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

Deep learning for developmental dysplasia of the hip: comparative classification strategies for ultrasound imaging with heterogeneous image quality.

Physical and engineering sciences in medicine·2026

Same author

Surgical Video Understanding with Alignment-Preserving Temporal Adaptation and Action Triplet Text Alignment.

Bioengineering (Basel, Switzerland)·2026

Same author

Feasibility Study of Multiorgan Dosiomics for Evaluating Radiation-Induced Xerostomia and Dysphagia in Head and Neck Cancer Radiotherapy.

Cancers·2026

Same author

Privacy-Aware Continual Self-Supervised Learning on Multi-Window Chest Computed Tomography for Domain-Shift Robustness.

Bioengineering (Basel, Switzerland)·2026

Same author

Contrast dose determination using effective diameter in patients of unknown weight for dynamic computed tomography of the upper abdomen: a feasibility study.

Radiological physics and technology·2026

Same author

Development and Validation of Transformer- and Convolutional Neural Network-Based Deep Learning Models to Predict Curve Progression in Adolescent Idiopathic Scoliosis.

Journal of clinical medicine·2025

Search research articles

Related Experiment Video

Updated: Aug 4, 2025

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

Acquisition time reduction in pediatric ^99m Tc-DMSA planar imaging using deep learning.

Shota Ichikawa^1,2, Hiroyuki Sugimori³, Koki Ichijiri²

¹Graduate School of Health Sciences, Hokkaido University, Sapporo, Japan.

Journal of Applied Clinical Medical Physics

|April 6, 2023

Summary

Deep learning significantly enhances pediatric technetium-99m dimercaptosuccinic acid (DMSA) scintigraphy by generating high-quality images from reduced acquisition times. This method improves image quality and maintains accurate renal uptake measurements, potentially lowering radiation dose.

Keywords:

acquisition time reduction deep learning image quality assessment pediatric 99mTc-DMSA scintigraphy renal uptake

More Related Videos

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure

Published on: July 30, 2009

Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring

Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring

Published on: December 9, 2010

Related Experiment Videos

Last Updated: Aug 4, 2025

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Whole-body PET/MRI of Pediatric Patients: The Details That Matter

Published on: December 19, 2017

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure

Making MR Imaging Child's Play - Pediatric Neuroimaging Protocol, Guidelines and Procedure

Published on: July 30, 2009

Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring

Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring

Published on: December 9, 2010

Area of Science:

Nuclear Medicine
Medical Imaging
Artificial Intelligence in Healthcare

Background:

Pediatric ^99m Tc-DMSA scintigraphy is crucial for diagnosing renal abnormalities.
Motion artifacts and long acquisition times pose challenges in pediatric imaging.
Reducing scan duration is desirable to minimize patient discomfort and motion-related artifacts.

Purpose of the Study:

To evaluate deep learning models for reconstructing full-quality pediatric ^99m Tc-DMSA planar images from 1/5th of the original acquisition time.
To assess the performance of these models in terms of image quality and quantitative accuracy of renal uptake measurements.

Main Methods:

Development and application of three deep learning models (DnCNN, Win5RB, ResUnet) on 155 retrospective pediatric ^99m Tc-DMSA planar imaging datasets.
Evaluation of image quality using Normalized Mean Squared Error (NMSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index Metrics (SSIM).
Assessment of quantitative renal uptake accuracy using Pearson correlation and Bland-Altman analysis compared to full-acquisition-time images.

Main Results:

Deep learning models significantly improved image quality compared to short-acquisition images.
The ResUnet model achieved the best performance with the lowest NMSE and highest PSNR and SSIM.
Excellent correlation (R² > 0.999) was observed for renal uptake measurements across all models, with ResUnet showing minimal bias.

Conclusions:

Deep learning-based image reconstruction is effective for pediatric ^99m Tc-DMSA scintigraphy.
This approach enables substantial reduction in imaging acquisition time and potentially the injected radiopharmaceutical dose.
The findings support the clinical utility of deep learning for optimizing pediatric nuclear medicine procedures.