Search research articles

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

The Banff 2024 Kidney Meeting Report: Rejection as a spectrum of phenotypes and focus on differential diagnostic reasoning.

American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons·2026

Same author

Role of lupus nephritis classification systems in everyday clinical practice: a questionnaire-based survey of the Renal Pathology Society (RPS).

Clinical kidney journal·2026

Same author

Shared multicellular injury programs of acute and chronic kidney disease enable mechanistic patient stratification.

medRxiv : the preprint server for health sciences·2026

Same author

Discoidin Domain Receptor 1 Translocation to the Mitochondria Promotes Oxidative Stress and Apoptosis in Acute Kidney Injury.

Journal of the American Society of Nephrology : JASN·2026

Same author

MedPTQ: a practical pipeline for real post-training quantization in 3D medical image segmentation.

Journal of medical imaging (Bellingham, Wash.)·2026

Same author

Signal Strength Aware Latent Spaces Reveal Molecularly Distinct Substructures within Human Kidney Tissue.

bioRxiv : the preprint server for biology·2026

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

Search research articles

Related Experiment Video

Updated: Nov 22, 2025

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Published on: May 3, 2018

Instance segmentation for whole slide imaging: end-to-end or detect-then-segment.

Aadarsh Jha¹, Haichun Yang², Ruining Deng¹

¹Vanderbilt University, Department of Electrical Engineering and Computer Science, Nashville, United States.

Journal of Medical Imaging (Bellingham, Wash.)

|January 11, 2021

Summary

A detect-then-segment approach outperforms end-to-end Mask-RCNN for glomeruli segmentation in kidney whole slide images. This method preserves high-resolution details, crucial for accurate analysis in renal pathology research.

Keywords:

Glomeruli Mask-RCNN U-Net deep learning segmentation whole slide imaging

More Related Videos

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Related Experiment Videos

Last Updated: Nov 22, 2025

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Automated Slide Scanning and Segmentation in Fluorescently-labeled Tissues Using a Widefield High-content Analysis System

Published on: May 3, 2018

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Area of Science:

Digital Pathology
Computer Vision
Renal Pathology

Background:

Automatic glomeruli segmentation in kidney whole slide imaging (WSI) is vital for renal pathology research.
End-to-end instance segmentation methods like Mask-RCNN are standard but may lose information from high-resolution WSI due to downsampling.
Glomeruli in high-resolution WSI can exceed 1000 pixels, posing challenges for standard segmentation pipelines.

Purpose of the Study:

To compare the performance of an end-to-end instance segmentation framework (Mask-RCNN) with a proposed detect-then-segment framework for glomeruli segmentation in high-resolution WSI.
To comprehensively evaluate the detect-then-segment pipeline using different segmentation backbones (U-Net, DeepLab_v3), image resolutions, and color spaces (RGB, LAB).

Main Methods:

Comparison of Mask-RCNN (end-to-end) against a novel detect-then-segment pipeline.
Evaluation of the detect-then-segment pipeline utilizing U-Net and DeepLab_v3 backbones.
Assessment across six different image resolutions (e.g., 0.25, 0.5, 1, 2, 4, 8 µm/pixel) and two color spaces (RGB, LAB).

Main Results:

The detect-then-segment pipeline with DeepLab_v3 achieved a Dice Similarity Coefficient (DSC) of 0.953, outperforming the end-to-end Mask-RCNN's DSC of 0.902.
The study found no significant performance difference between RGB and LAB color spaces within the detect-then-segment framework.
The detect-then-segment approach demonstrated superior segmentation accuracy for high-resolution WSI objects.

Conclusions:

The detect-then-segment pipeline offers improved segmentation performance over end-to-end methods for glomeruli in high-resolution WSI.
This study provides valuable quantitative insights for selecting optimal segmentation strategies for glomeruli and similar biological structures in WSI.
The findings guide researchers in choosing accurate segmentation approaches for high-resolution pathological images.