Similarity and quality metrics for MR image-to-image translation

Abstract Image-to-image translation can create large impact in medical imaging, as images can be synthetically transformed to other modalities, sequence types, higher resolutions or lower noise levels. To ensure patient safety, these methods should be validated by human readers, which requires a con...

Full description

Saved in:
Bibliographic Details
Main Authors: Melanie Dohmen, Mark A. Klemens, Ivo M. Baltruschat, Tuan Truong, Matthias Lenga
Format: Article
Language:English
Published: Nature Portfolio 2025-01-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-87358-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832571737906085888
author Melanie Dohmen
Mark A. Klemens
Ivo M. Baltruschat
Tuan Truong
Matthias Lenga
author_facet Melanie Dohmen
Mark A. Klemens
Ivo M. Baltruschat
Tuan Truong
Matthias Lenga
author_sort Melanie Dohmen
collection DOAJ
description Abstract Image-to-image translation can create large impact in medical imaging, as images can be synthetically transformed to other modalities, sequence types, higher resolutions or lower noise levels. To ensure patient safety, these methods should be validated by human readers, which requires a considerable amount of time and costs. Quantitative metrics can effectively complement such studies and provide reproducible and objective assessment of synthetic images. If a reference is available, the similarity of MR images is frequently evaluated by SSIM and PSNR metrics, even though these metrics are not or too sensitive regarding specific distortions. When reference images to compare with are not available, non-reference quality metrics can reliably detect specific distortions, such as blurriness. To provide an overview on distortion sensitivity, we quantitatively analyze 11 similarity (reference) and 12 quality (non-reference) metrics for assessing synthetic images. We additionally include a metric on a downstream segmentation task. We investigate the sensitivity regarding 11 kinds of distortions and typical MR artifacts, and analyze the influence of different normalization methods on each metric and distortion. Finally, we derive recommendations for effective usage of the analyzed similarity and quality metrics for evaluation of image-to-image translation models.
format Article
id doaj-art-8a81988bb63f43529ad1500492ff7000
institution Kabale University
issn 2045-2322
language English
publishDate 2025-01-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-8a81988bb63f43529ad1500492ff70002025-02-02T12:21:43ZengNature PortfolioScientific Reports2045-23222025-01-0115111810.1038/s41598-025-87358-0Similarity and quality metrics for MR image-to-image translationMelanie Dohmen0Mark A. Klemens1Ivo M. Baltruschat2Tuan Truong3Matthias Lenga4Bayer AG, RadiologyBayer AG, RadiologyBayer AG, RadiologyBayer AG, RadiologyBayer AG, RadiologyAbstract Image-to-image translation can create large impact in medical imaging, as images can be synthetically transformed to other modalities, sequence types, higher resolutions or lower noise levels. To ensure patient safety, these methods should be validated by human readers, which requires a considerable amount of time and costs. Quantitative metrics can effectively complement such studies and provide reproducible and objective assessment of synthetic images. If a reference is available, the similarity of MR images is frequently evaluated by SSIM and PSNR metrics, even though these metrics are not or too sensitive regarding specific distortions. When reference images to compare with are not available, non-reference quality metrics can reliably detect specific distortions, such as blurriness. To provide an overview on distortion sensitivity, we quantitatively analyze 11 similarity (reference) and 12 quality (non-reference) metrics for assessing synthetic images. We additionally include a metric on a downstream segmentation task. We investigate the sensitivity regarding 11 kinds of distortions and typical MR artifacts, and analyze the influence of different normalization methods on each metric and distortion. Finally, we derive recommendations for effective usage of the analyzed similarity and quality metrics for evaluation of image-to-image translation models.https://doi.org/10.1038/s41598-025-87358-0MetricsImage synthesisMRISimilarityImage quality
spellingShingle Melanie Dohmen
Mark A. Klemens
Ivo M. Baltruschat
Tuan Truong
Matthias Lenga
Similarity and quality metrics for MR image-to-image translation
Scientific Reports
Metrics
Image synthesis
MRI
Similarity
Image quality
title Similarity and quality metrics for MR image-to-image translation
title_full Similarity and quality metrics for MR image-to-image translation
title_fullStr Similarity and quality metrics for MR image-to-image translation
title_full_unstemmed Similarity and quality metrics for MR image-to-image translation
title_short Similarity and quality metrics for MR image-to-image translation
title_sort similarity and quality metrics for mr image to image translation
topic Metrics
Image synthesis
MRI
Similarity
Image quality
url https://doi.org/10.1038/s41598-025-87358-0
work_keys_str_mv AT melaniedohmen similarityandqualitymetricsformrimagetoimagetranslation
AT markaklemens similarityandqualitymetricsformrimagetoimagetranslation
AT ivombaltruschat similarityandqualitymetricsformrimagetoimagetranslation
AT tuantruong similarityandqualitymetricsformrimagetoimagetranslation
AT matthiaslenga similarityandqualitymetricsformrimagetoimagetranslation