Virtual Full-stack Scanning of Brain MRI via Imputing Any Quantised Code

TL;DR

This paper introduces CodeBrain, a unified framework for imputing missing brain MRI modalities by predicting region-level codes, enabling virtual full-stack scanning with high fidelity across diverse datasets.

Contribution

CodeBrain reformulates MRI modality imputation as a region-level code prediction task, improving generalisability and performance over existing methods.

Findings

Outperforms state-of-the-art methods on IXI and BraTS datasets

Establishes a new benchmark for brain MRI imputation

Enables high-fidelity virtual full-stack scanning

Abstract

Magnetic resonance imaging (MRI) is a powerful and versatile imaging technique, offering a wide spectrum of information about the anatomy by employing different acquisition modalities. However, in the clinical workflow, it is impractical to collect all relevant modalities due to the scan time and cost constraints. Virtual full-stack scanning aims to impute missing MRI modalities from available but incomplete acquisitions, offering a cost-efficient solution to enhance data completeness and clinical usability. Existing imputation methods often depend on global conditioning or modality-specific designs, which limit their generalisability across patient cohorts and imaging protocols. To address these limitations, we propose CodeBrain, a unified framework that reformulates various ``any-to-any'' imputation tasks as a region-level full-stack code prediction problem. CodeBrain adopts a two-stage pipeline: (1) it learns the compact representation of a complete MRI modality set by encoding it into scalar-quantised codes at the region level, enabling high-fidelity image reconstruction after decoding these codes along with modality-agnostic common features; (2) it trains a projection encoder to predict the full-stack code map from incomplete modalities via a grading-based design for diverse imputation scenarios. Extensive experiments on two public brain MRI datasets, i.e., IXI and BraTS 2023, demonstrate that CodeBrain consistently outperforms state-of-the-art methods, establishing a new benchmark for unified brain MRI imputation and enabling virtual full-stack scanning. Our code will be released at https://github.com/ycwu1997/CodeBrain.