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

Meet NUM-ENRICH: A Collaborative National Effort to Extend and Harmonize Research Infrastructures Within the German Network University Medicine.

Studies in health technology and informatics·2026

Same author

Investigating the temporal dynamics and modeling of mid-level feature representations in humans.

Imaging neuroscience (Cambridge, Mass.)·2026

Same author

Clinically relevant differences in stress shielding between two short-stemmed femoral prostheses.

Archives of orthopaedic and trauma surgery·2025

Same author

Net2Brain: a toolbox to compare artificial vision models with human brain responses.

Frontiers in neuroinformatics·2025

Same author

Detection of Hepatitis C Virus Infection from Patient Sera in Cell Culture Using Semi-Automated Image Analysis.

Viruses·2025

Same author

Reply to: "Unlocking hope: HCV re-treatment strategy for patients with active hepatocellular carcinoma".

JHEP reports : innovation in hepatology·2024

Same journal

Age-Related Concentric Remodeling and Sex-Dependent Dimensional Variation in Left Ventricular Geometry: A Cardiac Magnetic Resonance Study.

Tomography (Ann Arbor, Mich.)·2026

Same journal

Opportunistic Screening for Low Bone Density Using Automated Vertebral Trabecular CT Attenuation from Low-Dose CT Acquired During FDG PET/CT: A Single-Center Retrospective Study.

Tomography (Ann Arbor, Mich.)·2026

Same journal

Machine Learning-Based Classification of BI-RADS 4 and BI-RADS 5 Microcalcifications in Mammography Combined with DCE-MRI for Malignant-Benign Discrimination.

Tomography (Ann Arbor, Mich.)·2026

Same journal

Image Quality Assessment of Diffusion-Weighted Imaging (DWI) and Its Impact on Apparent Diffusion Coefficient (ADC) as a Quantitative Imaging Biomarker for Predicting Response to Neoadjuvant Chemotherapy in High-Risk Early Breast Cancer.

Tomography (Ann Arbor, Mich.)·2026

Same journal

Relationship Between Cervical Central Canal and Neural Foraminal Dimensions in a Normative Population.

Tomography (Ann Arbor, Mich.)·2026

Same journal

AI-Based Scientific Manuscript Peer Review: Is It Ready for Adoption?

Tomography (Ann Arbor, Mich.)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 8, 2025

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

Evaluating Medical Image Segmentation Models Using Augmentation.

Mattin Sayed¹, Sari Saba-Sadiya², Benedikt Wichtlhuber¹

¹Clinic for Radiology and Nuclear Medicine, University Hospital, Goethe University Frankfurt, Theodor-Stern-Kai 7, 60590 Frankfurt am Main, Germany.

Tomography (Ann Arbor, Mich.)

|December 27, 2024

Summary

This summary is machine-generated.

This study introduces a new method to validate automated medical image segmentation models using data augmentation. This approach assesses segmentation accuracy without needing manual review, improving efficiency in clinical and research settings.

Keywords:

AI TotalSegmentator augmentation automated segmentation evaluation medical imaging

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

Related Experiment Videos

Last Updated: May 8, 2025

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

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

Area of Science:

Medical imaging analysis
Artificial intelligence in healthcare
Computational pathology

Background:

Automated medical image segmentation is crucial for clinical and research applications.
Existing validation methods for segmentation models are limited, often requiring manual inspection.
TotalSegmentator is an example of a widely used automated segmentation model.

Purpose of the Study:

To develop a novel validation framework for automated medical image segmentation models.
To address the limitations of current validation techniques by reducing reliance on manual review.
To enhance the reliability and efficiency of using segmentation masks in medical applications.

Main Methods:

Developed a validation framework utilizing data augmentation to assess model consistency.
Generated segmentation masks for both original and augmented medical scans.
Calculated alignment metrics between segmentation masks of original and augmented scans.

Main Results:

Demonstrated a strong correlation between original scan segmentation quality and alignment metrics with augmented scans.
Validated findings using metrics such as coefficient of variance and average symmetric surface distance.
Confirmed that agreement with augmented-scan segmentation masks serves as a valid proxy for segmentation quality.

Conclusions:

The proposed framework enables segmentation performance evaluation without manual ground truth data.
Establishes a foundation for advancing automated medical image analysis pipelines.
Offers a more efficient and robust method for validating segmentation models in clinical practice.