Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep Learning

The objective of this study is to propose an advanced image enhancement strategy to address the challenge of reducing radiation doses in pediatric renal scintigraphy. Data from a public dynamic renal scintigraphy database were used. Based on noisier images, four denoising neural networks (DnCNN, UDn...

Full description

Saved in:
Bibliographic Details
Main Authors: Marta Arsénio, Ricardo Vigário, Ana M. Mota
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Journal of Imaging
Subjects:
Online Access:https://www.mdpi.com/2313-433X/11/3/88
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850280144000778240
author Marta Arsénio
Ricardo Vigário
Ana M. Mota
author_facet Marta Arsénio
Ricardo Vigário
Ana M. Mota
author_sort Marta Arsénio
collection DOAJ
description The objective of this study is to propose an advanced image enhancement strategy to address the challenge of reducing radiation doses in pediatric renal scintigraphy. Data from a public dynamic renal scintigraphy database were used. Based on noisier images, four denoising neural networks (DnCNN, UDnCNN, DUDnCNN, and AttnGAN) were evaluated. To evaluate the quality of the noise reduction, with minimal detail loss, the kidney signal-to-noise ratio (SNR) and multiscale structural similarity (MS-SSIM) were used. Although all the networks reduced noise, UDnCNN achieved the best balance between SNR and MS-SSIM, leading to the most notable improvements in image quality. In clinical practice, 100% of the acquired data are summed to produce the final image. To simulate the dose reduction, we summed only 50%, simulating a proportional decrease in radiation. The proposed deep-learning approach for image enhancement ensured that half of all the frames acquired may yield results that are comparable to those of the complete dataset, suggesting that it is feasible to reduce patients’ exposure to radiation. This study demonstrates that the neural networks evaluated can markedly improve the renal scintigraphic image quality, facilitating high-quality imaging with lower radiation doses, which will benefit the pediatric population considerably.
format Article
id doaj-art-70ae167afca446f39ae976fb40cb95cd
institution OA Journals
issn 2313-433X
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj-art-70ae167afca446f39ae976fb40cb95cd2025-08-20T01:48:52ZengMDPI AGJournal of Imaging2313-433X2025-03-011138810.3390/jimaging11030088Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep LearningMarta Arsénio0Ricardo Vigário1Ana M. Mota2Physics Department, NOVA School of Science and Technology, NOVA University of Lisbon, 2829-516 Caparica, PortugalPhysics Department, NOVA School of Science and Technology, NOVA University of Lisbon, 2829-516 Caparica, PortugalInstituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, PortugalThe objective of this study is to propose an advanced image enhancement strategy to address the challenge of reducing radiation doses in pediatric renal scintigraphy. Data from a public dynamic renal scintigraphy database were used. Based on noisier images, four denoising neural networks (DnCNN, UDnCNN, DUDnCNN, and AttnGAN) were evaluated. To evaluate the quality of the noise reduction, with minimal detail loss, the kidney signal-to-noise ratio (SNR) and multiscale structural similarity (MS-SSIM) were used. Although all the networks reduced noise, UDnCNN achieved the best balance between SNR and MS-SSIM, leading to the most notable improvements in image quality. In clinical practice, 100% of the acquired data are summed to produce the final image. To simulate the dose reduction, we summed only 50%, simulating a proportional decrease in radiation. The proposed deep-learning approach for image enhancement ensured that half of all the frames acquired may yield results that are comparable to those of the complete dataset, suggesting that it is feasible to reduce patients’ exposure to radiation. This study demonstrates that the neural networks evaluated can markedly improve the renal scintigraphic image quality, facilitating high-quality imaging with lower radiation doses, which will benefit the pediatric population considerably.https://www.mdpi.com/2313-433X/11/3/88<sup>99m</sup>Tc-MAG3deep learningnoise reductionpediatric renal scintigraphymedical imaging
spellingShingle Marta Arsénio
Ricardo Vigário
Ana M. Mota
Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep Learning
Journal of Imaging
<sup>99m</sup>Tc-MAG3
deep learning
noise reduction
pediatric renal scintigraphy
medical imaging
title Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep Learning
title_full Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep Learning
title_fullStr Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep Learning
title_full_unstemmed Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep Learning
title_short Recovering Image Quality in Low-Dose Pediatric Renal Scintigraphy Using Deep Learning
title_sort recovering image quality in low dose pediatric renal scintigraphy using deep learning
topic <sup>99m</sup>Tc-MAG3
deep learning
noise reduction
pediatric renal scintigraphy
medical imaging
url https://www.mdpi.com/2313-433X/11/3/88
work_keys_str_mv AT martaarsenio recoveringimagequalityinlowdosepediatricrenalscintigraphyusingdeeplearning
AT ricardovigario recoveringimagequalityinlowdosepediatricrenalscintigraphyusingdeeplearning
AT anammota recoveringimagequalityinlowdosepediatricrenalscintigraphyusingdeeplearning