Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Kidney Structure

Kidney Structure

The kidneys are two large bean-shaped organs located in the upper abdomen. They filter the blood several times a day to remove toxins and rebalance water and electrolytes of the circulatory system via the renal veins. The kidneys receive blood directly from the heart via the renal arteries. These arteries enter the kidney at the hilum, the concave surface of the bean, where they branch and divide into smaller vessels and capillaries.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Fluid-mediated nuclearity control in heterogeneous polyolefin catalysis.

Nature communications·2026

Same author

Layer-number-parity-dependent abnormal magnetic ordering in few-layer CrI3 on N-face AlN substrate.

Nature communications·2026

Same author

Development and validation of artificial intelligence-based model for bladder cancer immunophenotyping using whole slide images.

NPJ precision oncology·2026

Same author

Comparison of the learning curves of the osteotomy guide robot and guide plate-based robot-assisted total knee arthroplasty.

Arthroplasty (London, England)·2026

Same author

JUNB transcriptional regulation of KRT20 via ITGB1 activates PI3K/AKT signaling pathway against fibrosis-induced by renal injury.

Biology direct·2026

Same author

MM-CPI: A multimodal fusion framework for compound-protein interaction prediction.

International journal of biological macromolecules·2026

Same journal

Tranexamic acid in endoscopic enucleation of the prostate: does surgeon preference confound the protective effect?

World journal of urology·2026

Same journal

Holmium laser enucleation of the prostate as salvage therapy for benign prostatic obstruction after multiple prior surgical interventions.

World journal of urology·2026

Same journal

Testing reliability of pubourethral ligament hemostat forceps support test for diagnosis of stress incontinence.

World journal of urology·2026

Same journal

Safety and efficacy of different surgical approaches in single-port robot-assisted radical prostatectomy based on propensity score matching analysis.

World journal of urology·2026

Same journal

Intrarenal pressure and clinical outcomes during suction-assisted versus conventional percutaneous nephrolithotomy: a systematic review and meta-analysis.

World journal of urology·2026

Same journal

AI-driven model for early failure prediction after HIFU integrating immediate post-ablation ultrasound and clinical data.

World journal of urology·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 28, 2025

Author Spotlight: Developing a Bedside Protocol for Kidney and Genitourinary Ultrasonography

Author Spotlight: Developing a Bedside Protocol for Kidney and Genitourinary Ultrasonography

Published on: June 21, 2024

UroAngel: a single-kidney function prediction system based on computed tomography urography using deep learning.

Qingyuan Zheng^1,2, Xinmiao Ni^1,2, Rui Yang^1,2

¹Department of Urology, Renmin Hospital of Wuhan University, 99 Zhang Zhi-Dong Road, Wuhan, 430060, Hubei, People's Republic of China.

World Journal of Urology

|April 16, 2024

Summary

This summary is machine-generated.

A new deep learning system, UroAngel, accurately predicts single-kidney function in obstructive nephropathy patients using CT urography images. This non-invasive method offers a reliable alternative for assessing kidney function and guiding treatment.

Keywords:

Computed tomography urography Convolutional neural network Deep learning Glomerular filtration rate Obstructive nephropathy

More Related Videos

Whole-Kidney Three-Dimensional Staining with CUBIC

Whole-Kidney Three-Dimensional Staining with CUBIC

Published on: July 18, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 28, 2025

Author Spotlight: Developing a Bedside Protocol for Kidney and Genitourinary Ultrasonography

Author Spotlight: Developing a Bedside Protocol for Kidney and Genitourinary Ultrasonography

Published on: June 21, 2024

Whole-Kidney Three-Dimensional Staining with CUBIC

Whole-Kidney Three-Dimensional Staining with CUBIC

Published on: July 18, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Nephrology

Background:

Accurate estimation of glomerular filtration rate (GFR) is vital for managing obstructive nephropathy (ON).
Current methods for assessing single-kidney function in ON can be invasive or lack precision.
There is a need for non-invasive and convenient tools to predict kidney function in ON patients.

Purpose of the Study:

To develop and validate UroAngel, a deep learning system for non-invasive prediction of single-kidney function in ON patients.
To assess the accuracy of UroAngel compared to established equations and expert radiologists.

Main Methods:

Retrospective collection of computed tomography urography (CTU) images and reports from 520 ON patients.
Utilized a 3D U-Net model for renal parenchyma segmentation.
Employed a logistic regression model for renal function level prediction, validated against MDRD, CKD-EPI equations, and expert radiologists.

Main Results:

The 3D U-Net model achieved accurate renal cortex segmentation (Dice similarity coefficient: 0.861).
UroAngel demonstrated high performance in predicting renal function stage with 0.918 accuracy.
UroAngel outperformed MDRD, CKD-EPI equations, and two expert radiologists in predictive accuracy.

Conclusions:

An automated 3D U-Net-based system (UroAngel) can directly predict single-kidney function stage from CTU images.
UroAngel provides an accurate, reliable, convenient, and non-invasive method for assessing kidney function in ON patients.
This deep learning approach represents a novel advancement in managing obstructive nephropathy.