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

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

Imaging Studies III: Computed Tomography

Imaging Studies III: Computed Tomography

DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...

You might also read

Related Articles

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

Sort by

Same author

Temporal Dynamics of Parkinson's Disease Tremor: Clinical and Neuroimaging Insights.

Movement disorders : official journal of the Movement Disorder Society·2026

Same author

Artificial Intelligence Competencies and Educational Needs Among ERNICA Members: Results of a Multinational Survey.

European journal of pediatric surgery : official journal of Austrian Association of Pediatric Surgery ... [et al] = Zeitschrift fur Kinderchirurgie·2026

Same author

Predicting biological sex in pediatric skeleton X-rays using artificial intelligence.

Scientific reports·2025

Same author

Artificial Intelligence in Pediatric Surgery-From Vision to Clinical Reality.

European journal of pediatric surgery : official journal of Austrian Association of Pediatric Surgery ... [et al] = Zeitschrift fur Kinderchirurgie·2025

Same author

Automated AI fracture detection in initial presentation pediatric wrist X-rays: effects and benefits of adding follow-up examinations.

La Radiologia medica·2025

Same author

Artificial intelligence based sonographic differentiation between skull fractures and normal sutures in young children.

Scientific reports·2025

Same journal

Erratum for: Prediction of Lobar Emphysema Progression with a CT-Based Foundational Model.

Radiology·2026

Same journal

Erratum for: Associations of MRI-derived Paraspinal IMAT and LMM with Cardiometabolic Risk Factors: Results from a German Cohort.

Radiology·2026

Same journal

Erratum for: Blue Rubber Bleb Nevus Syndrome.

Radiology·2026

Same journal

Redefining the Clinical Role of MRI in Endometrial Cancer Staging.

Radiology·2026

Same journal

To Ablate or Not to Ablate: The Colorectal Liver Metastasis Question.

Radiology·2026

Same journal

The Limits of Radiologic Categorization in Pulmonary Nonsolid Nodules.

Radiology·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 28, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Impact of Test Set Composition on AI Performance for Pediatric Radiograph Appendicular Skeleton Fracture Detection.

Nikolaus Stranger¹, Mario Scherkl¹, Daniel Stütz¹

¹Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria.

|February 17, 2026

Summary

This summary is machine-generated.

Test set composition significantly impacts artificial intelligence (AI) performance in pediatric fracture detection. Complex radiographs in test sets decrease AI accuracy, highlighting the need for realistic evaluation datasets.

More Related Videos

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Published on: December 9, 2022

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Related Experiment Videos

Last Updated: Jun 28, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Assessment of Bone Fracture Healing Using Micro-Computed Tomography

Published on: December 9, 2022

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Area of Science:

Medical Imaging
Artificial Intelligence
Pediatric Radiology

Background:

AI performance evaluation often uses test sets that don't reflect real-world scenarios, potentially overestimating accuracy.
This can limit the clinical usability of AI tools for fracture detection.

Purpose of the Study:

To assess how different test set compositions affect AI model performance for pediatric fracture detection in radiography.
Investigate the influence of radiograph complexity on AI diagnostic capabilities.

Main Methods:

Retrospective analysis of pediatric appendicular trauma radiographs.
Two internal test sets were created: a 'difficult' set with assessment discrepancies and a 'matched' set.
AI models (EfficientNet, YOLOv8) were evaluated on these test sets by independent radiologists.

Main Results:

The 'difficult' test set showed a 40% decrease in correct classification odds for EfficientNet and an 80% decrease for YOLOv8 compared to the 'matched' set.
Radiographs in the 'difficult' set were rated as more challenging and contained more complex images.
AI performance was significantly lower on test sets with more complex radiographs (P < .001).

Conclusions:

AI performance in pediatric fracture detection is sensitive to test set composition and image complexity.
Using test sets that mirror real-world complexity is crucial for accurate AI performance assessment and clinical adoption.