A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study

Abstract

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.

Comparative Effectiveness of Two Models of Point-of-Care Ultrasound for Detection of Post-Void Residual Urine during Acute Ischemic Stroke: Preliminary Findings of Real-World Clinical Application

“…Bih et al [11] recommended an optimal correction coefficient of 0.72 for the entire data set and optimal correction coefficients of 0.66, 0.81, and 0.89 for triangular, ellipsoid, and cuboidal bladder shapes, respectively. Cho et al [17] developed a deep-learning measurement system for bladder volume for use in point-of-care settings. To achieve high accuracy, they used a segmentation model based on a lightweight convolutional neural network.…”

Detection of spondylosis deformans in thoracolumbar and lumbar lateral X-ray images of dogs using a deep learning network

“…To cope with the large variance in dog size (range: 1.64 kg−36 kg), the modified attention U-Net in this study was designed to have deeper feature extraction (i.e., multiscale features) than the original attention U-Net ( 22 ) architecture. The designed network extracts features at 7 levels, reducing the spatial resolution from (1024, 512) to ( 8 , 16 ) for height and width, respectively. The filter dimensions of the model ( F 1 , F 2 , F 3 , F 4 , F 5 , F 6 , F 7 ) were selected as 16, 32, 64, 128, 256, 512, and 1024, respectively.…”

Intelligent classifier for various degrees of coffee roasts using smart multispectral vision system

“…The recent widespread use of deep neural networks (DNNs) in artificial intelligence has led to advancements in image-related research (Cho et al, 2023;Karakanis & Leontidis, 2021;Saleh et al, 2023;Shuvo et al, 2021;Wang et al, 2022;Wei et al, 2020).…”

“…The nine-dimensional training data set based on IT8.7/2 color target D4 is presented in Table 1. RPNN offers superior recognition performance and fewer computational resource requirements compared with the lightweight deep learning approach used in (Cho et al, 2023;Karakanis & Leontidis, 2021;Saleh et al, 2023;Shuvo et al, 2021;Wang et al, 2022;Wei et al, 2020).…”