Bladder volume assessments are crucial for managing urinary disorders. Ultrasound imaging (US) is a preferred noninvasive, cost-effective imaging modality for bladder observation and volume measurements. However, the high operator dependency of US is a major challenge due to the difficulty in evaluating ultrasound images without professional expertise. To address this issue, image-based automatic bladder volume estimation methods have been introduced, but most conventional methods require high-complexity computing resources that are not available in point-of-care (POC) settings. Therefore, in this study, a deep learning-based bladder volume measurement system was developed for POC settings using a lightweight convolutional neural network (CNN)-based segmentation model, which was optimized on a low-resource system-on-chip (SoC) to detect and segment the bladder region in ultrasound images in real time. The proposed model achieved high accuracy and robustness and can be executed on the low-resource SoC at 7.93 frames per second, which is 13.44 times faster than the frame rate of a conventional network with negligible accuracy drawbacks (0.004 of the Dice coefficient). The feasibility of the developed lightweight deep learning network was demonstrated using tissue-mimicking phantoms.

No abstract

Inspecting the sealing integrity of lead tabs is an important means of ensuring the reliability and safety of pouch-type lithium-ion (Li-ion) batteries with a thin multi-layered aluminum (Al) laminated film. This paper presents a new air-coupled ultrasonic non-destructive testing (NDT) inspection method based on leaky Lamb wave transmission; and reception for evaluating the sealing integrity between the lead tab and the Al pouch film. The proposed method uses the critical incidence angle between the air and the layer with the fastest Lamb wave velocity to maximize the signal-to-noise ratio in the through-transmission mode. To determine the critical incidence angle, phantom experiments with two test pieces (i.e., an Al tab and an Al tab sealed with an Al pouch film) are conducted. In addition, 2D scans are performed at various incidence angles for an inhouse pouch-type Li-ion battery with a 1-mm-wide foreign material inserted as a defect. At the critical incidence angle (i.e., 22°), the proposed air-coupled ultrasonic NDT method in through-transmission mode successfully identifies the shape and location of the defect through c-scan image reconstruction. These preliminary results indicate that the proposed air-coupled ultrasonic NDT method with leaky Lamb waves can be used to inspect the sealing integrity of Li-ion pouch batteries in dry test conditions.