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

arXiv: https://arxiv.org/abs/2605.00923 · HTML: https://mlsanity.com/paper/2605.00923/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 53 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning](https://mlsanity.com/paper/1602.03409/) (2016)
- [Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation](https://mlsanity.com/paper/2402.05079/) (2024)
- [Deep learning for undersampled MRI reconstruction](https://mlsanity.com/paper/1709.02576/) (2017)
- [Synthetic CT Generation from MRI using 3D Transformer-based Denoising Diffusion Model](https://mlsanity.com/paper/2305.19467/) (2023)
- [Improving Across-Dataset Brain Tissue Segmentation Using Transformer](https://mlsanity.com/paper/2201.08741/) (2022)
- [Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis](https://mlsanity.com/paper/2303.10202/) (2023)
- [MedSegMamba: 3D CNN-Mamba Hybrid Architecture for Brain Segmentation](https://mlsanity.com/paper/2409.08307/) (2024)
- [Enhancing CT Image synthesis from multi-modal MRI data based on a multi-task neural network framework](https://mlsanity.com/paper/2312.08343/) (2023)

## Abstract (arXiv)

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.