Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning

Abstract Background T2-weighted images are a critical component of prostate magnetic resonance imaging (MRI), and it would be useful to automatically assess image quality (IQ) on a patient-specific basis without radiologist oversight. Methods This retrospective study comprised 1,412 axial T2-weighte...

Full description

Saved in:
Bibliographic Details
Main Authors: Jacob N. Gloe, Eric A. Borisch, Adam T. Froemming, Akira Kawashima, Jordan D. LeGout, Hirotsugu Nakai, Naoki Takahashi, Stephen J. Riederer
Format: Article
Language:English
Published: SpringerOpen 2025-04-01
Series:European Radiology Experimental
Subjects:
Online Access:https://doi.org/10.1186/s41747-025-00584-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850280206508490752
author Jacob N. Gloe
Eric A. Borisch
Adam T. Froemming
Akira Kawashima
Jordan D. LeGout
Hirotsugu Nakai
Naoki Takahashi
Stephen J. Riederer
author_facet Jacob N. Gloe
Eric A. Borisch
Adam T. Froemming
Akira Kawashima
Jordan D. LeGout
Hirotsugu Nakai
Naoki Takahashi
Stephen J. Riederer
author_sort Jacob N. Gloe
collection DOAJ
description Abstract Background T2-weighted images are a critical component of prostate magnetic resonance imaging (MRI), and it would be useful to automatically assess image quality (IQ) on a patient-specific basis without radiologist oversight. Methods This retrospective study comprised 1,412 axial T2-weighted prostate scans. Four experienced uroradiologists graded IQ using a 0-to-3 scale (0 = uninterpretable; 1 = marginally interpretable; 2 = adequately diagnostic; 3 = more than adequately diagnostic), binarized into nondiagnostic (IQ0 or IQ1), requiring rescanning, and diagnostic (IQ2 or IQ3), not requiring rescanning. The deep learning (DL) model was trained on 1,006 scans; 203 other scans were used for validation of multiple convolutional neural networks; the remaining 203 exams were used as a test set. 3D-DenseNet_169 was chosen among 11 models based on multiple evaluation criteria. The rescan predictions were compared to the number of rescans performed on a subset of 174 exams. Results The model accurately predicts radiologist IQ scores (Cohen κ = 0.658), similar to the human inter-rater reliability (κ = 0.688–0.791). The model also predicts rescanning necessity similarly to radiologists: model κ = 0.537; reviewer κ = 0.577–0.703. The rescan model prediction area under the curve was 0.867. Conclusion The DL model showed a strong ability to differentiate diagnostic from nondiagnostic axial T2-weighted prostate images, accurately mimicking expert radiologists’ IQ scores. Using the model, the clinical unnecessary rescan rate could be reduced from over 50% to less than 30%. Relevance statement DL assessment of T2-weighted prostate MRI scans can accurately assess IQ, determining the need to repeat inadequate scans as well as avoiding repeat scans of those with adequate diagnostic quality, resulting in reduced unnecessary rescanning. Key Points Artificial intelligence assessment of prostate MRI T2-weighted image quality can improve exam time management. The model showed over 75% accuracy in assessing prostate MRI T2-weighted image quality. Expert radiologists have a substantial agreement in evaluating prostate MRI T2-weighted image quality. Graphical Abstract
format Article
id doaj-art-816e81ac3c164937be072b403103ff9d
institution OA Journals
issn 2509-9280
language English
publishDate 2025-04-01
publisher SpringerOpen
record_format Article
series European Radiology Experimental
spelling doaj-art-816e81ac3c164937be072b403103ff9d2025-08-20T01:48:50ZengSpringerOpenEuropean Radiology Experimental2509-92802025-04-019111110.1186/s41747-025-00584-zDeep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanningJacob N. Gloe0Eric A. Borisch1Adam T. Froemming2Akira Kawashima3Jordan D. LeGout4Hirotsugu Nakai5Naoki Takahashi6Stephen J. Riederer7Department of Radiology, Mayo ClinicDepartment of Radiology, Mayo ClinicDepartment of Radiology, Mayo ClinicDepartment of Radiology, Mayo ClinicDepartment of Radiology, Mayo ClinicKyoto UniversityDepartment of Radiology, Mayo ClinicDepartment of Radiology, Mayo ClinicAbstract Background T2-weighted images are a critical component of prostate magnetic resonance imaging (MRI), and it would be useful to automatically assess image quality (IQ) on a patient-specific basis without radiologist oversight. Methods This retrospective study comprised 1,412 axial T2-weighted prostate scans. Four experienced uroradiologists graded IQ using a 0-to-3 scale (0 = uninterpretable; 1 = marginally interpretable; 2 = adequately diagnostic; 3 = more than adequately diagnostic), binarized into nondiagnostic (IQ0 or IQ1), requiring rescanning, and diagnostic (IQ2 or IQ3), not requiring rescanning. The deep learning (DL) model was trained on 1,006 scans; 203 other scans were used for validation of multiple convolutional neural networks; the remaining 203 exams were used as a test set. 3D-DenseNet_169 was chosen among 11 models based on multiple evaluation criteria. The rescan predictions were compared to the number of rescans performed on a subset of 174 exams. Results The model accurately predicts radiologist IQ scores (Cohen κ = 0.658), similar to the human inter-rater reliability (κ = 0.688–0.791). The model also predicts rescanning necessity similarly to radiologists: model κ = 0.537; reviewer κ = 0.577–0.703. The rescan model prediction area under the curve was 0.867. Conclusion The DL model showed a strong ability to differentiate diagnostic from nondiagnostic axial T2-weighted prostate images, accurately mimicking expert radiologists’ IQ scores. Using the model, the clinical unnecessary rescan rate could be reduced from over 50% to less than 30%. Relevance statement DL assessment of T2-weighted prostate MRI scans can accurately assess IQ, determining the need to repeat inadequate scans as well as avoiding repeat scans of those with adequate diagnostic quality, resulting in reduced unnecessary rescanning. Key Points Artificial intelligence assessment of prostate MRI T2-weighted image quality can improve exam time management. The model showed over 75% accuracy in assessing prostate MRI T2-weighted image quality. Expert radiologists have a substantial agreement in evaluating prostate MRI T2-weighted image quality. Graphical Abstracthttps://doi.org/10.1186/s41747-025-00584-zArtificial intelligenceDeep learningMagnetic resonance imagingProstateTime management
spellingShingle Jacob N. Gloe
Eric A. Borisch
Adam T. Froemming
Akira Kawashima
Jordan D. LeGout
Hirotsugu Nakai
Naoki Takahashi
Stephen J. Riederer
Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning
European Radiology Experimental
Artificial intelligence
Deep learning
Magnetic resonance imaging
Prostate
Time management
title Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning
title_full Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning
title_fullStr Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning
title_full_unstemmed Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning
title_short Deep learning for quality assessment of axial T2-weighted prostate MRI: a tool to reduce unnecessary rescanning
title_sort deep learning for quality assessment of axial t2 weighted prostate mri a tool to reduce unnecessary rescanning
topic Artificial intelligence
Deep learning
Magnetic resonance imaging
Prostate
Time management
url https://doi.org/10.1186/s41747-025-00584-z
work_keys_str_mv AT jacobngloe deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning
AT ericaborisch deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning
AT adamtfroemming deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning
AT akirakawashima deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning
AT jordandlegout deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning
AT hirotsugunakai deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning
AT naokitakahashi deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning
AT stephenjriederer deeplearningforqualityassessmentofaxialt2weightedprostatemriatooltoreduceunnecessaryrescanning