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

You might also read

Related Articles

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

Sort by

Same author

Free-breathing Dynamic MRI Analysis of Three-dimensional Diaphragm Curvatures in Pediatric Patients with Thoracic Insufficiency Syndrome.

Radiology. Cardiothoracic imaging·2026

Same author

FDG-PET/CT Parameters for distinguishing high and low microsatellite instability in colorectal cancer: A systematic review and Meta-analysis.

Annals of nuclear medicine·2026

Same author

A longitudinal, multi-omic atlas reveals the emergence of a spatially organized immunosuppressive ecosystem in resistant melanoma.

Cell reports. Medicine·2026

Same author

Evolving Landscape of Chest Wall Reconstruction: A Multimodality Imaging Approach.

Journal of thoracic imaging·2026

Same author

Open area segmentation in CT images based on pixel displacement and multi-view with application in the axillary and lower cervical regions.

Medical physics·2025

Same author

Spontaneous Pneumothorax: A Review of Underlying Etiologies and Diagnostic Imaging Modalities.

Tomography (Ann Arbor, Mich.)·2025

Search research articles

Related Experiment Video

Updated: Nov 17, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Segmentation evaluation with sparse ground truth data: Simulating true segmentations as perfect/imperfect as those

Jieyu Li¹, Jayaram K Udupa², Yubing Tong²

¹Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, 800 Dongchuan RD, Shanghai, 200240, China; Medical Image Processing Group, Department of Radiology, University of Pennsylvania, 602 Goddard building, 3710 Hamilton Walk, Philadelphia, PA, 19104, United States.

Medical Image Analysis

|February 15, 2021

Summary

This summary is machine-generated.

Generating accurate medical image segmentation data is costly and imprecise. SparseGT reduces workload by 80-96% using sparse manual annotations and deep learning for pseudo ground truth (p-GT) generation without sacrificing evaluation accuracy.

Keywords:

Ground truth generation Inter-segmenter variability Medical image segmentation Segmentation evaluation

More Related Videos

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Related Experiment Videos

Last Updated: Nov 17, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Area of Science:

Medical Imaging
Computer Vision
Biomedical Engineering

Background:

Accurate medical image segmentation requires fully annotated datasets, which are expensive and time-consuming to create.
Existing methods for generating ground truth (GT) segmentations face challenges with cost and precision.
Variability among human annotators is often overlooked in GT generation.

Purpose of the Study:

To propose a novel method, SparseGT, for efficient and precise ground truth (GT) generation in medical image segmentation.
To significantly reduce the manual workload in creating high-quality GT data.
To evaluate the impact of GT variability on segmentation algorithm performance.

Main Methods:

Developed SparseGT, a method that leverages human annotator variability to minimize manual effort in GT generation.
Generated pseudo ground truth (p-GT) segmentations using a fraction of manual annotations on sparsely selected slices, with automatic filling of remaining slices.
Investigated different sparseness levels and slice selection strategies (uniform, non-uniform, interpolation) combined with deep learning (DL) for segmentation filling.

Main Results:

SparseGT achieved substantial manual workload reduction, ranging from approximately 80-96%, by using DL-based segmentation filling on uniformly selected sparse slices.
Evaluation accuracy was maintained compared to fully manual GT, demonstrating the efficacy of p-GT.
Non-uniform slice selection proved advantageous for objects with irregular shape changes, while interpolation offered significant workload reduction without a training stage.

Conclusions:

SparseGT enables over 90% workload reduction in GT generation without compromising evaluation accuracy for medical image segmentation.
The optimal strategy and sparseness level for p-GT creation are dependent on the specific object and application.
The proposed method offers a practical solution for creating large-scale, high-quality annotated datasets efficiently.