Clinical Validation Study of Deep Learning-Generated Magnetic Resonance Images
10.12455/j.issn.1671-7104.240050
- VernacularTitle:基于深度学习生成的磁共振图像的临床验证研究
- Author:
Guangdong FU
1
;
Lifeng PENG
;
Zhihao ZHANG
;
Lei XIANG
;
Long WANG
;
Jian HE
Author Information
1. 南京医科大学鼓楼临床医学院,南京市,210000
- Keywords:
magnetic resonance image;
deep learning;
image generation;
spine
- From:
Chinese Journal of Medical Instrumentation
2024;48(5):493-497
- CountryChina
- Language:Chinese
-
Abstract:
This research utilizes a deep learning-based image generation algorithm to generate pseudo-sagittal STIR sequences from sagittal T1WI and T2WI MR images.The evaluations include both subjective assessments by two physicians and objective analyses,measuring image quality through SNR and CNR in ROIs of five different tissues.Further analyses,including MAE,PSNR,SSIM,and COR,establish a strong correlation between the generated STIR sequences and the gold standard,with Bland-Altman analysis indicating pixel consistency.The findings indicate that the deep learning-generated STIR sequences not only align with but potentially surpass the gold standard in terms of image quality and clinical diagnostic capabilities.Moreover,the approach demonstrates promise for clinical implementation,offering reduced scan time and enhanced imaging efficiency.
