Related Experiment Video

Updated: Aug 8, 2026

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.9K

Artificial intelligence-assisted quantification and assessment of whole slide images for pediatric kidney disease

Chunyue Feng1,2, Kokhaur Ong3, David M Young4,5

  • 1Department of Nephrology, Children's Hospital, Zhejiang University School of Medicine, Hangzhou 310000, China.

Bioinformatics (Oxford, England)
|December 7, 2023
PubMed

Insights

An AI tool, AI-based Pediatric Kidney Diagnosis (APKD), aids pathologists in diagnosing pediatric kidney disease by accurately segmenting and classifying kidney structures. APKD achieves high accuracy and is significantly faster than manual detection.

Area of Science:

  • Nephrology
  • Pathology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Pediatric kidney disease significantly impacts child development and often requires invasive renal biopsies for diagnosis.
  • Pathological evaluation of kidney biopsies is labor-intensive and susceptible to human error.
  • Accurate segmentation and classification of pediatric kidney structures are crucial for timely diagnosis and treatment.

Purpose of the Study:

  • To develop and validate an artificial intelligence (AI) method, AI-based Pediatric Kidney Diagnosis (APKD), for assisting pathologists in analyzing pediatric kidney biopsies.
  • To improve the accuracy and efficiency of diagnosing pediatric kidney diseases through automated analysis of histological structures.
  • To enable early identification of glomerular abnormalities for improved patient outcomes.

Main Methods:

  • Development of the AI-based Pediatric Kidney Diagnosis (APKD) model using a dataset of 2935 pediatric kidney disease patients.
  • Manual annotation of 93,932 histological structures by three expert nephropathologists for model training and validation.
  • Quantitative evaluation of APKD's performance using accuracy metrics, Spearman correlation coefficient, and intraclass correlation coefficient (ICC).

Main Results:

  • APKD achieved an average accuracy of 94% across all kidney structure categories, with 99% accuracy for glomeruli.
  • Strong correlation was observed between APKD and manual detection for glomeruli (Spearman's r = 0.98, ICC = 0.98).
  • APKD demonstrated a 5.5-fold increase in speed for glomeruli segmentation compared to manual methods and identified key pathological features.

Conclusions:

  • The AI-based Pediatric Kidney Diagnosis (APKD) system shows high accuracy and efficiency in segmenting and classifying pediatric kidney structures.
  • APKD can assist pathologists by reducing diagnostic time and potential errors, facilitating earlier and more accurate diagnosis of pediatric kidney diseases.
  • The AI model's ability to identify specific pathological features aids in the early detection of glomerular capillary wall abnormalities, improving diagnostic capabilities.
Abstract

More Related Videos

Use of 3D Robotic Ultrasound for In Vivo Analysis of Mouse Kidneys08:21

Use of 3D Robotic Ultrasound for In Vivo Analysis of Mouse Kidneys

Published on: August 12, 2021

3.5K
Whole-Kidney Three-Dimensional Staining with CUBIC04:31

Whole-Kidney Three-Dimensional Staining with CUBIC

Published on: July 18, 2022

3.9K

Related Concept Videos

Kidney Structure01:45

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.
Imaging Studies II: Ultrasonography01:24

Imaging Studies II: Ultrasonography

IntroductionUltrasonography, or renal ultrasound, is a noninvasive medical imaging technique that uses high-frequency sound waves to visualize the kidneys, ureters, bladder, and surrounding tissues.Indications for Urinary System UltrasonographyUrinary system ultrasonography is indicated in various clinical scenarios, such as:Kidney Stones (Urolithiasis): To detect and monitor the size and presence of kidney or urinary tract stones.Hydronephrosis: To assess the dilation of the renal pelvis and...
Imaging Studies VII: Vascular Imaging01:19

Imaging Studies VII: Vascular Imaging

DefinitionRenal angiography, also known as renal arteriography, is an imaging technique used to obtain a comprehensive view of blood flow and the vascular structure of blood vessels in the kidneys and surrounding areas.PurposeRenal angiography detects blood vessel abnormalities in the kidneys, such as aneurysms, stenosis, thrombosis, vascular tumors, and renal artery stenosis. It evaluates kidney function and guides interventional treatments like angioplasty or stent placement.Pre-Procedure...