Deep Learning Superresolution for 7T Knee MR Imaging: Impact on Image Quality and Diagnostic Performance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Pinzhen, Xu, Libo, Pan, Boyang, Li, Jing, Wang, Yuting, Xiong, Ran, Gou, Xiaoli, Qing, Long, Hou, Wenjing, Gong, Nan-jie, Chen, Wei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912803993944064
author Chen, Pinzhen
Xu, Libo
Pan, Boyang
Li, Jing
Wang, Yuting
Xiong, Ran
Gou, Xiaoli
Qing, Long
Hou, Wenjing
Gong, Nan-jie
Chen, Wei
author_facet Chen, Pinzhen
Xu, Libo
Pan, Boyang
Li, Jing
Wang, Yuting
Xiong, Ran
Gou, Xiaoli
Qing, Long
Hou, Wenjing
Gong, Nan-jie
Chen, Wei
contents Background: Deep learning superresolution (SR) may enhance musculoskeletal MR image quality, but its diagnostic value in knee imaging at 7T is unclear. Objectives: To compare image quality and diagnostic performance of SR, low-resolution (LR), and high-resolution (HR) 7T knee MRI. Methods: In this prospective study, 42 participants underwent 7T knee MRI with LR (0.8*0.8*2 mm3) and HR (0.4*0.4*2 mm3) sequences. SR images were generated from LR data using a Hybrid Attention Transformer model. Three radiologists assessed image quality, anatomic conspicuity, and detection of knee pathologies. Arthroscopy served as reference in 10 cases. Results: SR images showed higher overall quality than LR (median score 5 vs 4, P<.001) and lower noise than HR (5 vs 4, P<.001). Visibility of cartilage, menisci, and ligaments was superior in SR and HR compared to LR (P<.001). Detection rates and diagnostic performance (sensitivity, specificity, AUC) for intra-articular pathology were similar across image types (P>=.095). Conclusions: Deep learning superresolution improved subjective image quality in 7T knee MRI but did not increase diagnostic accuracy compared with standard LR imaging.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02436
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Deep Learning Superresolution for 7T Knee MR Imaging: Impact on Image Quality and Diagnostic Performance
Chen, Pinzhen
Xu, Libo
Pan, Boyang
Li, Jing
Wang, Yuting
Xiong, Ran
Gou, Xiaoli
Qing, Long
Hou, Wenjing
Gong, Nan-jie
Chen, Wei
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Background: Deep learning superresolution (SR) may enhance musculoskeletal MR image quality, but its diagnostic value in knee imaging at 7T is unclear. Objectives: To compare image quality and diagnostic performance of SR, low-resolution (LR), and high-resolution (HR) 7T knee MRI. Methods: In this prospective study, 42 participants underwent 7T knee MRI with LR (0.8*0.8*2 mm3) and HR (0.4*0.4*2 mm3) sequences. SR images were generated from LR data using a Hybrid Attention Transformer model. Three radiologists assessed image quality, anatomic conspicuity, and detection of knee pathologies. Arthroscopy served as reference in 10 cases. Results: SR images showed higher overall quality than LR (median score 5 vs 4, P<.001) and lower noise than HR (5 vs 4, P<.001). Visibility of cartilage, menisci, and ligaments was superior in SR and HR compared to LR (P<.001). Detection rates and diagnostic performance (sensitivity, specificity, AUC) for intra-articular pathology were similar across image types (P>=.095). Conclusions: Deep learning superresolution improved subjective image quality in 7T knee MRI but did not increase diagnostic accuracy compared with standard LR imaging.
title Deep Learning Superresolution for 7T Knee MR Imaging: Impact on Image Quality and Diagnostic Performance
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2601.02436