Cargando…

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

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 evalua...

Descripción completa

Detalles Bibliográficos
Autores principales: Cho, Hyunwoo, Song, Ilseob, Jang, Jihun, Yoo, Yangmo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10215791/
https://www.ncbi.nlm.nih.gov/pubmed/37237594
http://dx.doi.org/10.3390/bioengineering10050525
_version_ 1785048147470319616
author Cho, Hyunwoo
Song, Ilseob
Jang, Jihun
Yoo, Yangmo
author_facet Cho, Hyunwoo
Song, Ilseob
Jang, Jihun
Yoo, Yangmo
author_sort Cho, Hyunwoo
collection PubMed
description 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.
format Online
Article
Text
id pubmed-10215791
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102157912023-05-27 A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study Cho, Hyunwoo Song, Ilseob Jang, Jihun Yoo, Yangmo Bioengineering (Basel) Article 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. MDPI 2023-04-26 /pmc/articles/PMC10215791/ /pubmed/37237594 http://dx.doi.org/10.3390/bioengineering10050525 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cho, Hyunwoo
Song, Ilseob
Jang, Jihun
Yoo, Yangmo
A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study
title A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study
title_full A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study
title_fullStr A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study
title_full_unstemmed A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study
title_short A Lightweight Deep Learning Network on a System-on-Chip for Wearable Ultrasound Bladder Volume Measurement Systems: Preliminary Study
title_sort lightweight deep learning network on a system-on-chip for wearable ultrasound bladder volume measurement systems: preliminary study
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10215791/
https://www.ncbi.nlm.nih.gov/pubmed/37237594
http://dx.doi.org/10.3390/bioengineering10050525
work_keys_str_mv AT chohyunwoo alightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy
AT songilseob alightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy
AT jangjihun alightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy
AT yooyangmo alightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy
AT chohyunwoo lightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy
AT songilseob lightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy
AT jangjihun lightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy
AT yooyangmo lightweightdeeplearningnetworkonasystemonchipforwearableultrasoundbladdervolumemeasurementsystemspreliminarystudy