Feasibility of deep learning-based super-resolution reconstruction for endometrial cancer T2-weighted imaging
Preprint
- 12 December 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Background No study has assessed the application of deep learning (DL) networks in combination with more advanced super-resolution (SR) reconstruction for endometrial cancer (EC) MRI and the influence of this methods on myometrial invasion. We aimed to evaluate the performance and clinical value of DL-based SR reconstruction for image quality improvement in under-sampling accelerated EC T2WI. Methods Two sets of T2WI were acquired for 23 volunteers with low (T2 LR ) and high (T2 HR ) resolution, respectively. For 41 EC patients, T2 LR and MultiVane T2WI (T2 MV ) were performed. T2 SR images were reconstructed from T2 LR through DL network. Image quality and diagnostic accuracy were evaluated by radiologists. Results For 23 volunteers, the signal-to-noise ratio and peak signal-to-noise ratio of T2 SR were notably higher than those of T2 LR and T2 HR , and the edge rise distance of T2 SR was lower ( P < 0.005). For 41 EC patients, the image sharpness, capsule delineation, overall image quality, and diagnostic confidence of T2 SR and T2 MV were notably higher than those of T2 LR ( P < 0.005). Compared with T2 MV , the scanning time of T2 SR was reduced by 61% (50s vs. 128s). T2 SR and T2 MV images had similar diagnostic accuracy for myometrial invasion assessed by radiologists. Conclusions DL-based super-resolution reconstruction significantly improved the image quality of uterus T2WI compared to the conventional iterative reconstruction by compressed sensing, saving scanning time and ensuring the accurate evaluation of myometrial invasion of endometrial cancer.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Evaluation of multi-parameter MRI in preoperative staging of endometrial carcinomaEuropean Journal of Radiology Open, 2024
- The global incidence, mortality, and burden of uterine cancer in 2019 and correlation with SDI, tobacco, dietary risks, and metabolic risk factors: An ecological studyHealth Science Reports, 2024
- Shortening Acquisition Time and Improving Image Quality for Pelvic MRI Using Deep Learning Reconstruction for Diffusion-Weighted Imaging at 1.5 TAcademic Radiology, 2023
- Utility of accelerated T2-weighted turbo spin-echo imaging with deep learning reconstruction in female pelvic MRI: a multi-reader studyEuropean Radiology, 2023
- MRI to assess deep myometrial invasion in patients with endometrial cancer:A multi-reader study to evaluate the diagnostic role of different sequencesEuropean Journal of Radiology, 2021
- Compressed sensing and deep learning reconstruction for women’s pelvic MRI denoising: Utility for improving image quality and examination time in routine clinical practiceEuropean Journal of Radiology, 2021
- Comparison of HASTE with multiple signal averaging versus conventional turbo spin echo sequence: a new option for T2-weighted MRI of the female pelvisEuropean Radiology, 2020
- MRI of the lung using the PROPELLER technique: Artifact reduction, better image quality and improved nodule detectionEuropean Journal of Radiology, 2016
- Rigid‐body motion correction with self‐navigation MRIMagnetic Resonance in Medicine, 2008
- Artifacts and pitfalls in MR imaging of the pelvisJournal of Magnetic Resonance Imaging, 2007