Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
-
Annu Int Conf IEEE Eng Med Biol Soc · Jul 2019
Heart Rate Estimation using PPG signal during Treadmill Exercise.
An instantaneous heart rate tracking method is presented to estimate beat-to-beat heart rates from wearable photoplethysmographic (PPG) sensors that are affected by nonstationary motion artifacts. Many state-of-the-art heart rate tracking methods estimate heart rates using an 8-second average instead of the instantaneous heart rates which especially fluctuate during exercises. In this paper, our novel technique showed accurate heart rate estimation from PPG signals acquired from wearable wrist and forehead devices which are affected by motion artifacts especially when subjects were running on a treadmill. ⋯ We present preliminary results compared with one of the most accurate state-of-the-art techniques [12]. The results were derived from two different datasets: IEEE Signal Processing Cup Challenge and our own dataset obtained from a wrist and a forehead PPG sensor, respectively, with subjects running on a treadmill. We obtained the average absolute error of 2.93 beats per minute and average relative error of 2.31 beats per minute, which are 121% and 119% improvement, respectively, when compared to the previously published algorithm [12].
-
Annu Int Conf IEEE Eng Med Biol Soc · Jul 2019
Relationship Between Offline and Online Metrics in Myoelectric Pattern Recognition Control Based on Target Achievement Control Test.
Offline classification accuracy (CA) is a widely accepted measure to evaluate the performance in pattern recognition based myoelectric scheme. However, whether offline metrics are able to be transferred to evaluate or predict online performance is still unclear. In this study, the relationship between offline metrics and online metrics are analyzed. ⋯ Completion rate, completion time and path efficiency are considered as online metrics. Our results demonstrate that online completion rate is strongly correlated with offline global CA and class-wise accuracy std. The correlation between offline and online performance metrics indicates it is reasonable to develop efficient algorithm in offline scenario if both global CA and class-wise accuracy are considered.
-
Annu Int Conf IEEE Eng Med Biol Soc · Jul 2019
Prediction of Patient-specific Acute Hypotensive Episodes in ICU Using Deep Models.
Forecasting acute hypotensive episodes (AHE) in intensive care patients has been of recent interest to researchers in the healthcare domain. Advance warning of an impending AHE may give care providers additional information to help mitigate the negative clinical impact of a serious event such as an AHE or prompt a search for an evolving disease process. However, the currently accepted definition of AHE is restrictive does not account for inter-patient variability. ⋯ Next, we utilize a deep learning-based method to predict the onset of an AHE from multiple physiological readings for different definitions of the prediction task including variable input and gap lengths. Using a cohort of 538 patients, our model was able to successfully predict the onset of an AHE with an accuracy and AUC score of 0.80 and 0.87 respectively. Compared to a baseline logistic regression model, our model outperforms the baseline in most of the definitions of the prediction task.
-
Annu Int Conf IEEE Eng Med Biol Soc · Jul 2019
Pancreas Segmentation in Abdominal CT Scans using Inter-/Intra-Slice Contextual Information with a Cascade Neural Network.
Automatic pancreas segmentation with high precision in Computed Tomography (CT) images is a fundamental issue in both medical image analysis and computer-aided diagnosis (CAD). However, pancreas segmentation is challenging because of the high variability in location and anatomy of the organs, while occupying only a very small part of the entire abdominal CT scans. Due to the rapid development of the CAD system and the urgent need for clinical treatment, the pancreas image segmentation with high precision is demanded. ⋯ Fully convolutional neural networks (FCN) are used to extract intra-slice contextual information for pancreas segmentation. Recurrent neural networks (RNNs) is introduced to extract inter-slice contextual information. With the setting bounding boxes, the proposed method outperforms the state-of-the-arts with an average Dice Similarity Coefficient (DSC) of 87.72 for NIH dataset with 4-fold cross-validation.
-
Annu Int Conf IEEE Eng Med Biol Soc · Jul 2019
A Simulation Study of Light Propagation in the Spinal Cord for Optogenetic Surface Stimulation.
For utilizing optogenetics in neuroscience research, a proper setup is necessary, which delivers sufficient light to target cells and minimizes unexpected side effects caused by light exposure. In this study, we were interested in the area of influence of optical surface stimulation on a spinal cord tissue. We built a 3D spinal cord structure of rat and utilized the Monte-Carlo methods to simulate the light transport in it. ⋯ In contrast, when we put the fiber on a lateral position, 0:8 mm away from the central line, relatively sufficient light intensity could be detected deep into the lamina 5 area. The experimental results obtained herein suggest that tissue type and the position of stimulation could greatly affect the area of influence of light stimulation in a 3D spinal cord. It is important to consider the location of the interested neural pathways and plan a proper stimulation site before conducting optogenetic surface stimulation of the spinal cord.