IEEE Transactions on Biomedical Engineering
Test Article

Test Article
Mammography Image Quality Assurance Using Deep Learning
Image quality assurance is crucial in mammography to ensure reliable breast cancer diagnostics. Analyzing images of a technical phantom allows to routinely and reliably assess image quality. Current state-of-the-art analysis determines local image quality features by applying pre-processing and regression procedures for a set of repeatedly recorded images. This proof of concept paper demonstrates that mammography image quality assessment can benefit from deep learning. A neural network is trained on a large database of phantom images, and it is shown that the trained net retrieves the local image quality features already from single images without cumbersome pre-processing. This allows to maintain quality standards at significantly less labor... Read more
Test Article
A Machine Learning Enabled Wireless Intracranial Brain Deformation Sensing System
A leading cause of traumatic brain injury (TBI) is intracranial brain deformation from mechanical impact. This deformation is viscoelastic and differs from a traditional rigid transformation. Here, we present a machine learning enabled wireless sensing system, which can predict the trajectory of intracranial brain deformation by interpreting the magnetic sensor outputs created by the change in position of the implanted soft magnet. Both in vitro and in vivo experimental results showed an overall accuracy of over 92%, suggesting that this sensing scheme can be an effective tool for studying TBI due to in situ and real-time brain deformation prediction... Read more
Test Article
Brain-Computer Interface-based Soft Robotic Glove Rehabilitation for Stroke
This paper presents the results of a study involving the use of a Brain-Computer Interface-based Soft Robotic Glove as a novel strategy in stroke rehabilitation. The technology uses the electroencephalogram signals from stroke patients to drive the assistive actions of the soft robotic glove to assist them in physically carrying out activities of daily living. The two-arm study showed prolonged improvements in FMA and ARAT scores although no significant intergroup differences were observed during the study. In addition, all of the patients in the BCI-SRG group also experienced a vivid kinesthetic illusion lasting beyond the active intervention period... Read more
Test Article
On the Safety of Human Body Communication
Human Body Communication (HBC) utilizes the human body as a physically secure, energy-efficient communication medium between devices on and around the body by sending electrical signals through the body. This paper provides a safety analysis of different modalities of HBC, for the first time, by comparing the current, electric field, magnetic field intensities from HBC with the established ICNIRP, IEEE, NIOSH safety standards through theory, analytical models and simulations. A study on a set of 7 subjects show that wearing an HBC enabled watch does not affect vital parameters including l heart rate, Mean Arterial Pressure, Respiration Rate, Peripheral Capillary Oxygen Saturation, Temperature... Read more
Test Article
Laparoscopic Renal Denervation System for Treating Resistant Hypertension: Overcoming Limitations of Catheter-based Approaches
The radical sympathectomy and percutaneous catheter-based renal denervation (RDN) are two techniques proposed to treat life-threatening resistant hypertension. However, sympathectomy has been abandoned due to the procedure being too invasive, and RDN resulted in variation in blood pressure reduction between patients due to suboptimal denervation. Thus, a method to effectively ablate renal nerves while not being very invasive is needed to treat the resistant hypertension patients. Here we propose a minimally invasive Laparoscopic Denervation System (LDS) to serve this unmet clinical need. The LDS employs a direct renal nerve ablation technique while not imparting thermal arterial damage... Read more