A Physics-Driven Smartphone Framework for Remote Uroflowmetry Using Computer Vision
Abstract
Uroflowmetry is routinely used in urology to characterize urinary flow during voiding and to support assessment of lower urinary tract dysfunction. In conventional testing, the patient uses a dedicated collection device equipped with a calibrated transducer. This arrangement generally limits testing to clinical facilities, adds equipment and maintenance requirements, does not retain a direct visual record of the void, and may influence normal voiding behavior. This study presents a physics-informed video analysis framework in which a three-tier computer-vision architecture is used instead of dedicated flow-rate acquisition hardware. A smartphone recording is scaled using a fixed 26 cm physical reference and passed through a processing pipeline comprising background subtraction (MOG2), region-of-interest (ROI) locking, width-based gating, morphological cleanup, vertical dilation, and geometric (aspect-ratio) filtering to distinguish the stream from the surrounding body, hands, and background. Velocity tracking and volume normalization convert the isolated stream into a clinically meaningful flow curve, from which metrics including peak flow rate (Qmax), average flow rate, flow time, voiding time, time to Qmax, and hesitancy are derived. A confidence-weighted ensemble fuses top- and side-view recordings for improved robustness. The resulting workflow is implemented as an end-to-end clinical web platform: a React-based frontend for patient intake, video upload, and report viewing; a FastAPI backend providing JWT-authenticated, role-based endpoints for patient management, analysis orchestration, and report/email delivery; and cloud-based media storage. This work is presented as a proposed and implemented system architecture; quantitative validation results, accuracy figures, and dataset-level evaluation are not yet available and are identified as required future work. The principal contribution is a smartphone-based acquisition approach that avoids dedicated uroflow transducer hardware that extends existing AI-based uroflow curve-classification research, which assumes a transducer-derived signal, into the signal-acquisition stage itself.
References
H.-H. Huang, P.-Y. Cheng, and C.-Y. Tsai, “Exploring artificial intelligence in functional urology: A comprehensive review,” Urological Science, vol. 36, no. 1, pp. 2–10, 2025, doi: 10.1097/us9.0000000000000057.
“Machine Learning for Uroflow Analysis” (“Paper1 Study”), as referenced in project source material, 2024. [DATA REQUIRED — this source could not be independently verified; a matching publication with the described SVM/neural-network methodology and this exact title was not found. Do not include in a final submission until the correct source is confirmed and re-cited.]
L. E. Chew, J. H. Hannick, L. L. Woo, J. K. Weaver, and M. S. Damaser, “The future of urodynamics: Innovations, challenges, and possibilities,” Neurourology and Urodynamics, vol. 45, no. 2, pp. 293–298, 2026 (published online 14 May 2025), doi: 10.1002/nau.70074.
M. Plata, J. Azuero, F. Daza, M. Rojas-Rivillas, V. Garcia, A. Gutierrez, S. Cañar, T. Rodriguez, S. Gomez, and L. Giraldo, “AI-based platform for automated uroflowmetry curve morphology classification,” presented at the International Continence Society (ICS) / EUS Annual Meeting, Abstract 557, Sept. 19, 2025.
OpenCV Development Team, OpenCV Library Documentation — Background Subtraction (MOG2) and Contour Analysis. [DATA REQUIRED: access date/URL, as cited in project source material]
S. Ramírez, FastAPI: High-Performance Web Framework for Building APIs with Python, FastAPI Documentation. [DATA REQUIRED: access date/URL]
Meta Open Source, React 19 — A JavaScript Library for Building User Interfaces, React Documentation. [DATA REQUIRED: access date/URL]
M. J. Drake et al., Fundamentals of Urodynamic Practice — Uroflowmetry Principles and Interpretation. [DATA REQUIRED: publisher, edition, year, page numbers]
P. Virtanen et al., “SciPy 1.0: Fundamental algorithms for scientific computing in Python,” Nature Methods, vol. 17, pp. 261–272, 2020, doi: 10.1038/s41592-019-0686-2. (Note: this is the well-known, independently verifiable SciPy 1.0 paper; confirm it is indeed the source your project intended to cite before finalizing.)
Project Repository README, “Uroflow Computer Vision Analysis System” (clean-doc_ag / Dockothon). [DATA REQUIRED: repository URL, access date]
Refbacks
- There are currently no refbacks.