Saved in:
Bibliographic Details
Main Authors: Xin, Zhuoyao, Zhang, Yiren, Wu, Christopher, Liu, Dong, Gu, Chunming, Greco, Elena, Middlebrooks, Erik H., Hua, Jun, Guo, Jia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.00923
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911639692902400
author Xin, Zhuoyao
Zhang, Yiren
Wu, Christopher
Liu, Dong
Gu, Chunming
Greco, Elena
Middlebrooks, Erik H.
Hua, Jun
Guo, Jia
author_facet Xin, Zhuoyao
Zhang, Yiren
Wu, Christopher
Liu, Dong
Gu, Chunming
Greco, Elena
Middlebrooks, Erik H.
Hua, Jun
Guo, Jia
contents Accurate synthesis of computed tomography (CT) images from magnetic resonance imaging (MRI) is clinically valuable for cranial applications such as attenuation correction, radiotherapy planning, and image-guided interventions. However, heterogeneity across MRI field strengths and acquisition protocols limits the generalizability of existing methods. In this study, we formulate cranial CT synthesis as a modular, structurally coupled problem and propose a deep learning framework to improve robustness across heterogeneous MRI conditions. The model is designed to adapt to variations in field strength and imaging protocols while preserving anatomical consistency. Experiments on multi-site datasets demonstrate improved performance and generalization compared with conventional approaches. The proposed method enables reliable CT synthesis across heterogeneous MRI settings, supporting broader clinical translation.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00923
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths
Xin, Zhuoyao
Zhang, Yiren
Wu, Christopher
Liu, Dong
Gu, Chunming
Greco, Elena
Middlebrooks, Erik H.
Hua, Jun
Guo, Jia
Image and Video Processing
Computer Vision and Pattern Recognition
Accurate synthesis of computed tomography (CT) images from magnetic resonance imaging (MRI) is clinically valuable for cranial applications such as attenuation correction, radiotherapy planning, and image-guided interventions. However, heterogeneity across MRI field strengths and acquisition protocols limits the generalizability of existing methods. In this study, we formulate cranial CT synthesis as a modular, structurally coupled problem and propose a deep learning framework to improve robustness across heterogeneous MRI conditions. The model is designed to adapt to variations in field strength and imaging protocols while preserving anatomical consistency. Experiments on multi-site datasets demonstrate improved performance and generalization compared with conventional approaches. The proposed method enables reliable CT synthesis across heterogeneous MRI settings, supporting broader clinical translation.
title A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.00923