In order to improve the clarity of ECG waveforms and the anti-interference ability of ECG acquisition under abnormal conditions, this study proposes a high-definition ECG recording method based on superimposed averaging algorithm. The results show that the proposed method can more clearly reflect the details of the ECG. Meanwhile, it has a significant inhibitory effect on EMG interference. As a result, the proposed method has a positive significance for improving the anti-interference ability of ECG equipment.
Algorithms ; Electrocardiography

The count and recognition of white blood cells in blood smear images play an important role in the diagnosis of blood diseases including leukemia. Traditional manual test results are easily disturbed by many factors. It is necessary to develop an automatic leukocyte analysis system to provide doctors with auxiliary diagnosis, and blood leukocyte segmentation is the basis of automatic analysis. In this paper, we improved the U-Net model and proposed a segmentation algorithm of leukocyte image based on dual path and atrous spatial pyramid pooling. Firstly, the dual path network was introduced into the feature encoder to extract multi-scale leukocyte features, and the atrous spatial pyramid pooling was used to enhance the feature extraction ability of the network. Then the feature decoder composed of convolution and deconvolution was used to restore the segmented target to the original image size to realize the pixel level segmentation of blood leukocytes. Finally, qualitative and quantitative experiments were carried out on three leukocyte data sets to verify the effectiveness of the algorithm. The results showed that compared with other representative algorithms, the proposed blood leukocyte segmentation algorithm had better segmentation results, and the mIoU value could reach more than 0.97. It is hoped that the method could be conducive to the automatic auxiliary diagnosis of blood diseases in the future.
Algorithms ; Leukocytes

OBJECTIVE: To explore the application of extended reality (XR) technology in clinical surgeries for improving the success rate of surgeries. METHODS: To assist the surgeons to better understand the location, size and geometric shape of the lesions and reduce potential radiation exposure in minimally invasive surgical navigation based on two-dimensional images, we constructed three-dimensional models based on CT data and used XR technology to achieve intraoperative navigation. An improved quaternion method was used to improve the accuracy of electromagnetic positioning, with which the system error of positioning accuracy was reduced to below 2 mm. A 5G network was used to optimize the server GPU programming algorithm, and real-time video stream coding strategy and network design were adopted to reduce data transmission jam and delay in the remote surgery network, which achieved an average delay of less than 60 ms. A Gaussian distribution deformation model was used to simulate collision detection and stress deformation of the tissues to achieve a tactile perception effect. RESULTS AND CONCLUSION The intraoperative navigation system based on XR technology allowed more accurate determination of the location of the lesions, effectively reduced the surgical risk, and avoided the risk of intraoperative radiation exposure. The low latency and high fidelity of 5G network achieved real-time interaction during the surgery to provide a technical basis for multi-terminal remote cooperative surgery. The combination of force feedback technology and XR technology enables the surgeons to conduct deep immersion preoperative planning and virtual surgery to improve the success rate of surgery and shorten the learning curve.
Algorithms ; Technology

Aiming at the shortcomings of traditional medical device tracking and supervision mode, such as delayed feedback of medical device positioning information, poor visual tracking effect of medical device, and missing early warning of medical device working state supervision, a medical device visual tracking and supervision system based on wireless Local Area Network (LAN) real-time positioning system is developed. Introduction of wireless LAN real-time positioning system, using standard coding algorithm generating device object ID tags, with the only attribute based on RFID read-write terminal complete physical mapping of medical equipment and material ID label, we realize a real-time positioning and traceability of medical equipment, with the help of active warning algorithm based on depth of learning medical equipment working state supervision for early warning, with the help of indoor map generation and trajectory playback medical equipment to realize visualization back regulation. Choose equipment of hospital of Linyi Central Hospital for performance evaluation of the carrier, the evaluation model of engineering practice and clinical statistical analysis, the results show that the system has a complete real-time positioning, visible trace, abnormal warning function. In medical equipment real-time positioning information visual tracing feedback, abnormal state warning etc, medical equipment has obvious advantages.
Algorithms ; Local Area Networks

Chromatography is a basic process in the current proteomics workflow, and the retention time alignment of the chromatogram is one of the important steps to effectively improve the identification and quantification accuracy. After years of development, a series of algorithms for retention time alignment have been developed. This review summarizes the advances of chromatographic retention time alignment algorithms and tools for proteomics analysis from the perspective of proteomics users, and discusses the development and future application directions.
Algorithms ; Proteomics/methods*

With the market development and demand change, the use of adaptive algorithms in medical devices has become a possible trend. However, some uncertainties in the adaptive algorithm itself will bring challenges to the existing current supervisory work model. This article focuses on the ademptions of US agencies on artificial intelligence device supervision, and discusses the problems that existing pilot policies may encounter when facing devices with adaptive algorithms. In this way, we will provide relevant suggestions and look forward to discussing with scholars.
Algorithms ; Artificial Intelligence

Computational medicine is an emerging discipline that uses computer models and complex software to simulate the development and treatment of diseases. Advances in computer hardware and software technology, especially the development of algorithms and graphics processing units (GPUs), have led to the broader application of computers in the medical field. Computer vision based on mathematical biological modelling will revolutionize clinical research and diagnosis, and promote the innovative development of Chinese medicine, some biological models have begun to play a practical role in various types of research. This paper introduces the concepts and characteristics of computational medicine and then reviews the developmental history of the field, including Digital Human in Chinese medicine. Additionally, this study introduces research progress in computational medicine around the world, lists some specific clinical applications of computational medicine, discusses the key problems and limitations of the research and the development and application of computational medicine, and ultimately looks forward to the developmental prospects, especially in the field of computational Chinese medicine.
Algorithms ; Computer Simulation ; Humans

The modifications of slices, flip angle, SAR mode and TR time are required when the SAR exceeds the limits. The scan time and image quality are affected by those. This study analyzes the SAR from the basic side. With the principle diagram of SIEMENS 1.5 T AVANTO and 3.0 T VERIO MRIS, the trouble shooting procedure of SAR problem is reached both in application and problem sides.
Algorithms ; Image Enhancement

OBJECTIVE: To investigate the sensing volume of open-ended coaxial probe technique for measurement of dielectric characteristics. METHODS: A measurement model combining macro- measurement device with a layer model of dielectric properties parameters was established for evaluating the sensing volume of open-ended coaxial probe technique. We defined sensing depth and sensing diameter to describe the distance that could be detected in vertical and horizontal direction. Using a variety of materials with different dielectric properties (Teflon, deionized water, ethanol, and gradient concentration sodium chloride solution), a layered model of dielectric properties differentiation was established. The total combined uncertainties (TCU) were calculated for different output power, and the output power was controlled to increase from -50 dBm to 15 dBm to calibrate the error range of the dielectric properties measurement system. The optimal output power range was determined based on the results of TCU test. In sensing volume measurement experiment, we set the control groups based on measurement parameters that potentially affect the sensing volume including output power (-10, -5, 0, 3, 6, and 9 dBm), frequency (1-500 MHz), Teflon, deionized water, and ethanol to form a dielectric constant difference between high and low contrast groups. Different concentrations of sodium chloride solution and Teflon were used to generate a conductivity difference between high and low contrast groups. These groups were tested in the sensing depth and sensing diameter measurement experiments. RESULTS: The result of TCU test indicated that accurate and stable measurement results could be obtained when the output power was greater or equal to-10 dBm (TCU < 2%). Sensing volume measurement experiment revealed a positive correlation between the sensing depth and output power ( < 0.05). As the measured power increased, the sensing depth gradually increased in deionized water and ethanol, and the difference reached 70 μm. The sensing depth was negatively correlated frequency ( < 0.05). As the concentration of sodium chloride solution increased, the corresponding sensing depth gradually decreased, with a difference reaching 270 μm. The sensing depth of high dielectric materials was greater than that pf low dielectric materials. The results of sensing diameter measurement were not obviously affected by the measurement parameters, and the sensing diameter was stable in a fixed range (1.0 to 1.8 mm) between the diameter of the inner conductor and the diameter of the insulation layer, and was less than the diameter of the probe. CONCLUSIONS The sensing volume of open-ended coaxial probe technique is affected by measurement parameters and dielectric properties of materials, which significantly affect the sensing depth.
Algorithms ; Electric Conductivity

Objective To explore the semi-supervised learning (SSL) algorithm for long-tail endoscopic image classification with limited annotations. Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir, the largest gastrointestinal public dataset with 23 diverse classes. Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling. After splitting the training dataset and the test dataset at a ratio of 4:1, we sampled 20%, 50%, and 100% labeled training data to test the classification with limited annotations. Results The classification performance was evaluated by micro-average and macro-average evaluation metrics, with the Mathews correlation coefficient (MCC) as the overall evaluation. SSL algorithm improved the classification performance, with MCC increasing from 0.8761 to 0.8850, from 0.8983 to 0.8994, and from 0.9075 to 0.9095 with 20%, 50%, and 100% ratio of labeled training data, respectively. With a 20% ratio of labeled training data, SSL improved both the micro-average and macro-average classification performance; while for the ratio of 50% and 100%, SSL improved the micro-average performance but hurt macro-average performance. Through analyzing the confusion matrix and labeling bias in each class, we found that the pseudo-based SSL algorithm exacerbated the classifier's preference for the head class, resulting in improved performance in the head class and degenerated performance in the tail class. Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification, especially when the labeled data is extremely limited, which may benefit the building of assisted diagnosis systems for low-volume hospitals. However, the pseudo-labeling strategy may amplify the effect of class imbalance, which hurts the classification performance for the tail class.
Supervised Machine Learning ; Algorithms