Ultrasound Imaging Technology Research Articles

Graph regularized least squares regression for automated breast ultrasound imaging

Breast cancer, recognized as one of the most pervasive malignancies affecting females, manifests a perpetual escalation in its worldwide morbidity. Timely screening offers patients interventions that are not only more expeditious but also more efficacious. ABUS, as an automated breast ultrasound imaging technology, has the advantages of high resolution, reproducible results, and strong objectivity. However, manual interpretation of ABUS images can be highly tedious and laborious when handling huge amounts of data from images, may leading to the risk of missed diagnosis. In practical clinical diagnosis, the incorporation of Computer-Aided Diagnosis (CAD) systems emerges as a more favorable option. In consideration of the holistic factors encompassing model construction efficiency, training cost and overall performance, we provide a unique subspace clustering approach known as Graph regularized Least Squares Regression (GLSR) in this paper. Firstly, we encode the data's intrinsic geometry into the framework of least squares regression to respect local and global correlation structures at the same time. Secondly, we construct a nearest neighbor graph to model the smooth structure of the representation, which may lead to a more accurate representation. Finally, a nonnegative constraint is introduced into our framework so that the representation obtained by GLSR has clearer physical meaning. We provide an optimization approach for solving such a framework based on iterative updates of four blocks. Extensive experimental results indicate the effectiveness of the proposed method compared with state-of-the-art approaches on real-world breast cancer images and other biological data.

Interobserver Reproducibility of Ultrasound Attenuation Imaging Technology in Liver Fat Quantification.

This study aims to investigate the interobserver variability in the quantitative assessment of liver fat content using ultrasound attenuation imaging technology (USAT). This prospective, single-center study included 96 adult patients who were either diagnosed with or suspected of having metabolic dysfunction-associated steatotic liver disease. Independent observers, blinded to each other's assessments, evaluated hepatic steatosis visually and through USAT measurements. Separate measurements were taken at five intercostal and subcostal sites, and the median values of these measurements were recorded. The correlation between USAT measurements and visual steatosis grades was examined using Spearman's correlation test. Intraclass correlation coefficient (ICC) and Bland-Altman analysis were used to evaluate the interobserver variability of USAT measurements. Interobserver agreement for USAT measurements was excellent for the intercostal examination and good for the subcostal examination (p < 0.001). Body mass index did not significantly affect the level of interobserver agreement. Interobserver variability in Bland-Altman plots of USAT measurements was within the 95% limits of agreement. USAT measurements correlated very strongly with the visual degree of hepatic steatosis, both intercostal and subcostal (p < 0.001). USAT measurements were also significantly different between different visual degrees of hepatic steatosis (p < 0.001). In the assessment of hepatic steatosis, USAT measurements obtained from the intercostal space showed excellent agreement in terms of interobserver reproducibility.

Two-Stage Multimodal Method for Predicting Intramuscular Fat in Pigs

Intramuscular fat (IMF) content significantly influences pork tenderness, flavor, and juiciness. Maintaining an optimal IMF range not only enhances nutritional value but also improves the taste of pork products. However, traditional IMF measurement methods are often invasive and time-consuming. Ultrasound imaging technology offers a non-destructive solution capable of predicting IMF content and assessing backfat thickness as well as longissimus dorsi muscle area size. A two-stage multimodal network model was developed in this study. First, using B-mode ultrasound images, we employed the UNetPlus segmentation network to accurately delineate the longissimus dorsi muscle area. Subsequently, we integrated data on backfat thickness and longissimus dorsi muscle area to create a multimodal input for IMF content prediction using our model. The results indicate that UNetPlus achieves a 94.17% mean Intersection over Union (mIoU) for precise longissimus dorsi muscle area segmentation. The multimodal network achieves an R2 of 0.9503 for IMF content prediction, with Spearman and Pearson correlation coefficients of 0.9683 and 0.9756, respectively, all within a compact model size of 4.96 MB. This study underscores the efficacy of combining segmented longissimus dorsi muscle images with data on backfat thickness and muscle area in a two-stage multimodal approach for predicting IMF content.

Application of small animal ultrasound imaging technology for identification of polycystic ovary syndrome in a mouse model

Background and AimsPolycystic ovary syndrome (PCOS) is a hormonal disorder common among women of reproductive age, characterized by irregular menstrual periods, elevated levels of androgens, and polycystic ovaries, leading to various symptoms and complications such as infertility, metabolic issues, and increased risk of diabetes and heart disease. This study aimed to compare traditional histological methods and ultrasound imaging for consistency in identifying PCOS in a mouse model. The shortest time to construct the PCOS model using letrozole was determined. MethodsFemale C57/BL mice were randomly divided into three groups: Group A received normal saline and a regular diet; Group B received 1 mg/kg/day of letrozole with a regular diet; and Group C received 1 mg/kg/day of letrozole with a high-fat diet. All mice were administered letrozole by intragastric gavage daily for five weeks. The traditional identification method included measuring body weight, examining vaginal smears, monitoring the estrous cycle, measuring serum androgen levels, and performing H&E staining of ovarian tissues. The PCOS model was evaluated using ultrasound imaging to identify and monitor follicles. The significance of the difference between the traditional identification method and the ultrasonic method was calculated using the nonparametric McNemar test, and consistency between the two methods was assessed with the kappa-coefficient test. On this basis, the ultrasound imaging technology was used to monitor the model-making process for 2, 3 and 4 weeks, and to monitor the parameters of the ovary and follicles to judge the shortest time that gavage letrozole caused the appearance of vesicular follicles in the mouse ovary. ResultsThe traditional identification method showed no PCOS phenotype in group A mice, while groups B and C showed multiple ovarian cystic follicles, indicating successful model induction. The ultrasound imaging results were consistent with the traditional method, showing no PCOS in group A and multiple cystic follicles in groups B and C. The McNemar test revealed no significant difference between the traditional and ultrasonic identification methods. The kappa-coefficient test assessed consistency, yielding a value of 0.903, indicating strong agreement between the methods. The ovarian area, diameter, and the number and diameter of cystic follicles were not significantly changed at two weeks in the letrozole group compared with the control group. At three weeks, there were significant increases in the number and in the diameter of vesicular follicles compared with control cells. At four weeks, the number and diameter, the maximum cross-sectional area and diameter of the ovary were significantly increased compared with the control group. ConclusionsThe ultrasound and traditional methods provide consistent results for identifying PCOS in a mouse model. Construction of the PCOS model by letrozole gavage takes at least three weeks.

A low-voltage-driven MEMS ultrasonic phased-array transducer for fast 3D volumetric imaging

Wearable ultrasound imaging technology has become an emerging modality for the continuous monitoring of deep-tissue physiology, providing crucial health and disease information. Fast volumetric imaging that can provide a full spatiotemporal view of intrinsic 3D targets is desirable for interpreting internal organ dynamics. However, existing 1D ultrasound transducer arrays provide 2D images, making it challenging to overcome the trade-off between the temporal resolution and volumetric coverage. In addition, the high driving voltage limits their implementation in wearable settings. With the use of microelectromechanical system (MEMS) technology, we report an ultrasonic phased-array transducer, i.e., a 2D piezoelectric micromachined ultrasound transducer (pMUT) array, which is driven by a low voltage and is chip-compatible for fast 3D volumetric imaging. By grouping multiple pMUT cells into one single drive channel/element, we propose an innovative cell–element–array design and operation of a pMUT array that can be used to quantitatively characterize the key coupling effects between each pMUT cell, allowing 3D imaging with 5-V actuation. The pMUT array demonstrates fast volumetric imaging covering a range of 40 mm × 40 mm × 70 mm in wire phantom and vascular phantom experiments, achieving a high temporal frame rate of 11 kHz. The proposed solution offers a full volumetric view of deep-tissue disorders in a fast manner, paving the way for long-term wearable imaging technology for various organs in deep tissues.

The use of non-invasive tomographic imaging to monitor lung condition

The development of ultrasound tomography (UST) aimed to significantly enhance the precision and safety of non-invasive UST imaging, particularly for studying crystallization processes in biological tissues. The initiative sought to address the limitations of previous versions by incorporating advanced technological upgrades and providing a more user-friendly interface. The revised system comprises eight four-channel measurement cards interconnected via a high-speed FD CAN bus capable of 8 MBPS data transfer. Each card features a dedicated square wave generator, band-pass filters tailored to specific ultrasonic transducer frequencies, and a sophisticated signal envelope processing unit. The core processing unit is built around a 32-bit STM32G474RE microcontroller, ensuring robust data handling and image reconstruction capabilities. The UST device presented demonstrates improved image clarity and reduced noise interference. The measurement card redesign has achieved a sampling rate of 4 MBPS per channel and includes a two-stage amplification for dynamic range management. Upgraded power components, comprehensive shielding, and the integration of advanced analog switches have led to an enhanced signal-to-noise ratio, pivotal for high-resolution imaging. The advancements presented in the UST device mark a noteworthy progression in ultrasound imaging technology, extending beyond traditional applications. High-speed data collection, precise signal processing, and user-centered design have all come together to make a system that can image crystallization processes more accurately and accurately over and over again.

Diversity of solitonic wave structures to the M‐truncated dynamical system in ultrasound imaging

The utilization of ultrasound imaging has become extensively prevalent and well‐established in clinical practice. The fundamental technologies that serve as the foundation for various applications in the field include transducers, beam shaping, pulse compression, tissue harmonic imaging, contrast agents, methodologies for quantifying blood flow and tissue motion, and three‐dimensional imaging. This article focuses on the examination of ultrasonic propagation, which involves the transmission of mechanical vibrations within the molecules or particles of a material. It quantifies the velocity of sound propagation in the medium of air. The third‐order nonlinear M‐fractional Westervelt model has been used as a governing model in the imaging process for securing the different wave structures. The recently developed computational methods have been applied in this study. The different wave structures are secured in various forms of solitary wave solutions including bright, dark, and combo solitons. In the domains of medical imaging and therapy, the investigation of sound wave propagation and high‐amplitude phenomena is facilitated by the utilization of wave structures. The effectiveness of these solutions extends to acoustic cavitation, acoustic levitation, underwater acoustics, and facilitating the process of ultrasonic propagation in tissue. Ultrasound imaging technologies currently find application in the medical field, enabling the visualization and examination of internal human tissue. This technology exhibits a wide array of applications in the fields of industry and medicine. A representation of the graphs is produced using the appropriate parametric values. The results suggest that the chosen approaches exhibit effectiveness, viability, and adaptability when implemented in complex systems in various fields, with particular emphasis on ultrasonic imaging.

Mesothelin-Mediated Paclitaxel Phase-Shifted Nanodelivery System for Molecular Ultrasound Imaging and Targeted Therapy Potential in Ovarian Cancer

Background: Ovarian cancer presents a substantial risk to women's health and lives, with early detection and treatment proving challenging. Targeted nanodelivery systems are viewed as a promising approach to enhance the effectiveness of ovarian cancer treatment and ultrasonic imaging outcomes. Objective: A phase-shifted nanodelivery system (NPs) loaded with paclitaxel (PTX) and further conjugated with avidin (Ab) was studied, with the goal of investigating the effects of targeted nanodelivery strategies on the in vitro therapeutic efficacy and ultrasonic imaging of ovarian cancer. This study provides a foundation for future in vivo treatments utilizing this approach. Methods: PTX-NPs were prepared using the single water-in-oil (O/W) emulsion solvent evaporation method, with avidin coupling achieved through biotin-avidin affinity. The encapsulation efficiency and release profile of PTX were analyzed using UV spectrophotometry. The phase-shift properties of the Ab-PTX-NPs delivery system were evaluated, and the targeting efficiency, cytotoxicity against SKOV3 cells, and in vivo biosafety of various nanodelivery systems were assessed. Results: The prepared nanodelivery system showed a stable and uniform structure with a good particle size distribution and exhibited favorable release characteristics under ultrasound exposure. In vitro experiments revealed that the nanodelivery system displayed excellent targeting and cytotoxic effects against SKOV3 cells, indicating the potential of the Ab-PTX-NPs delivery system for targeted ovarian cancer therapy. In vivo safety studies demonstrated the high biosafety of the prepared nanodelivery system. Conclusion: A novel nanodelivery system was developed, and the experimental results obtained provide a solid experimental basis for further research on in vivo ultrasound molecular imaging technology, offering new insights into targeted ultrasound molecular imaging and the treatment of ovarian cancer.

Effects of Platelet-Rich Plasma Combined with Physical Therapy on IL-1β, TGF-β1, and MMP-3 in Patients with Knee Osteoarthritis.

The occurrence of osteoarthritis in the knee joint is regulated by a complex network, and there is currently no specific therapeutic drug available. Functional exercises and treatments targeting inflammatory factors have shown the potential to alleviate knee osteoarthritis to some extent. Therefore, the aim of this study was to assess the intra-articular injection (IAI) of autologous platelet-rich plasma (PRP) combined with physical therapy (PT) in treating knee osteoarthritis. A total of 128 patients with knee osteoarthritis were included in the study, including 64 males and 64 females. A total of 128 patients were divided into sodium hyaluronate group (HA group), PRP group, PRP + PT group, and PT group, with 32 cases in each group. Visual analog scale (VAS), Western Ontario and McMaster University Osteoarthritis Index (WOMAC), and Japanese Orthopaedic Association (JOA) were employed to evaluate the recovery of patients from pain and osteoarthritis. Color Doppler ultrasound imaging technology was utilized to assess joint effusion, synovial membrane thickness, and articular cartilage thickness in patients with knee osteoarthritis. Enzyme-linked immunosorbent assay (ELISA) was employed to detect the levels of interleukin-1β (IL-1β), transforming growth factor-β1 (TGF-β1), and matrix metallopeptidase 3 (MMP-3) in the synovial fluid. Compared to the HA group, the PT group, PRP group, and PRP combined with PT (PRP + PT) group all showed reduced VAS and WOMAC scores, increased JOA scores, decreased joint effusion, synovial membrane thickness, and articular cartilage thickness in the knee joint. Additionally, levels of IL-1β and MMP-3 in the synovial fluid decreased, while TGF-β1 levels increased (P < 0.05). Compared with the PT group, the VAS and WOMAC scores of the knee joint in the PRP group decreased, JOA scores increased, joint effusion, synovial thickness, and articular cartilage thickness decreased, but there was no statistically significant difference (P > 0.05), and the PRP + PT group showed decreased VAS and WOMAC scores, increased JOA scores, reduced joint effusion, synovial membrane thickness, and articular cartilage thickness in the knee joint. Moreover, levels of IL-1β and MMP-3 in the synovial fluid decreased, while TGF-β1 levels increased (P < 0.05). No severe adverse reactions were observed in any of the four groups, but the pain rate in the PRP + TP group was significantly lower than PT group, PRP group, and PRP + PT group (P < 0.05). The efficacy of intra-articular injection of PRP combined with exercise therapy in the treatment of knee osteoarthritis is superior to that of single interventions such as simple interventions of HA, PRP injection, and PT. Furthermore, intra-articular injection of PRP combined with exercise therapy demonstrates enhanced effectiveness in improving the inflammatory levels associated with knee osteoarthritis and facilitating the rehabilitation process.

Imaging performance of portable and conventional ultrasound imaging technologies for ophthalmic applications.

The aim of this study was to evaluate the imaging capabilities of Butterfly iQ with conventional ophthalmic (piezoelectric) ultrasound (COU) for ophthalmic imaging. Custom phantom molds were designed and imaged with Butterfly iQ and COU to compare spatial resolution capabilities. To evaluate the clinical imaging performance of Butterfly iQ and COU, a survey containing pathological conditions from human subjects, imaged with both Butterfly iQ and COU probes, was given to three retina specialists and graded on image detail, resolution, quality, and diagnostic confidence on a ten-point Likert scale. Kruskal-Wallis analysis was performed for survey responses. Butterfly iQ and COU had comparable capabilities for imaging small axial and lateral phantom features (down to 0.1 mm) of high and low acoustic reflectivity. One of three retina specialists demonstrated a statistically significant preference for COU related to resolution, detail, and diagnostic confidence, but the remaining graders showed no significant preference for Butterfly iQ or COU across all sample images presented. The emergence of portable ultrasound probes offers an affordable alternative to COU technologies with comparable qualitative imaging resolution down to 0.1 mm. These findings suggest the value to further study the use of portable ultrasound systems and their utility in routine eye care.

Ultrasonic surface acoustic wave elastography: A review of basic theories, technical developments, and medical applications.

Physiological and pathological changes in tissues often cause changes in tissue mechanical properties, making tissue elastography an effective modality in medical imaging. Among the existing elastography methods, ultrasound elastography is of great interest due to the inherent advantages of ultrasound imaging technology, such as low cost, portability, safety, and wide availability. However, most current ultrasound elastography methods are based on the bulk shear wave; they can image deep tissues but cannot image superficial tissues. To address this challenge, ultrasonic elastography methods based on surface acoustic waves have been proposed. In this paper, we present a comprehensive review of ultrasound-based surface acoustic wave elastography techniques, including their theoretical foundations, technical implementations, and existing medical applications. The goal is to provide a concise summary of the state-of-the-art of this field, hoping to offer a reliable reference for the further development of these techniques and foster the expansion of their medical applications.

Real-time 3D ultrasound imaging with a clip-on device attached to common 1D array transducers

Performing 3D ultrasound imaging at a real-time volume rate (e.g., &amp;gt;20 Hz) is a challenging task. While 2D array transducers remain the most practical approach for real-time 3D imaging, the large number of transducer elements (e.g., several thousand) that are necessary to cover an effective 3D field-of-view impose a fundamental constraint on imaging speed. Although solutions such as multiplexing and specialized transducers, including sparse arrays and row-column-addressing arrays, have been developed to address this limitation, they inevitably compromise imaging quality (e.g., SNR, resolution) in favor of speed. Coupled with the high equipment cost of 2D arrays, these compromises hinder the widespread adoption of 3D ultrasound imaging technologies in clinical settings. In this presentation, we introduce an innovative transducer clip-on device comprising a water-immersible, fast-tilting electromechanical acoustic reflector and a redirecting reflector to enable real-time 3D ultrasound imaging using common 1D array transducers. We will first introduce the principles underlying our novel technique, followed by validation studies incorporating simulation and experimental data. We will also demonstrate the feasibility of using the clip-on device to achieve a high 3D imaging volume rate that is suitable for advanced imaging modes such as shear wave elastography, blood flow imaging, and super-resolution ultrasound localization microscopy.

A Clinical Retrospective Study on the Qualitative Value of Multimodal Ultrasonography for ACR-TIRADS 4 Thyroid Nodules Ranging from 1 cm to 1.5 cm.

This study explored the clinical value and application of ultrasound contrast imaging technology in the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) TR4 benign and malignant thyroid nodules. We retrospectively analyzed data from the medical records of 40 patients who met the inclusion criteria between January 2020 and December 2023. Each patient was evaluated using the ACR TI-RADS classification and contrast-enhanced ultrasound (CEUS). The agreement between pathological outcomes and ultrasound indicators and the diagnostic value and significance of each parameter were assessed. The diameters did not differ between benign and malignant nodules (P = 0.324). Ring enhancement was closely associated with benign thyroid nodules, with a negative predictive value of 100%. Homogeneous enhancement and enhancement intensity showed good diagnostic value for pathological results, with an area under the curve (AUC) > 0.8. This parameter showed a high diagnostic value for serial and parallel combinations of homogeneous enhancement and enhancement intensity, with a sensitivity of 77.8% and specificity of 85.7% for the serial combination and 100% and 71.4%, respectively. for the parallel combination. Among ACR TI-RADS TR4 nodules, diameter 1.0-1.5 cm was not significantly correlated with a benign or malignant nature. Nodules featuring ring enhancement with ring-enhancing features should be considered benign. Similarly, nodules showing no, homogeneous, or high enhancement with clear borders on CEUS imaging may be benign. However, nodules with uneven low enhancement or unclear borders may be malignant. Therefore, uneven and low enhancement on CEUS imaging may have a high diagnostic value for malignant nodules. Moreover, the combination of these features may have even higher specificity.

On the dynamics of soliton solutions for the nonlinear fractional dynamical system: Application in ultrasound imaging

This article examines the third-order non-linear fractional Westervelt model by using a newly developed integration tool termed the new extended direct algebraic approach. The different wave structures to the considered model are secured in various forms, including bright, dark, and combo solitons. The application of wave structures is advantageous in the examination of sound wave propagation and high amplitude phenomena in the fields of medical imaging and therapy. These solutions are effective in facilitating ultrasound propagation in tissue, underwater acoustics, acoustic cavitation, acoustic levitation, and other related applications. The internal tissue of human beings can be visualized and studied through the use of ultrasound imaging technologies in the field of medicine. This technology possesses numerous uses in both industrial and medicinal sectors. There has been a growing interest in fractional nonlinear partial differential equations due to their ability to describe various complex occurrences and exhibit more dynamic architectures of localized wave solutions. On employing accurate parameter values, multiple graphical representations are generated to provide the visual depiction of the acquired results. The results of this study indicate that the chosen methodology effectively improves nonlinear dynamical processes. The findings indicate that the selected methodology demonstrates efficacy, feasibility, and versatility when applied to intricate systems across several domains, with a special emphasis on ultrasonic imaging. The findings indicate that the system exhibits a potentially significant abundance of soliton structures.

Interfacial self-healing polymer electrolytes for long-cycle solid-state lithium-sulfur batteries

Coupling high-capacity cathode and Li-anode with solid-state electrolyte has been demonstrated as an effective strategy for increasing the energy densities and safety of rechargeable batteries. However, the limited ion conductivity, the large interfacial resistance, and unconstrained Li-dendrite growth hinder the application of solid-state Li-metal batteries. Here, a poly(ether-urethane)-based solid-state polymer electrolyte with self-healing capability is designed to reduce the interfacial resistance and provides a high-performance solid-state Li-metal battery. With its dynamic covalent disulfide bonds and hydrogen bonds, the proposed solid-state polymer electrolyte exhibits excellent interfacial self-healing ability and maintains good interfacial contact. Full cells are assembled with the two integrated electrodes/electrolytes. As a result, the Li||Li symmetric cells exhibit stable long-term cycling for more than 6000 h, and the solid-state Li-S battery shows a prolonged cycling life of 700 cycles at 0.3 C. The use of ultrasound imaging technology shows that the interfacial contact of the integrated structure is much better than those of traditional laminated structure. This work provides an interesting interfacial dual-integrated strategy for designing high-performance solid-state Li-metal batteries.

Differential Diagnostic Value of Two-dimensional Ultrasound Combined with Three-dimensional Ultrasound Imaging Technology for Cesarean Scar Pregnancy.

Cesarean scar pregnancy (CSP) refers to the phenomenon in which a fertilized egg implants and develops in the scar of the uterus in a woman with a history of cesarean section. The study aimed to explore the differential diagnostic value of two-dimensional ultrasound (2D US) combined with three-dimensional ultrasound (3D US) for CSP. Clinical data of 89 patients with CSP admitted to our hospital from January 2022 to January 2023 were retrospectively analyzed. Of them, 65 patients met the inclusion criteria. Patients underwent 2D US, 3D US, and combined 2D and 3D US imaging. Using the clinical pathological diagnosis as the "gold standard", the differential diagnostic value of 2D US, 3D US, and 2D US combined with 3D US for CSP was compared. The detection rate of CSP using a combined 2D US and 3D US was 98.46%, which was higher than 84.62% and 89.23% achieved with 2D US and 3D US alone, respectively (P<0.05). The pathological results showed that among 65 patients, CSP type I accounted for 24.62%, type II accounted for 55.38%, and type III accounted for 20.00%. The coincidence rate of 2D US combined with 3D US was 98.46%, which was higher than that of 2D US (83.08%) and 3D US 89.23%) alone (P<0.05). The accuracy, specificity, and sensitivity of 2D US combined with 3D US in diagnosing CSP were higher compared to the two methods alone (P<0.05). The combination of 2D US and 3D US can accurately detect and classify CSP, further improving diagnostic efficiency.

A novel image-to-knowledge inference approach for automatically diagnosing tumors

Breast cancer is one of the most vulnerable malignant tumors for women in the world, which seriously threatens women’s life and health. Breast ultrasound imaging technology is widely used in clinical breast cancer detection due to its advantages of high safety, real-time and convenience. However, breast ultrasound diagnosis relies on experienced diagnostic medical sonographers to read the images and requires high-quality imaging of ultrasound images. On the one hand, reading the breast ultrasound images manually by the doctors is time-consuming and burdensome. On the other hand, cultivating an ultrasonographer is a costly process. The development of computer-aided diagnostic systems in recent years is a solution to these problems to some extent. More and more computer-aided diagnostic systems for breast ultrasound are being used in clinical practice, and their sensitivity and accuracy are higher than those of less senior ultrasonographers, which reduces the workload of physicians and improves diagnostic efficiency to a certain extent. Existing assisted diagnosis systems mainly use texture information such as LBP statistical histograms or deep features extracted from deep networks as the basis for diagnosis, which is not in line with the diagnosis mode of physicians and does not employ medical knowledge for diagnosis, making it difficult to make trade-offs in terms of interpretability and diagnostic performance. In this work, a new interpretable reasoning paradigm from images to knowledge is proposed. Based on this paradigm, interpretable features are firstly perceived as the medical knowledge from the images. The perceived features may be inaccurately identified, then the interpretable features are further amended to obtain high-quality knowledge. Finally, the knowledge is constructed into a knowledge graph and the diagnosis results are obtained by interpretable knowledge inference on the knowledge graph. The experimental results demonstrate that our approach achieves a trade-off in interpretability and diagnostic performance compared to the mainstream diagnostic systems based on deep learning methods and those based on traditional machine learning methods.

Research on the 3D Reverse Time Migration Technique for Internal Defects Imaging and Sensor Settings of Pressure Pipelines.

Although pressure pipelines serve as a secure and energy-efficient means of transporting oil, gas, and chemicals, they are susceptible to fatigue cracks over extended periods of cyclic loading due to the challenging operational conditions. Their quality and efficiency directly affect the safe operation of the project. Therefore, a thorough and precise characterization approach towards pressure pipelines can proactively mitigate safety risks and yield substantial economic and societal benefits. At present, the current mainstream 2D ultrasound imaging technology faces challenges in fully visualizing the internal defects and topography of pressure pipelines. Reverse time migration (RTM), widely employed in geophysical exploration, has the capability to visualize intricate geological structures. In this paper, we introduced the RTM into the realm of ultrasonic non-destructive testing, and proposed a 3D ultrasonic RTM imaging method for internal defects and sensor settings of pressure pipelines. To accurately simulate the extrapolation of wave field in 3D pressure pipelines, we set the absorbing boundary and double free boundary in cylindrical coordinates. Subsequently, using the 3D ultrasonic RTM approach, we attained higher-precision 3D imaging of internal defects in the pressure pipelines through suppressing imaging artifacts. By comparing and analyzing the imaging results of different sensor settings, the design of the observation system is optimized to provide a basis for the imaging and interpretation of actual data. Both simulations and actual field data demonstrate that our approach delivers top-notch 3D imaging of pipeline defects (with an imaging range accuracy up to 97.85%). This method takes into consideration the complexities of multiple scattering and mode conversions occurring at the base of the defects as well as the optimal sensor settings.

MASK CLASSIFICATION SEGMENTATION METHOD BASED ON GROUPED CONVOLUTION AND SPATIAL PYRAMIDAL CONVOLUTION MODEL FOR THYROID CANCER IDENTIFICATION

Ultrasound plays different roles in the whole process of thyroid cancer management. With the advancement of ultrasound imaging technology and diagnostic level, it is gradually becoming an irreplaceable role in the diagnosis and treatment of thyroid cancer. However, the diagnosis of thyroid cancer by means of sonographic features is subjective and highly dependent on the operator’s experience and knowledge. To avoid unnecessary puncture biopsies, alleviate anxiety and improve diagnostic efficiency, in this paper, we utilize a purely convolutional model with a pyramid structure strategy to extract sonographic features at different scales. Combined with a per-pixel classification segmentation method, which is different from the previous mainstream, it is used for the intelligent recognition of thyroid cancer. Finally, the experimental results show that our radiologists achieve better performance than five mainstream segmentation methods in four metrics (Sensitivity, Jarccard, Dice, ASD) on the thyroid cancer dataset. It provides the possibility to help radiologists to overcome diagnostic subjectivity and obtain accurate, reproducible and more objective diagnostic results.

Chiral Two-Dimensional Hybrid Organic-Inorganic Perovskites for Piezoelectric Ultrasound Detection.

Hybrid organic-inorganic perovskites (HOIPs) have exhibited striking application potential in piezoelectric energy harvesting and sensing due to their high piezoelectricity, light weight, and solution processability. However, to date, the application of piezoelectric HOIPs in ultrasound detection has not yet been explored. Here, we report the synthesis of a pair of chiral two-dimensional piezoelectric HOIPs, R-(4-bromo-2-butylammonium)2PbBr4 and S-(4-bromo-2-butylammonium)2PbBr4 [R-(BrBA)2PbBr4 and S-(BrBA)2PbBr4], which show low mechanical strength and significant piezoelectric strain coefficients that are advantageous for mechanoelectrical energy conversion. Benefiting from these virtues, the R-(BrBA)2PbBr4@PBAT and S-(BrBA)2PbBr4@PBAT [PBAT = poly(butyleneadipate-co-terephthalate)] composite films show prominent underwater ultrasound detection performance with a transmission effectivity of 12.0% using a 10.0 MHz probe, comparable with that of a polyvinylidene fluoride (PVDF) device fabricated in the same conditions. Density functional theory calculations reveal that R-(BrBA)2PbBr4 and S-(BrBA)2PbBr4 have a beneficial acoustic impedance (5.07-6.76 MRayl) compatible with that of water (1.5 MRayl), which is responsible for the facile ultrasound-induced electricity generation. These encouraging results open up new possibilities for applying piezoelectric HOIPs in underwater ultrasound detection and imaging technologies.