Ultrasound Diagnosis System Research Articles

Progress in the Application of Portable Ultrasound Combined with Artificial Intelligence in Pre-Hospital Emergency and Disaster Sites

With the miniaturization of ultrasound and the development of artificial intelligence, its application in disaster scenes and pre-hospital emergency care has become more and more common. This study summarizes the literature on portable ultrasound in pre-hospital emergency and disaster scene treatment in the past decade and reviews the development and application of portable ultrasound. Portable ultrasound diagnostic equipment can be used to diagnose abdominal bleeding, limb fracture, hemopneumothorax, pericardial effusion, etc., based on which trauma can be diagnosed pre-hospital and provide guiding suggestions for the next triage and rescue; in early rescue, portable ultrasound can guide emergency operations, such as tracheal intubation, pericardial cavity puncture, and thoracic and abdominal puncture as well as improve the accuracy and timeliness of operation techniques. In addition, with the development of artificial intelligence (AI), AI-assisted diagnosis can improve the diagnosis level of ultrasound at disaster sites. The portable ultrasound diagnosis system equipped with an AI robotic arm can maximize the pre-screening classification and fast and concise diagnosis and treatment of batch casualties, thus providing a reliable basis for batch casualty classification and evacuation at disaster accident sites.

Endoscopic ultrasound diagnosis system based on deep learning in images capture and segmentation training of solid pancreatic masses.

Early detection of solid pancreatic masses through contrast-enhanced harmonic endoscopic ultrasound (CH-EUS) is important. But CH-EUS is difficult to learn. To design a deep learning-based CH-EUS diagnosis system (CH-EUS MASTER) for real-time capture and segmentation of solid pancreatic masses and to verify its value in the training of pancreatic mass identification under endoscopic ultrasound (EUS). We designed a real-time capture and segmentation model for solid pancreatic masses and then collected 4530 EUS images of pancreatic masses retrospectively, used for training and testing of this model at a ratio of 8:2. The model is loaded into the EUS host computer to establish the CH-EUS MASTER system. A crossover trial was then conducted to evaluate the model's value in EUS trainee training by successfully conducting two groups of EUS trainees in model learning and trainer-guided training. The intersection over union (IoU) and the time to find the lesion were used to evaluate the model performance metrics, and the Mann-Whitney test was used to compare the IoU and the time to find the lesion in different groups of subjects. Paired t-test was used to compare the effects before and after training. When α≤0.05, it is considered to have a significant statistical difference. The model test showed that the model successfully captured and segmented the pancreatic solid mass region in 906 EUS images. The real-time capture and segmentation model had a Dice coefficient of 0.763, a recall rate of 0.941, a precision rate of 0.642, and an accuracy of 0.842 (when the threshold is set to 0.5), and the median IoU of all cases was 0.731. For the AI training effect, the averageIoU of eight trainees improved from 0.80 to 0.87 (95% CI, 0.032-0.096; p=0.002). The average time for identifying lesions inthepancreaticbodyandtail improved from 22.75 to 17.98 s (95% CI, 3.664-5.886; p < 0.01). The average time for identifying lesions inthe pancreatic head and uncinate processimproved from 34.21 to 25.92 s (95% CI, 7.661-8.913; p < 0.01). CH-EUS MASTER can provide an effect equivalent to trainer guidance in training pancreatic solid mass identification and segmentation under EUS.

Independent association of blood cadmium with subclinical lower extremity atherosclerosis: An observational study based on dose-response analysis

BackgroundAtherosclerosis is an increasingly public health issue globally. Previous studies have showed a causal link between heavy metal exposure and atherosclerosis. However, the association of cadmium concentration with subclinical lower extremity atherosclerosis (SLEA) remains unclear. AimsTo investigate the association of blood cadmium with SLEA and its extent, and further analyze the potential dose-response relationship. MethodsBlood cadmium concentration was measured using inductively coupled plasma mass spectrometry. SLEA and its extent were assessed by ultrasound diagnosis system. Multivariate models were applied to evaluate the association of blood cadmium with SLEA and its extent. Restricted cubic splines were performed to explore the potential dose-response relationship. ResultsThis observational study consisted of 1664 participants from cardiovascular outpatient, with an average age of 62.4 years and 1218 (73.2%) men. When blood cadmium was included as a categorical variable in multivariate models, logistic regression analysis showed that high quartile in blood cadmium was an independent risk factor of SLEA (OR = 2.704, 95%CI 1.866–3.919). After log-transformed for SLEA extent parameters, linear regression analysis indicated that high quartile in blood cadmium was significantly associated with higher Crouse score (GMR = 1.21, 95%CI 1.15–1.28), plaque maximum thickness (GMR = 1.13, 95%CI 1.09–1.18) and diseased vessel count (GMR = 1.14, 95%CI 1.10–1.19), respectively. When blood cadmium was used as a continuous variable in restricted cubic splines, the dose-response relationship presented a positive progression in SLEA (P = 0.302), plaque maximum thickness (P = 0.145) and diseased vessel count (P = 0.055) apparently that did not deviate from linearity. ConclusionsBlood cadmium exhibited an independent association with SLEA, and this dose-response relationship was progressive without significant departure from linearity.

Effects of maslinic acid on cardiac function in ischemia–reperfusion injury rats

Maslinic acid (MA), a pentacyclic triterpenoid, has been reported to exert broad pharmacological properties. However, it is still unclear whether MA exhibits protective effects against ischemia/reperfusion (I/R) injury. Herein, we...

A novel evolutionary method for spine detection in ultrasound samples of spina bifida cases

Background and objectives:Spina bifida is a fetal spine defect observed during pregnancy. The defect is caused by unfinished closure of the embryonic neural column. Common diagnosis of the defect is still based on manual examination which aims to detect any deformation on spinal axis. This study proposes a novel evolutionary method for locating spinal axis on sonograms of spina bifida pathology.Methods: The method involves a meta-heuristic evolutionary approach, where the sonogram is automatically divided into columns and bone regions belonging to the spine are classified. Accordingly, a specific genetic algorithm is utilized which constructs a set of candidate spine axes. Fitness of the candidate axes is measured by a proposed problem-specific fitness function. A combination of conventional genetic operators and a novel energy minimization approach is applied to each population in order to explore the problem search space.Results: Results show that presented algorithm is generally able to distinguish the spinal bones from others even in the presence of severe morphological defects.Conclusion: It is observed that the presented approach is promising and in most samples the spines identified by the proposed algorithm closely match those drawn by the experts. A computer assisted ultrasound diagnosis system specialized for spina bifida cases does not exist yet, but an algorithm to identify the spine, such as the one presented in this work, is the first natural step towards a diagnosis system. In the future, we intend to improve the algorithm by improving the segmentation stage and further optimizing the various stages of the genetic algorithm.

A performance, power, and energy analysis of ultrasound B‐mode imaging on a GPU with VFS

SummaryBecause of the power and energy constraints in modern computing systems, it is important to find a balance between performance and power/energy consumption to produce not only energy efficient portable devices but also reliable computing systems. In this paper, we present an analytical investigation of the performance and power/energy consumption of a well‐known medical application, “ultrasound B‐mode imaging,” which is implemented on modern commercial graphics processing units (GPUs). With this target application, we investigate the impact of GPU hardware features on performance, power, and energy by experimentally applying voltage and frequency scaling on various GPU devices. Based on our results, we mathematically build a performance prediction model to show the analytical relationship between the architectural features of those GPUs and the application performance. Our results show that the performance prediction model has errors of less than 8.71% and that there exists an energy‐optimal point in the design space spanned by the core clock frequency. We expect that our model can help engineers to design an ultrasound diagnosis system with the most suitable GPU that satisfies cost, performance, and power/energy constraints.

Spatial–temporal three-dimensional ultrasound plane-by-plane active cavitation mapping for high-intensity focused ultrasound in free field and pulsatile flow

Cavitation plays important roles in almost all high-intensity focused ultrasound (HIFU) applications. However, current two-dimensional (2D) cavitation mapping could only provide cavitation activity in one plane. This study proposed a three-dimensional (3D) ultrasound plane-by-plane active cavitation mapping (3D-UPACM) for HIFU in free field and pulsatile flow. The acquisition of channel-domain raw radio-frequency (RF) data in 3D space was performed by sequential plane-by-plane 2D ultrafast active cavitation mapping. Between two adjacent unit locations, there was a waiting time to make cavitation nuclei distribution of the liquid back to the original state. The 3D cavitation map equivalent to the one detected at one time and over the entire volume could be reconstructed by Marching Cube algorithm. Minimum variance (MV) adaptive beamforming was combined with coherence factor (CF) weighting (MVCF) or compressive sensing (CS) method (MVCS) to process the raw RF data for improved beamforming or more rapid data processing. The feasibility of 3D-UPACM was demonstrated in tap-water and a phantom vessel with pulsatile flow. The time interval between temporal evolutions of cavitation bubble cloud could be several microseconds. MVCF beamformer had a signal-to-noise ratio (SNR) at 14.17dB higher, lateral and axial resolution at 2.88times and 1.88times, respectively, which were compared with those of B-mode active cavitation mapping. MVCS beamformer had only 14.94% time penalty of that of MVCF beamformer. This 3D-UPACM technique employs the linear array of a current ultrasound diagnosis system rather than a 2D array transducer to decrease the cost of the instrument. Moreover, although the application is limited by the requirement for a gassy fluid medium or a constant supply of new cavitation nuclei that allows replenishment of nuclei between HIFU exposures, this technique may exhibit a useful tool in 3D cavitation mapping for HIFU with high speed, precision and resolution, especially in a laboratory environment where more careful analysis may be required under controlled conditions.

FPGA-based digital filter used in ultrasound diagnostic device

A large real-time processing of ultrasonic signals is a very important part in the ultrasound diagnosis system,especially with digital hardware processing.A key part of the signal processing is the filter design which will affect the performance of ultrasound diagnostic equipment.In this paper,the classification of digital filters is introduced briefly,and a number of hardware implementation methods of digital filter in recent years,especially the realization of FIR filters which belongs to the classical filter based on Distributed Algorithms are discussed.Then a number of advantages and problems of digital filter in recent years are analyzed.On this basis,the paper forecasts its developing trends in the future. Key words: Digital filter; FPGA; Ultrasonic diagnostic apparatus

Development of Ultrasound Diagnosis System for Carotid Artery Using Probe Pose Estimation and Three-dimensional Structure Reconstruction Techniques

Development of Ultrasound Diagnosis System for Carotid Artery Using Probe Pose Estimation and Three-dimensional Structure Reconstruction Techniques

Assemblable Hand for Laparoscopic Surgery with Phased Array and Single-Element Ultrasound Probes

During laparoscopic surgery, large internal organs should often be manipulated while being internally visualized. For this purpose, we study an assemblable two-fingered hand implemented with an ultrasound probe. The fingers are separately introduced into the abdominal cavity through small incisions and are assembled into a hand sufficiently large to grasp or manipulate the large organ. Two types of ultrasound probes are employed; a phased array probe of a commercially available ultrasound diagnosis system, and a single-element probe. Using the latter probe, the hand is assembled through 12 mm trocars and is assessed in an in vivo experiment. Ultrasound echo sensing is found to retrieve diagnostic information regarding specific internal organs. It also visualizes the finger and its back during grasping, which can improve the safety of hand grasping and manipulation. Furthermore, ultrasound echo sensing can assist the measurement of the relative position and orientation of the two grasping fingers.

Development of a robot assisted carotid blood flow measurement system

The ultrasound diagnosis of the carotid artery is one of the most common non-invasive methods to detect early stage heart and cerebrovascular diseases. However, the precision and repetitiveness of the probe positioning depend exclusively on the operator's skills and dexterity. For this purpose, we propose the development of a robot assisted system to enhance the accuracy and repetitiveness of the probe positioning to measure the wave intensity (WI) index. In this paper, the W aseda- T okyo Women's Medical- A loka Blood Flow Measurement Robot System No. 2 R efined (WTA-2R) is presented. The WTA-2R consists of a conventional ultrasound diagnosis system, a 6-DOFs parallel link slave manipulator, a 6-DOFs serial link passive arm, and a master device. Experiments were carried out to verify its effectiveness in terms of accuracy and required time to perform the task. From the experimental results, the positioning accuracy and reduction of required time were confirmed. ► Ultrasound diagnosis of the carotid artery is done to detect early stage diseases. ► A robot assisted system was proposed to enhance the performance of probe positioning. ► GA algorithm was used to optimize the dimensions of a 6-PUS parallel link mechanism. ► A joystick-styled remote controller with embedded sensors was designed. ► Pre-clinical test were carried out by medical staff.