Mamba-driven MRI-to-CT Synthesis for MRI-only Radiotherapy Planning

TL;DR

This paper introduces Mamba-based architectures for MRI-to-CT synthesis in radiotherapy planning, demonstrating improved volumetric feature capture and inference speed over traditional CNNs, facilitating MRI-only workflows.

Contribution

It adapts state-space Mamba architectures for cross-modality image synthesis, showcasing advantages over standard CNNs in MRI-to-CT translation.

Findings

Effective CT synthesis with high image similarity metrics.

Preservation of geometric consistency in generated images.

Fast inference times suitable for clinical workflows.

Abstract

Radiotherapy workflows for oncological patients increasingly rely on multi-modal medical imaging, commonly involving both Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). MRI-only treatment planning has emerged as an attractive alternative, as it reduces patient exposure to ionizing radiation and avoids errors introduced by inter-modality registration. While nnU-Net-based frameworks are predominantly used for MRI-to-CT synthesis, we explore Mamba-based architectures for this task, aiming to showcase the advantages of state-space modeling for cross-modality translation compared to standard convolutional neural networks. Specifically, we adapt both the U-Mamba and the SegMamba architecture, originally proposed for segmentation, to perform cross-modality image generation. Our 3D Mamba architecture effectively captures complex volumetric features and long-range dependencies, thus allowing accurate CT synthesis while maintaining fast inference times. Experiments were conducted on a subset of SynthRAD2025 dataset, comprising registered single-channel MRI-CT volume pairs across three anatomical regions. Quantitative evaluation is performed via a combination of image similarity metrics computed in Hounsefield Units (HU) and segmentation-based metrics obtained from TotalSegmentator to ensure geometric consistency is preserved. The findings pave the way for the integration of state-space models into radiotherapy workflows.