A new single-sagittal-plane deep learning approach for continuous bladder volume monitoring: a feasibility study
Ultrasonography · 01.07.2026 · 45 (4) · 393-401
DOI: 10.14366/usg.25258 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ultrasonography, erschienen am 01.07.2026. Verfasst von Junhwan Kwon und 4 weiteren Autor:innen. Beteiligte Einrichtung: Edgecare Inc., Seoul, Korea. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: Ministry of Science and ICT, Ministry of Trade, Industry and Energy, Ministry of Health and Welfare.
Abstract (Originalsprache)
Purpose
Conventional ultrasound-based bladder volumetry multiplies three orthogonal diameters and applies a heuristic shape coefficient. This approach requires near-simultaneous transverse and sagittal imaging and is vulnerable to interplane misregistration and coefficient-dependent bias. This study evaluated whether a single sagittal B-mode image can provide accurate, patient-specific bladder volume estimation by leveraging sagittal morphology, perivesical echotexture, and latent image features associated with overall bladder geometry.
Methods
In this Institutional Review Board–approved, single-center study, participants were scanned in the supine position, and bladder volume was referenced to immediate Foley catheter drainage. Segmentation masks were independently annotated by two sonographers and adjudicated by a urologist. Maximum sagittal length was extracted using OpenCV and included as an auxiliary scalar input. A single-stage deep learning model was developed that receives one sagittal B-mode image and its expert-annotated segmentation mask as input. The model used a lightweight convolutional neural network backbone with integrated self-attention to capture global echotextural cues. Performance on a held-out test set (n=53) was assessed using linear regression, Bland-Altman analysis, mean absolute error, and mean absolute percentage error.
Results
The model demonstrated a strong correlation with catheter-derived volumes (R²=0.87). Bland-Altman analysis showed a mean bias of −3.96±48.44 mL, with limits of agreement from −98.90 to +90.98 mL. Stratified error analysis showed a mean absolute error of 14.15 mL for volumes of 0–100 mL and a mean absolute percentage error of 16.64% for volumes ≥100 mL. Attention maps emphasized the bladder wall and perivesical soft tissues, suggesting reliance on contextual echotexture.
Conclusion
A deep learning framework using a single sagittal plane estimated bladder volume with accuracy approaching that of two-plane techniques while simplifying image acquisition and eliminating reliance on fixed shape coefficients.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Edgecare Inc., Seoul, Korea.
- Anesthesia and Pain Research Institute, Yonsei University College of Medicine, Seoul, Korea.
- Medical Solution Institute, Sogang University, Seoul, Korea.
- Department of Urology, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea.
- Department of Electronic Engineering, Sogang University, Seoul, Korea.
- Department of Biomedical Engineering, Sogang University, Seoul, Korea.
Förderung
- Ministry of Science and ICT
- Ministry of Trade, Industry and Energy
- Ministry of Health and Welfare
- Ministry of Food and Drug Safety
- Severance Hospital Research Fund for Clinical excellence
Zitieren
APA
Kwon, J., Song, I., Park, S., Lee, J., & Yoo, Y. (2026). A new single-sagittal-plane deep learning approach for continuous bladder volume monitoring: a feasibility study. Ultrasonography, 45(4), 393-401. https://doi.org/10.14366/usg.25258
Vancouver
Kwon J, Song I, Park S, Lee J, Yoo Y. A new single-sagittal-plane deep learning approach for continuous bladder volume monitoring: a feasibility study. Ultrasonography. 2026;45(4):393-401. doi:10.14366/usg.25258
BibTeX
@article{Kwon2026,
author = {Kwon, Junhwan and Song, Ilseob and Park, Sangeun and Lee, Jongsoo and Yoo, Yangmo},
title = {A new single-sagittal-plane deep learning approach for continuous bladder volume monitoring: a feasibility study},
journal = {Ultrasonography},
year = {2026},
volume = {45},
number = {4},
pages = {393--401},
doi = {10.14366/usg.25258}
}
EUVIMED