TechRxiv
JBHI.pdf (670.58 kB)
Download file

Model Generalizability Investigation for GFCE-MRI Synthesis in Radiotherapy of NPC patients Using Multi-institutional Data and Patient-based Data Normalization

Download (670.58 kB)
preprint
posted on 06.10.2022, 13:26 authored by Wen LiWen Li, Saikit Lam, Tian Li, Jens Kleesiek, Andy Lai-Yin Cheung, Ying Sun, Francis Kar-ho Lee, Kwok-hung Au, Victor Ho Fun LeeVictor Ho Fun Lee, Jing Cai

In this study, we aimed at investigating generalizability of GFCE-MRI model using data from seven institutions by manipulating heterogeneity of training MRI data under two popular normalization approaches. A multimodality-guided synergistic neural network (MMgSN-Net) was applied to map from T1-weighted and T2-weighted MRI to contrast-enhanced MRI (CE-MRI) for GFCE-MRI synthesis in patients with nasopharyngeal carcinoma. MRI data from three institutions were used separately to generate three uni-institution models and jointly for a tri-institution model. Min-Max and Z-Score were applied for data normalization of each model. MRI data from the remaining four institutions served as external cohorts for model generalizability assessment. Quality of GFCE-MRI was quantitatively evaluated against ground-truth CE-MRI using mean absolute error (MAE) and peak signal-to-noise ratio (PSNR). Results showed that performance of all uni-institution models remarkably dropped on the external cohorts. By contrast, model trained using multi-institutional data with Z-Score normalization yielded significantly improved model generalizability 

Funding

Development of A Patient Stratification Software Tool for Identifying Nasopharyngeal Carcinoma Patients for Adaptive Radiation Therapy

Innovation and Technology Commission

Find out more...

P0035421

SGDX20201103095002019

JCYJ20210324130209023

History

Email Address of Submitting Author

wen25.li@connect.polyu.hk

Submitting Author's Institution

The Hong Kong Polytechnic University

Submitting Author's Country

Hong Kong

Usage metrics

Licence

Exports