Quantitative assessment of velocity and flow using compressed SENSE in children and young adults with adequate acquired temporal resolution

Background Phase contrast (PC) cardiovascular magnetic resonance (CMR) imaging with parallel imaging acceleration is established and validated for measuring velocity and flow. However, additional acceleration to further shorten acquisition times would be beneficial in patients with complex vasculature who need multiple PC-CMR measurements, especially pediatric patients with higher heart rates. Methods PC-CMR images acquired with compressed sensitivity encoding (C-SENSE) factors of 3 to 6 and standard of care PC-CMR with sensitivity encoding (SENSE) factor of 2 (S2) acquired as part of clinical CMR examinations performed between November 2020 and January 2021 were analyzed retrospectively. The velocity and flow through the ascending aorta (AAo), descending aorta (DAo), and superior vena cava (SVC) in a transverse plane at the level of pulmonary artery bifurcation were compared. Additionally, frequency power distribution and dynamic time warp distance were calculated for these acquisitions. To further validate the adequate temporal resolution requirement, patients with S2 PC-CMR in the same acquisition plane were added in frequency power distribution analysis. Results Twenty-eight patients (25 males; 15.9 ± 1.9 years; body surface area (BSA) 1.7 ± 0.2 m2; heart rate 81 ± 16 bpm) underwent all five PC-CMR acquisitions during the study period. An additional 22 patients (16 males; 17.5 ± 7.7 years; BSA 1.6 ± 0.5 m2; heart rate 91 ± 16 bpm) were included for frequency power spectrum analysis. As expected, scan time decreased with increasing C-SENSE acceleration factor = 3 (37.5 ± 6.5 s, 26.4 ± 7.6%), 4 (28.1 ± 4.9 s, 44.7 ± 5.6%), 5 (21.6 ± 3.6 s, 57.6 ± 4.4%), and 6 (19.1 ± 3.2 s, 62.3 ± 4.2%) relative to SENSE = 2 (51.3 ± 10.1 s) PC-CMR acquisition. Mean peak velocity, net flow, and cardiac output were comparable (p > 0.87) between the five PC-CMR acquisitions with mean differences less than < 4%, < 2%, and < 3% respectively. All individual blood vessels showed a non-significant dependence of difference in fmax99 (< 4 Hz, p > 0.2), and dynamic time warp distance (p > 0.3) on the C-SENSE acceleration factor used. There was a strongly correlated (r = 0.74) increase in fmax99 (10.5 ± 2.2, range: 7.1–16.4 Hz) with increasing heart rate. The computed minimum required cardiac phase number was 15 ± 2.0 (range: 11–20) over the heart rate of 86 ± 15 bpm (range: 58–113 bpm). Conclusions Stroke volume, cardiac output, and mean peak velocity measurements using PC-CMR with C-SENSE of up to 6 agree with measurements by standard of care PC-CMR with SENSE = 2 and resulted in up to a 65% reduction in acquisition time. Adequate temporal sampling can be ensured by acquiring 20 cardiac phases throughout the entire cardiac cycle over a wide range of pediatric and young adult heart rates.

End-to-End Deep Learning by MCU Implementation: An Intelligent Gripper for Shape Identification

This paper introduces a real-time processing and classification of raw sensor data using a convolutional neural network (CNN). The established system is a microcontroller-unit (MCU) implementation of an intelligent gripper for shape identification of grasped objects. The pneumatic gripper has two embedded accelerometers to sense acceleration (in the form of vibration signals) on the jaws for identification. The raw data is firstly transferred into images by short-time Fourier transform (STFT), and then the CNN algorithm is adopted to extract features for classifying objects. In addition, the hyperparameters of the CNN are optimized to ensure hardware implementation. Finally, the proposed artificial intelligent model is implemented on a MCU (Renesas RX65N) from raw data to classification. Experimental results and discussions are introduced to show the performance and effectiveness of our proposed approach.

Hand Gesture Controlled Robot using Arduino and MPU6050

As the use of robots in different fields has been increasing day by day in doing different types works. To make some complicated works easy in industrial areas, military purpose and in any places where human can’t go, the gesture controlled robot are used in which the motion of robot is dependent on the human hand. We are using the MPU6050 sensor which has 6-axis of motion tracking device in which accelerometer has 3-axis, gyroscope has the other 3-axis and it also has an additional feature like temperature sensor. Where the acceleration is a keyword of an Inertial Measurement Unit. Accelerometer meter is a device used to sense acceleration off gravity of directions like forward, backward, left and right. The movement of the robot has been controlled by the accelerometer. By which the information from RF Transmitter to the RF Receiver has been pass through wireless communication system. The other parts are control Arduino in which the code is dumped.