A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths

TL;DR

This study introduces a deep learning framework for synthesizing cranial CT images from MRI scans, aiming to improve robustness across different MRI field strengths and protocols for clinical applications.

Contribution

It formulates CT synthesis as a modular, structurally coupled problem and proposes a method that adapts to MRI heterogeneity, enhancing generalization and clinical utility.

Findings

Improved performance over conventional methods on multi-site datasets.

Enhanced robustness to variations in MRI field strength and protocols.

Supports broader clinical translation of CT synthesis.

Abstract

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.