Medical Imaging Equipment Research Articles

Maintenance and Management Technology of Medical Imaging Equipment Based on Deep Learning.

Medical equipment maintenance in modern hospital management is an emerging marginal discipline which is one of the important branches of hospital management with the dual function of management and technology. The good or bad management of medical equipment directly affects the quality of hospital work. With the development of science and technology, the scale of hospitals continues to expand and develop; hospitals are equipped with more and more medical equipment and its technical content is getting higher and higher, which makes the medical equipment management and maintenance practitioners more demanding. However, the situation of existing medical equipment management and maintenance personnel is not optimistic. For this reason, this paper designs a good database structure, which can effectively reduce data redundancy and better avoid the problems that may occur during the database operation. As a reference guideline for database design, the three database paradigms can be studied and understood in depth to help software designers design more “robust” databases, enabling effective maintenance and management of medical imaging equipment.

RA-SIFA: Unsupervised domain adaptation multi-modality cardiac segmentation network combining parallel attention module and residual attention unit.

Convolutional neural network has achieved a profound effect on cardiac image segmentation. The diversity of medical imaging equipment brings the challenge of domain shift for cardiac image segmentation. In order to solve the domain shift existed in multi-modality cardiac image segmentation, this study aims to investigate and test an unsupervised domain adaptation network RA-SIFA, which combines a parallel attention module (PAM) and residual attention unit (RAU). First, the PAM is introduced in the generator of RA-SIFA to fuse global information, which can reduce the domain shift from the respect of image alignment. Second, the shared encoder adopts the RAU, which has residual block based on the spatial attention module to alleviate the problem that the convolution layer is insensitive to spatial position. Therefore, RAU enables to further reduce the domain shift from the respect of feature alignment. RA-SIFA model can realize the unsupervised domain adaption (UDA) through combining the image and feature alignment, and then solve the domain shift of cardiac image segmentation in a complementary manner. The model is evaluated using MM-WHS2017 datasets. Compared with SIFA, the Dice of our new RA-SIFA network is improved by 8.4%and 3.2%in CT and MR images, respectively, while, the average symmetric surface distance (ASD) is reduced by 3.4 and 0.8mm in CT and MR images, respectively. The study results demonstrate that our new RA-SIFA network can effectively improve the accuracy of whole-heart segmentation from CT and MR images.

Collaborative networking and support for medical physics development in low and middle income (LMI) countries.

Medical physics is one of the key aspects of contemporary medicine, primarily focused on the safe and effective use of medical imaging and radiotherapy equipment. The number of medical physicists and their activities are directly related to the national/regional healthcare provision. The distribution of the medical physics workforce however is still very uneven—more than 70% of all medical physicists are in North America and Europe, serving the healthcare provision of about 1 billion people. The remaining 30% of medical physicists serve the healthcare provision of the rest of the world—serving about 6.5 billion people. A number of activities were taken by various teams and organisations to address this issue. The increase of quality of healthcare and the effectiveness of medical technology usage, lie in adequate education and training for medical physicists and engineers, who are the front-liners when it comes to dealing with technology in healthcare. To help LMI countries professional growth in the field of medical physics and technology, we developed an education and capacity building strategy, based on the revolutionary application of digital resources combined with experience sharing through large international network.

Application of MBSAP to a Complex Problem with Social Dimensions: Utilization in Outpatient Imaging Centers

ABSTRACTOutpatient imaging centers struggle daily to manage the negative impact of same day missed appointments. The technical component of outpatient imaging centers includes a complex IT infrastructure and advanced medical imaging equipment. The social component of outpatient imaging centers includes stakeholders that regularly interact with these technologies and one another all to help physicians diagnose their patients. The effectiveness of the technology used in outpatient imaging is dependent on operator ability and stakeholder collaboration. Problems in this type of system require intentional systems thinking to understand stakeholder needs. The Model‐Based System Architecture Process (MBSAP) provides a visually understandable framework for system development in an industry unfamiliar with Systems Engineering methods. The primary social dimensions in outpatient imaging are the Customer Dimension, Planning Dimension, Operations Dimension, and Technical Dimension. Each dimension has stakeholders with a diverse set of needs that must be well‐understood and incorporated into the requirements. This paper presents an architecture for a system that utilizes all available exam time slots without a dependency on modifying patient behavior to prevent same day missed appointments. The MBSAP artefacts are the starting point for making the system a reality with stakeholders and finding the right balance between separate social dimensional measures.

Dielectric, piezoelectric, and spurious mode vibration properties by four types of waveforms AC poling for Pb(Mg1/3Nb2/3)O3-PbTiO3 single crystals

Four types of waveforms of AC poling (ACP) and DC poling (DCP) were applied on [001]-oriented 0.72Pb(Mg1/3Nb2/3)O3-0.28PbTiO3 (PMN-28PT) ferroelectric single crystals (SCs) at 80 °C. High voltage (5 kV cm−1) ACP of all four waveforms and DCP SCs tend to show low piezoelectric coefficient (d 33) less than 1660 pC/N and large spurious-mode vibration (SMV) at the thickness mode vibration (TMV) on impedance spectrum. The highest d 33 of 1830 pC/N was obtained by a triangle wave of 3 kV cm−1 SCs with tiny SMV. By contrast, low voltage (1.5 kV cm−1) ACP SCs with sine and triangle waveforms showed high d 33 of 1750 pC/N and 1670 pC/N without any SMV. We consider that the SMV is more easily caused by the over-poling of PMN-28PT SC. This information will help realize high piezoelectric properties and high production yield for ACP PMN-PT SC transducers for high-resolution medical ultrasound imaging equipment.

Demand-side Synergy and Firms' Competitive and Collaborative Strategies over Platform Lifecycle

The paper examines how emergence of a digital platform that bolsters demand-side synergy affects complementary product firms’ competitive and collaborative strategies and how they evolve across the platform lifecycle. Building on demand-side research and digital platform literature, I suggest the bundling of a digital platform service can be an important source of firms’ demand-side product synergy and the potential size of demand-side economies of scope may vary across different stages of platform evolution. Using the context of U.S. medical diagnostic imaging equipment manufacturers 1987-2013 and the introduction of an image communication system in 1993, I find that on average, imaging device manufacturers spanning across multiple complementary product markets are more likely to bundle a platform service as opposed to the firms specialized in a single product market, and more so in the early period of the platform lifecycle. The results also suggest that firms with product/platform bundling are likely to further increase diversity in their product lines and create walled gardens around their platform services. In terms of within-industry collaborations, the complementary product firms with platform service are more likely to engage in alliances than those without, but less so as the platform matures.

Spurious-mode vibrations caused by alternating current poling and their solution process for Pb(Mg1/3Nb2/3)O3-PbTiO3 single crystals

The effects of alternating current poling (ACP) at 80 °C on electrical properties of [001]-oriented 0.72 Pb(Mg1/3Nb2/3)O3-0.28PbTiO3 (PMN-28PT) single crystals (SCs) have been investigated. The square-wave ACP SCs poled at high voltage (HV, 5 kVrms/cm) occasionally showed large fluctuations and low opposite values of piezoelectric coefficient (d33 = ± 1370 pC/N) in one plate. This revealed spurious-mode vibrations (SMV) of impedance spectrum. However, after depolarizing and repolarizing the sample with a sine-wave ACP at low voltage (LV, 3.5 kVrms/cm), the d33 enhanced to be 1720 pC/N (+26%) and did not exhibit large fluctuation or opposite values in one plate any more. The impedance spectrum became clean and the abnormal SMV disappeared. We proposed four possible mechanisms of the SMV, and speculate that the main cause maybe by macro-scale sub-domain structure and/or phase change in the main domain structure and/or phase in the SC plate due to the specific poling conditions not eternal mechanical damage of PMN-PT SCs. This study will be useful to realize a high d33 and improve other properties of PMN-PT ACP SC ultrasonic transducers without any SMV for high-frequency medical imaging equipment.

A diagnostic medical physicist’s guide to the American College of Radiology Fluoroscopy Dose Index Registry

A diagnostic medical physicist’s guide to the American College of Radiology Fluoroscopy Dose Index Registry

DeepEDN: A Deep-Learning-Based Image Encryption and Decryption Network for Internet of Medical Things

Internet of Medical Things (IoMT) can connect many medical imaging equipments to the medical information network to facilitate the process of diagnosing and treating for doctors. As medical image contains sensitive information, it is of importance yet very challenging to safeguard the privacy or security of the patient. In this work, a deep learning based encryption and decryption network (DeepEDN) is proposed to fulfill the process of encrypting and decrypting the medical image. Specifically, in DeepEDN, the Cycle-Generative Adversarial Network (Cycle-GAN) is employed as the main learning network to transfer the medical image from its original domain into the target domain. Target domain is regarded as a "Hidden Factors" to guide the learning model for realizing the encryption. The encrypted image is restored to the original (plaintext) image through a reconstruction network to achieve an image decryption. In order to facilitate the data mining directly from the privacy-protected environment, a region of interest(ROI)-mining-network is proposed to extract the interested object from the encrypted image. The proposed DeepEDN is evaluated on the chest X-ray dataset. Extensive experimental results and security analysis show that the proposed method can achieve a high level of security with a good performance in efficiency.

Health Evaluation and Fault Diagnosis of Medical Imaging Equipment Based on Neural Network Algorithm

In recent years, high-precision medical equipment, especially large-scale medical imaging equipment, is usually composed of circuit, water, light, and other structures. Its structure is cumbersome and complex, so it is difficult to detect and diagnose the health status of medical imaging equipment. Based on the vibration signal of mechanical equipment, a PLSR-DNN hybrid network model for health prediction of medical equipment is proposed by using partial least squares regression (PLSR) algorithm and deep neural networks (DNNs). At the same time, in the diagnosis of medical imaging equipment fault, the paper proposes to use rough set to screen the fault factors and then use BP neural network to classify and identify the fault and analyzes the practical application effect of the two technologies. The results show that the PLSR-DNN hybrid network model for health prediction of medical imaging equipment is basically consistent with the actual health value of medical equipment; medical imaging equipment fault diagnosis technology is based on rough set and BP neural network. In the test set, the sensitivity, specificity, and accuracy of medical imaging equipment fault identification are 75.0%, 83.3%, and 85.0%. The above results show that the proposed health prediction method and fault diagnosis method of medical imaging equipment have good performance in health prediction and fault diagnosis of medical equipment.

Technologies for magnetic induction tomography sensors and image reconstruction in medical assisted diagnosis: A review.

Magnetic induction tomography (MIT) is a non-invasive and non-contact imaging technology, which can be used in medical diagnosis by reconstructing the electrical distribution of biological tissues. Unlike other large medical imaging equipment, the device of MIT is with small size and low cost. The theoretical basis of MIT is by measuring the phase difference of magnetic flux density generated around the imaging objects, analyzing the eddy current distribution, and then using the reconstruction algorithms to obtain the electrical characteristic distribution of the object. This review introduces the development of imaging systems and the reconstruction algorithms of MIT as a medical assisted diagnostic technology, including the optimal design of the sensors, the excitation methods of the system, the calculation methods of the eddy current, and the improved methods of different reconstruction algorithms.

Design and Implementation of a Multi-scale Object Detection Algorithm on TensorFlow

The technology of object detection is a very important subject in computer vision task. It has been widely used in intelligent transportation, face detection, aerospace and medical image equipment. In this paper, a kind of object detection algorithm based on regression and region proposals is studied. We use a popular deep learning framework—TensorFlow, as the experimental platform. We propose a multi-scale object detection algorithm based on RPN region proposal network, which can extract the features of large and small objects by using the level of feature map. In addition, this paper also improves the classification regression model and proposes a two-dimensional loss function, which makes the region proposals closer to the groundtruth boxes in the final training, which makes the training process of the improved network easier. The experimental data set used in this paper is PASCAL VOC data set, the accuracy and speed of each category in 20 detection objects are calculated and analyzed. A number of experiments have proved that the proposed multi-scale object detection algorithm based on RPN have improved in accuracy and speed. The average detection precision on the PASCAL VOC dataset increased to 74.4%.

Long-term clinical performance of flapless implant surgery compared to the conventional approach with flap elevation: A systematic review and meta-analysis.

BACKGROUNDThe conventional implant approach involves flap elevation, which may result in increased soft tissue and bone loss and postoperative morbidity. The flapless surgical technique, aided by three-dimensional medical imaging equipment, is regarded as a possible alternative to the conventional approach to alleviate the above issues. Several studies have been performed regarding the role of flapless implant surgery. However, the results are inconsistent and there is no robust synthesis of long-term evidence to better inform surgeons regarding which type of surgical technique is more beneficial to the long-term prognosis of patients in need of implant insertion.AIMTo compare the long-term clinical performance after flapless implant surgery to that after the conventional approach with flap elevation.METHODSPubMed, EMBASE, Cochrane Central Register of Controlled Trials, and grey literature databases were searched from inception to 23 September 2019. Randomised controlled trials (RCTs) and cohort studies comparing the long-term clinical performance after flapless implant surgery to that after the conventional approach over a follow-up of three years or more were included. Meta-analyses were conducted to estimate the odds ratios (ORs) or mean differences (MDs) and their 95% confidence intervals (CIs) between the long-term implant survival rate, marginal bone loss, and complication rate of the flapless and conventional groups. Subgroup analyses were carried out to account for the possible effects of the guided or free-hand method during flapless surgery.RESULTSTen articles, including four RCTs and six cohort studies, satisfied the eligibility criteria and nine of them were included in the meta-analysis. There was no significant difference between the long-term implant survival rate [OR = 1.30, 95%CI (0.37, 4.54), P = 0.68], marginal bone loss [MD = 0.01, 95%CI (-0.42, 0.44), P = 0.97], and complication rate [OR = 1.44, 95%CI (0.77, 2.68), P = 0.25] after flapless implant surgery and the conventional approach. Moreover, subgroup analyses revealed that there was no statistically significant difference between the implant survival rate [guided: OR = 1.52, 95%CI (0.19, 12.35), P = 0.70]; free-hand: n = 1, could not be estimated), marginal bone loss [guided: MD = 0.22, 95%CI (-0.14, 0.59), P = 0.23; free-hand: MD = -0.27, 95%CI (-1.10, 0.57), P = 0.53], or complication rate [guided: OR = 1.16, 95%CI (0.52, 2.63), P = 0.71; free-hand: OR = 1.75, 95%CI (0.66, 4.63), P = 0.26] in the flapless and conventional groups either with use of the surgical guide or by the free-hand method.CONCLUSIONThe flapless surgery and conventional approach had comparable clinical performance over three years or more. The guided or free-hand technique does not significantly affect the long-term outcomes of flapless surgery.

Application of Image Fusion in Diagnosis and Treatment of Liver Cancer

With the accelerated development of medical imaging equipment and techniques, image fusion technology has been effectively applied for diagnosis, biopsy and radiofrequency ablation, especially for liver tumor. Tumor treatment relying on a single medical imaging modality might face challenges, due to the deep positioning of the lesions, operation history and the specific background conditions of the liver disease. Image fusion technology has been employed to address these challenges. Using the image fusion technology, one could obtain real-time anatomical imaging superimposed by functional images showing the same plane to facilitate the diagnosis and treatments of liver tumors. This paper presents a review of the key principles of image fusion technology, its application in tumor treatments, particularly in liver tumors, and concludes with a discussion of the limitations and prospects of the image fusion technology.

3D printed CT-based abdominal structure mannequin for enabling research

An anthropomorphic phantom is a radiologically accurate, tissue realistic model of the human body that can be used for research into innovative imaging and interventional techniques, education simulation and calibration of medical imaging equipment. Currently available CT phantoms are appropriate tools for calibration of medical imaging equipment but have major disadvantages for research and educational simulation. They are expensive, lacking the realistic appearance and characteristics of anatomical organs when visualized during X-ray based image scanning. In addition, CT phantoms are not modular hence users are not able to remove specific organs from inside the phantom for research or training purposes. 3D printing technology has evolved and can be used to print anatomically accurate abdominal organs for a modular anthropomorphic mannequin to address limitations of existing phantoms. In this study, CT images from a clinical patient were used to 3D print the following organ shells: liver, kidneys, spleen, and large and small intestines. In addition, fatty tissue was made using modelling beeswax and musculature was modeled using liquid urethane rubber to match the radiological density of real tissue in CT Hounsfield Units at 120kVp. Similarly, all 3D printed organ shells were filled with an agar-based solution to mimic the radiological density of real tissue in CT Hounsfield Units at 120kVp. The mannequin has scope for applications in various aspects of medical imaging and education, allowing us to address key areas of clinical importance without the need for scanning patients.

The Effects of X-Ray Contrast Media on Actin

Most pictures made from given tissues by medical imaging equipment are usually lack of good contrast. While it is not an issue for certain examinations for the screening of many tissues low contrast difference can be a huge problem. In such cases contrast materials are very good tools to enhance the density and intensity of a vessel, body part, organ or tissue. Pharmaceutical companies develop safer contrast agents with less side-effects, so the older ionic, high osmolality compounds have been replaced by non-ionic, low osmolality contrast materials. It is clear from certain publications that these contrast agent molecules easily penetrate in cells of different tissues and because of their limited ability of depletion these molecules can accumulate in cells of many different tissues. The overview of the corresponding literature clarifies that the effects of the clinically applied contrast materials expressed directly on the actin cytoskeleton and the detailed molecular mechanisms are unknown. Our aim is to investigate the effects of the latest contrast agents on the actin cytoskeleton. Primarily we want to focus on the investigations of any effects contrast materials can cause on the actin protein itself (structural change, loss of function, changed affinities for nucleotides, change in average filament length, etc.) and on the dynamic organisation/rearrangement of the actin network. Our first results show dramatic effects caused by the applied contrast materials on the polymerisation properties of actin. The examined contrast compounds (Iomeprol, Iobitridol) decreased the rate of actin polymerisation by 3-fold. The way of binding of substance molecules to actin is not clear yet, but our DSC results show that the thermal stability of actin filaments is significantly decreased in the presence of contrast agents.

Low dose ionizing radiation strongly stimulates insertional mutagenesis in a γH2AX dependent manner.

Extrachromosomal DNA can integrate into the genome with no sequence specificity producing an insertional mutation. This process, which is referred to as random integration (RI), requires a double stranded break (DSB) in the genome. Inducing DSBs by various means, including ionizing radiation, increases the frequency of integration. Here we report that non-lethal physiologically relevant doses of ionizing radiation (10-100 mGy), within the range produced by medical imaging equipment, stimulate RI of transfected and viral episomal DNA in human and mouse cells with an extremely high efficiency. Genetic analysis of the stimulated RI (S-RI) revealed that it is distinct from the background RI, requires histone H2AX S139 phosphorylation (γH2AX) and is not reduced by DNA polymerase θ (Polq) inactivation. S-RI efficiency was unaffected by the main DSB repair pathway (homologous recombination and non-homologous end joining) disruptions, but double deficiency in MDC1 and 53BP1 phenocopies γH2AX inactivation. The robust responsiveness of S-RI to physiological amounts of DSBs can be exploited for extremely sensitive, macroscopic and direct detection of DSB-induced mutations, and warrants further exploration in vivo to determine if the phenomenon has implications for radiation risk assessment.

Analysis of Risk in Production for PET/MR and Suggestions for Field Inspection

PET/MR is a high-end medical imaging equipment with integrating PET and MR equipment into the highly sophisticated one and has rich clinical and molecular diagnosis functions, can obtain comprehensive information about the human body structure, function and metabolism, is of great value for the diagnosis and treatment of disease improvement. In this paper, through the analysis of existing production risk points on one of the primary stages of the whole product life cycle, combining with the medical device good manufacture practice, some suggestions have been put forward exploratively to field inspection for PET/MR manufacturers. It has certain significance for regulators of medical devices to clear the production risk point and improve verification efficiency during field inspection.

Quality of Service aware Medical CT Image Transmission Anti-collision Mechanism Based on Big Data Autonomous Anti-collision Control

Background: At present, due to the limitation of hardware, software and network transmission performance, the medical diagnosis of medical CT image equipment is easy to be carried out based on the wrong image. In addition, due to the complex structure of human organs and unpredictable lesion location, it is difficult to judge the reliability of medical CT images, spatial localization of the lesion, two-dimensional slice images and shape based on stereotypes. Therefore, how to improve the efficiency of medical CT terminal and the image quality has become the key technology to improve the satisfaction of medical diagnosis and treatment. Objective: To improve the work efficiency of medical CT terminal and medical image transmission quality, with the medical CT terminal state and service quality. Methods: Firstly, from the view of throughput, packet loss rate, delay and so on, a QoS aware model for medical CT image transmission has been established. Then, with throughput, packet length, path loss, service area size, access point location, and the number of medical CT terminals, the performance change regulation of the medical CT image transmission is completed and the optimal quality of service guarantee parameters sequence is obtained. Next, the medical CT image big data autonomous collision control scheme is proposed. Results: The experimental and mathematical results verify the real-time performance, reliability, effectiveness and feasibility of the proposed medical CT image transmission anti-collision mechanism. Conclusion: The proposed scheme can satisfy the high-quality high demand for data transmission at the same time, according to a variety of user experience demand and real-time adjustment of medical CT terminal working state, which provides effective data quality assurance and optimization of the network source distribution, and also enhances the quality of medical image data transmission service.

A medical transportation robot for carrying and positioning patients between different devices

Purpose This paper aims to present a prototype of medical transportation robot whose positioning accuracy can reach millimeter-level in terms of patient transportation. By using this kind of mobile robot, a fully automatic image diagnosis process among independent CT/PET devices and the image fusion can be achieved. Design/methodology/approach Following a short introduction, a large-load 4WD-4WS (four-wheel driving and four-wheel steering) mobile robot for carrying patient among multiple medical imaging equipments is developed. At the same time, a specially designed bedplate with self-locking function is also introduced. For further improving the positioning accuracy, the authors proposed a calibration method based on Gaussian process regression (GPR) to process the measuring data of the sensors. The performance of this robot is verified by the calibration experiment and Image fusion experiment. Finally, concluding comments are drawn. Findings By calibrating the robot’s positioning system through the proposed GPR method, one can obtain the accuracy of the robot’s offset distance and deflection angle, which are 0.50 mm and +0.21°, respectively. Independent repeated trials were then set up to verify this result. Subsequent phantom experiment shows the accuracy of image fusion can be accurate within 0.57 mm in the front-rear direction and 0.83 in the left-right direction, respectively, while the clinical experiment shows that the proposed robot can practically realize the transportation of patient and image fusion between multiple imaging diagnosis devices. Practical implications The proposed robot offers an economical image fusion solution for medical institutions whose imaging diagnosis system basically comprises independent MRI, CT and PET devices. Also, a fully automatic diagnosis process can be achieved so that the patient’s suffering of getting in and out of the bed and the doctor’s radiation dose can be obviated. Social implications The general bedplate presented in Section 2 that can be mounted on the CT and PET devices and the self-locking mechanism has realized the catching and releasing motion of the patient on different medical devices. They also provide a detailed method regarding patient handling and orientation maintenance, which was hardly mentioned in previous research. By establishing the positioning system between the robot and different medical equipment, a fully automatic diagnosis process can be achieved so that the patient’s suffering of getting in and out of the bed and the doctor’s radiation dose can be obviated. Originality/value The GPR-based method proposed in this paper offers a novel method for enhancing the positioning accuracy of the industrial AGV while the transportation robot proposed in this paper also offers a solution for modern imaging fusion diagnosis, which are basically predicated on the conjoint analysis between different kinds of medical devices.