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

Search research articles

Related Experiment Video

Updated: May 2, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Automatic classification of DMSA scans using an artificial neural network.

J W Wright¹, R Duguid, F McKiddie

¹Department of Nuclear Medicine, Glasgow Royal Infirmary, NHS Greater Glasgow and Clyde, G4 0SF, UK.

Physics in Medicine and Biology

|March 13, 2014

Summary

This summary is machine-generated.

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 relationship between lung function and cognitive function in older adults: examining differences between men and women.

Irish medical journal·2025

Same author

Patient Preparation and Radiation Protection Guidance for Adult Patients Undergoing Radioiodine Treatment for Thyroid Cancer in the UK.

Clinical oncology (Royal College of Radiologists (Great Britain))·2022

Same author

The Eye and Its Treatment.

The Southern medical record·2022

Same author

The influence of childhood intelligence, social class, education and social mobility on memory and memory decline in late life.

Age and ageing·2018

Same author

THE EVOLUTIONARY HISTORY OF PARTHENOGENETIC CNEMIDOPHORUS LEMNISCATUS (SAURIA: TEIIDAE). II. MATERNAL ORIGIN AND AGE INFERRED FROM MITOCHONDRIAL DNA ANALYSES.

Evolution; international journal of organic evolution·2017

Same author

MITOCHONDRIAL DNA ANALYSES AND THE ORIGIN AND RELATIVE AGE OF PARTHENOGENETIC CNEMIDOPHORUS: PHYLOGENETIC CONSTRAINTS ON HYBRID ORIGINS.

Evolution; international journal of organic evolution·2017

An artificial neural network achieved 95.9% accuracy in classifying Dimercaptosuccinic acid (DMSA) scans for renal defects. This AI tool shows promise as a clinical screening assistant, outperforming expert observers.

Area of Science:

Nuclear Medicine
Artificial Intelligence in Healthcare
Medical Imaging Analysis

Background:

Dimercaptosuccinic acid (DMSA) scintigraphy is crucial for assessing functional renal tissue in patients.
Accurate interpretation of DMSA scans is vital for diagnosing renal abnormalities.
Current interpretation relies on expert human analysis, which can be subjective and time-consuming.

Purpose of the Study:

To evaluate the efficacy of an artificial neural network (ANN) in the diagnostic classification of DMSA scans.
To compare the ANN's performance against expert radiologists in identifying renal defects.
To explore the potential of ANNs as a screening tool in nuclear medicine.

Main Methods:

An ANN was trained to classify DMSA scans as positive or negative for defects using 257 historical images, with radiological reports serving as the gold standard.

More Related Videos

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

Related Experiment Videos

Last Updated: May 2, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

The trained ANN was independently validated on a separate set of 193 DMSA scans.

ANN performance was compared to three expert observers using a six-point defect scale and receiver operating characteristic (ROC) analysis.

Main Results:

The ANN achieved a high binary classification accuracy of 95.9% on the independent test set.
ROC analysis demonstrated a statistically significant improvement in performance of the ANN compared to a consensus of expert observers.
The optimized ANN achieved a 100% negative predictive value for renal defects and identified 93% of negative cases.

Conclusions:

Artificial neural networks can accurately classify DMSA scans, demonstrating performance superior to expert interpretation in some aspects.
The developed ANN shows significant potential for use as a screening tool or quality assurance assistant in clinical nuclear medicine practice.
This study supports the integration of AI in medical imaging for enhanced diagnostic efficiency and accuracy.