Creating a Medical Imaging Workflow Based on FHIR, DICOMweb, and SVG.

This paper proposes a web-based workflow scheme for the organization of medical images using FHIR and DICOM servers equipped with standard RESTful APIs. In our integrated workflow, the client systems (including order placer, scheduler, imaging modality, viewer, and report creator) use standard FHIR and DICOMweb APIs. The proposed scheme also facilitates the creation of reports formatted as standard FHIR resources. This paper leverages W3C Scalable Vector Graphics (SVG) to record the image graphic annotations, and encapsulates the SVG image annotation in FHIR observation. FHIR DiagnosticReports and Observations are used to encapsulate reports, findings, and annotations, thereby facilitating the implementation and integration of the scheme within existing structures. The proposed scheme also provides the potential to make it possible to convert results of Computer Aided Detection/Diagnosis from medical images into FHIR DiagnosticReports and Observations to be stored on a FHIR server. The resulting web-based solution uses FHIR XML and/or JSON data to record and exchange information related to imaging workflow. It can also be used to store imaging reports, findings, and annotations linked to the images using the DICOM WADO-RS protocol. As a result, it is possible to integrate all information that is created in medical imaging workflow. Finally, the proposed scheme is easily integrated with other FHIR systems.

Human Motion Tracking Using 3D Image Features with a Long Short-Term Memory Mechanism Model-An Example of Forward Reaching.

Human motion tracking is widely applied to rehabilitation tasks, and inertial measurement unit (IMU) sensors are a well-known approach for recording motion behavior. IMU sensors can provide accurate information regarding three-dimensional (3D) human motion. However, IMU sensors must be attached to the body, which can be inconvenient or uncomfortable for users. To alleviate this issue, a visual-based tracking system from two-dimensional (2D) RGB images has been studied extensively in recent years and proven to have a suitable performance for human motion tracking. However, the 2D image system has its limitations. Specifically, human motion consists of spatial changes, and the 3D motion features predicted from the 2D images have limitations. In this study, we propose a deep learning (DL) human motion tracking technology using 3D image features with a deep bidirectional long short-term memory (DBLSTM) mechanism model. The experimental results show that, compared with the traditional 2D image system, the proposed system provides improved human motion tracking ability with RMSE in acceleration less than 0.5 (m/s2) X, Y, and Z directions. These findings suggest that the proposed model is a viable approach for future human motion tracking applications.

Use of a rich internet application solution to present medical images.

Browser with Rich Internet Application (RIA) Web pages could be a powerful user interface for handling sophisticated data and applications. Then the RIA solutions would be a potential method for viewing and manipulating the most data generated in clinical processes, which can accomplish the main functionalities as general picture archiving and communication system (PACS) viewing systems. The aim of this study is to apply the RIA technology to present medical images. Both Digital Imaging and Communications in Medicine (DICOM) and non-DICOM data can be handled by our RIA solutions. Some clinical data that are especially difficult to present using PACS viewing systems, such as ECG waveform, pathology virtual slide microscopic image, and radiotherapy plan, are as well demonstrated. Consequently, clinicians can use browser as a unique interface for acquiring all the clinical data located in different departments and information systems. And the data could be presented appropriately and processed freely by adopting the RIA technologies.

Deep-learning-based human motion tracking for rehabilitation applications using 3D image features.

Motion rehabilitation is increasingly required owing to an aging population and suffering of stroke, which means human motion analysis must be valued. Based on the concept mentioned above, a deep-learning-based system is proposed to track human motion based on three-dimensional (3D) images in this work; meanwhile, the features of traditional red green blue (RGB) images, known as two-dimensional (2D) images, were used as a comparison. The results indicate that 3D images have an advantage over 2D images due to the information of spatial relationships, which implies that the proposed system can be a potential technology for human motion analysis applications.

Analyzing the audio signals of degenerative arthritis with an electronic stethoscope.

The advance of modern medical technology has extended people's life and increased the average age of the society. Some chronic diseases are due to the aging of the population and knee joint aging is a common disease in the elderly. Common joint pathology contains degenerative arthritis, arthroncus of knees, and gouty arthritis. Knee joints are the largest and the most complicated joints in a human body as well as the joint bearing huge pressure. Wrong posture, overuse, or vigorous exercise often cause injuries to knee joints, and such injuries could easily result in joint pathology and patients falling and breaking bones due to pain and powerlessness. An acoustic wave technology, aiming at knee joints, is designed to examine a patient's current condition of joints. An electronic stethoscope or high-resolution recording equipment is utilized for collecting necessary signals, through which the wide-frequency audio signals of knee joints could be measured for the analyses and statistics in a back-end computer. Besides, it could classify the groups with healthy and degenerative knee joints to assist physicians in proceeding non-invasive joint degeneration examination clinically and doing the most suitable rehabilitation therapy.

Improving the performance of hearing aids in noisy environments based on deep learning technology.

The performance of a deep-learning-based speech enhancement (SE) technology for hearing aid users, called a deep denoising autoencoder (DDAE), was investigated. The hearing-aid speech perception index (HASPI) and the hearing- aid sound quality index (HASQI), which are two well-known evaluation metrics for speech intelligibility and quality, were used to evaluate the performance of the DDAE SE approach in two typical high-frequency hearing loss (HFHL) audiograms. Our experimental results show that the DDAE SE approach yields higher intelligibility and quality scores than two classical SE approaches. These results suggest that a deep-learning-based SE method could be used to improve speech intelligibility and quality for hearing aid users in noisy environments.

Electrical lumped model for arterial vessel beds.

Numerous electrical analog models of the circulatory system have been proposed. However, conventional models are either too simple, focusing exclusively on heart function, or overly complex, characterizing arteries in excessive detail. The vessel beds, which comprise arteries, capillaries and veins, are well known to be responsible for most of the pressure drop in blood pressure and to dominate the draining of blood flow. Consequently, electrical analog models of the circulatory system should pay more attention to the vessel beds. This investigation divided the arterial system into several aortic segments with vessel beds, and proposed a model that used electrical lumped elements to represent the vessel beds. The model was adopted to simulate blood pressure propagation by considering each vessel bed as an isolated subsystem. The transfer function between the terminals of isolated subsystems was used to identify the electrical components of the lumped elements that characterized the vessel beds. Simulation results reveal that the compliance and impedance of the vessel beds are larger than in previous models that focused on the aorta or arteries. The proposed electrical lumped model could deal with much more information than the simple models due to the lumped element structure. Furthermore, its isolated subsystem approach also makes the proposed model significantly easier to use than the complex models.

Inhibition of peroxisome proliferator-activated receptor gamma prevents the melanogenesis in murine B16/F10 melanoma cells.

The purpose of this study was to investigate if PPARγ plays a role in the melanogenesis. B16/F10 cells were divided into five groups: control, melanin stimulating hormone (α-MSH), α-MSH+retinol, α-MSH+GW9662 (PPARγ antagonist), and GW9662. Cells in the control group were cultured in the Dulbecco's modified Eagle's medium (DMEM) for 48 hrs. To initiate the melanogenesis, cells in all α-MSH groups were cultured in medium containing α-MSH (10 nM) for 48 hrs. Cells were treated simultaneously with retinol (5 µM) in the α-MSH+retinol group. Instead of retinol, GW9662 (10 µM) was cocultured in the α-MSH+GW9662 group. Cells in the final group were cultured in the DMEM with GW9662. All the analyses were carried out 48 hours after treatments. The α-MSH was able to increase cell number, melanin production, and the activity of tyrosinase, the limiting enzyme in melanogenesis. These α-MSH-induced changes were prevented either by retinol or by GW9662. Further analyses of the activities of antioxidant enzymes including glutathione, catalase, and the superoxide dismutase (SOD) showed that α-MSH treatment raised the activity of SOD which was dependent on PPARγ level. According to our results, the α-MSH-induced melanogenesis was PPARγ dependent, which also modulated the expression of SOD.

Different patterns of dynamic variations on electrical conductances of acupoints between Qi Vacuity and Qi non-Vacuity after glucose ingestion.

OBJECTIVES: In Traditional Chinese Medicine (TCM), Qi maintains the physiologic function and indicates physiologic energy. Glucose provides energy to humans, thereby playing a role analogous to "nutritive Qi." This study aims to identify the correlations among blood glucose, Qi Vacuity (QV), and the electrical conductances of acupoints. METHODS: Twenty (20) subjects who had ingested a glucose solution after a 10-hour overnight fast were divided into two groups based on QV score. Then their acupoint conductances were measured sequentially using a Ryodoraku instrument during the following 120 minutes. Data were analyzed using generalized estimating equations as a time-series model. RESULTS: Eight (8) subjects were categorized into a Qi Vacuous group for QV score >6, and the other 12 subjects were categorized into a Qi non-Vacuous group for QV score ≤6. During the first 30 minutes, the acupoint conductances decreased on the left Pericardium, left Heart, right Liver, Kidney, and Gallbladder meridians in the Qi Vacuous group, and increased on the right Pericardium meridian and decreased on the right Gallbladder meridian in the Qi non-Vacuous group. From 30 to 60 and 60 to 90 minutes, the acupoint conductances decreased on the Gallbladder, Heart, left Pericardium, left Kidney, right Liver, and right Stomach meridians in the Qi Vacuous group, and increased on the Pericardium, Heart, left Small Intestine, and left Lung meridians in the Qi non-Vacuous group. During the last 30 minutes, more of the acupoint conductances were increased in the Qi non-Vacuous group, whereas only the acupoint conductance on the liver meridian was increased and that on the left gallbladder meridian was decreased in the Qi Vacuous group. CONCLUSIONS: The findings suggest that the energy distribution and transformation in meridian vessels present different patterns in QV and non-QV groups after glucose consumption.

A communication platform for diabetes surveillance.

Diabetes mellitus is a common and precarious chronic disease, which affects cellular metabolism and energy production. The condition is divided into types I and II; the most common form is type II diabetes, which is an adult-onset disease. Blood glucose testing is crucial to diabetes control, and it is effective in reducing the risk of complications and improving life quality. Unfortunately, both elderly patients and their caregivers find it difficult to monitor glucose levels long term. This study developed a communication platform for diabetes surveillance. The developed system prompts diabetics to measure their blood glucose regularly at home, and provides remote care persons with complete information about the patient's measurement. This aids in the improvement in diabetes control, thereby increasing the social activities and life quality of diabetics.