%, with sensitivity reaching up to 90%, specificity up to 87%, and an F1-score up to 89%. This approach effectively reflects the performance of scan line classification pertinent to B-line identification. Our approach reduces the reliance on large annotated datasets, thereby streamlining the preprocessing phase.

Ultrasound contrast agent is a medical reagent used for ultrasound contrast imaging. After more than 50 years of development, with the continuous deepening of research, the composition, physicochemical properties, functions and application directions of contrast agents have undergone significant changes. paper describes the generation, development stage, classification, main clinical applications and the latest technical progress of ultrasound contrast agents relatively comprehensively, reviews imaging principles, safety, tumor targeted imaging and treatment of UCA, introduces the classification of ultrasound contrast agents and their clinical applications in the whole body in detail, and compares the physical characteristics and diagnostic performance of SonoVue and Sonazoid, the two most widely used contrast agents in clinical practice. This paper reviews the types and clinical use of ultrasound contrast agents for those who may be new to the field.

To explore the image features and the diagnostic value of contrast-enhanced ultrasound (CEUS) for ductal carcinoma in situ (DCIS) of the breast. A total of 96 female patients with a solitary and histologically proven DCIS were analyzed retrospectively, and 100 female cases of invasive ductal carcinoma (IDC) lesions were used as the control group. The Breast Imaging Reporting and Data System (BI-RADS) category of breast lesions was assessed according to conventional ultrasound features. The DCIS lesions were classified into mass type and non-mass type. The CEUS characteristics of these breast lesions were retrospectively analyzed qualitatively and quantitatively. The final gold standard was biopsy or surgery with histo-pathological examination. Comparing the ultrasound images of DCIS with that of IDC, there were significant differences in echo pattern, calcification morphology, and calcification distribution (p < .05 for all). There was a significant difference between DCIS and IDC in enhancement intensity, perfusion defects, peripheral high enhancement, intratumoral vessels, and arrival time (AT) (p < .05 for all). In the logistic multivariate regression analysis, two indicators linked with DCIS were recognized: perfusion defects (p = .002) and peripheral high enhancement (p < .001). In forecasting DCIS, the logistic regression equation resulted in an AUC of 0.689, a specificity of 0.720, and a sensitivity of 0.563. CEUS showed differences in enhancement characteristics between DCIS and IDC, with perfusion defects and peripheral high enhancement being associated with DCIS.