Non-Contact Breathing Monitoring Using Sleep Breathing Detection Algorithm (SBDA) Based on UWB Radar Sensors.

Ultra-wideband radar application for sleep breathing monitoring is hampered by the difficulty of obtaining breathing signals for non-stationary subjects. This occurs due to imprecise signal clutter removal and poor body movement removal algorithms for extracting accurate breathing signals. Therefore, this paper proposed a Sleep Breathing Detection Algorithm (SBDA) to address this challenge. First, SBDA introduces the combination of variance feature with Discrete Wavelet Transform (DWT) to tackle the issue of clutter signals. This method used Daubechies wavelets with five levels of decomposition to satisfy the signal-to-noise ratio in the signal. Second, SBDA implements a curve fit based sinusoidal pattern algorithm for detecting periodic motion. The measurement was taken by comparing the R-square value to differentiate between chest and body movements. Last but not least, SBDA applied the Ensemble Empirical Mode Decomposition (EEMD) method for extracting breathing signals before transforming the signal to the frequency domain using Fast Fourier Transform (FFT) to obtain breathing rate. The analysis was conducted on 15 subjects with normal and abnormal ratings for sleep monitoring. All results were compared with two existing methods obtained from previous literature with Polysomnography (PSG) devices. The result found that SBDA effectively monitors breathing using IR-UWB as it has the lowest average percentage error with only 6.12% compared to the other two existing methods from past research implemented in this dataset.

Loss of intercellular bridges in the depth of invasion measurement area is a novel negative prognostic factor for oral squamous cell carcinoma: A retrospective study.

OBJECTIVE: This study aimed to evaluate intercellular bridges in the depth of invasion (DOI) measurement area as prognostic factors in oral squamous cell carcinoma (OSCC). STUDY DESIGN: The mode of invasion was determined based on the Yamamoto-Kohama classification system by observing the hematoxylin-eosin-stained whole-slide images of specimens obtained from 78 patients with OSCC, and the clinicopathologic features were characterized. The presence of intercellular bridges was analyzed in 46 patients with Yamamoto-Kohama classification grade ≥3 whose DOI was measured by dividing the measurement area into 3 parts: the surface, center, and front of the tumor. RESULTS: Univariate analyses identified lymph node metastasis, loss of intercellular bridges in the DOI measurement area, DOI of ≥4500 µm, and pattern of invasion 4C-4D as negative prognostic factors. Multivariate analyses revealed that lymph node metastasis and the loss of intercellular bridges in the entire area were independent factors, with hazard ratios of 9.34 (95% confidence interval, 2.09-42.03; P = .003) and 3.64 (95% confidence interval, 1.10-11.99; P = .045), respectively. CONCLUSIONS: Loss of intercellular bridges in the DOI measurement area is a negative prognostic factor for OSCC and may be useful in selecting treatment.

LASOR: Learning Accurate 3D Human Pose and Shape via Synthetic Occlusion-Aware Data and Neural Mesh Rendering.

A key challenge in the task of human pose and shape estimation is occlusion, including self-occlusions, object-human occlusions, and inter-person occlusions. The lack of diverse and accurate pose and shape training data becomes a major bottleneck, especially for scenes with occlusions in the wild. In this paper, we focus on the estimation of human pose and shape in the case of inter-person occlusions, while also handling object-human occlusions and self-occlusion. We propose a novel framework that synthesizes occlusion-aware silhouette and 2D keypoints data and directly regress to the SMPL pose and shape parameters. A neural 3D mesh renderer is exploited to enable silhouette supervision on the fly, which contributes to great improvements in shape estimation. In addition, keypoints-and-silhouette-driven training data in panoramic viewpoints are synthesized to compensate for the lack of viewpoint diversity in any existing dataset. Experimental results show that we are among the state-of-the-art on the 3DPW and 3DPW-Crowd datasets in terms of pose estimation accuracy. The proposed method evidently outperforms Mesh Transformer, 3DCrowdNet and ROMP in terms of shape estimation. Top performance is also achieved on SSP-3D in terms of shape prediction accuracy. Demo and code will be available at https://igame-lab.github.io/LASOR/.

Noise-Reducing Fabric Electrode for ECG Measurement.

In this work, we propose a fabric electrode with a special structure that can play the role of a noise reduction filter. Fabric electrodes made of the conductive fabric have been used for long-term ECG measurements because of their flexibility and non-invasiveness; however, due to the large impedance between the skin and the fabric electrodes, noise is easily introduced into the ECG signal. In contrast to conventional work, in which chip-type passive elements are glued to the electrode to reduce noise, the proposed electrode can obtain a noise-reduced ECG by changing the structure of fabric. Specifically, the proposed electrode was folded multiple times to form a capacitor with a capacitance of about 3 nF. It is combined with the skin-electrode impedance to form a low-pass filter. In the experiment, we made a prototype of the electrodes and measured ECG at rest and during EMG-induced exercise. As a result, the SNR values at rest and during exercise were improved about 12.02 and 10.29 dB, respectively, compared with the fabric electrode without special structure. In conclusion, we have shown that changing the fabric electrode structure effectively removes noise in ECG measurement.

The Use of Augmented Reality Technology in Medical Specimen Museum Tours.

Human anatomical specimen museums are commonly used by medical, nursing, and paramedical students. Through dissection and prosection, the specimens housed in these museums allow students to appreciate the complex relationships of organs and structures in more detail than textbooks could provide. However, it may be difficult for students, particularly novices, to identify the various parts of these anatomical structures without additional explanations from a docent or supplemental illustrations. Recently, augmented reality (AR) has been used in many museum exhibits to display virtual objects in videos captured from the real world. This technology can significantly enhance the learning experience. In this study, three AR-based support systems for tours in medical specimen museums were developed, and their usability and effectiveness for learning were examined. The first system was constructed using an AR marker. This system could display virtual label information for specimens by capturing AR markers using a tablet camera. Individual AR markers were required for all specimens, but their presence in and on the prosected specimens could also be obtrusive. The second system was developed to set the specimen image itself as an image marker, as most specimens were displayed in cross section. Visitors could then obtain the label information presented by AR without any markers intruding on the display or anatomical specimens. The third system was comprised of a head-mounted display combined with a natural click interface. The system could provide visitors with an environment for the natural manipulation of virtual objects with future scalability.