Masked Sinogram Model with Transformer for ill-Posed Computed Tomography Reconstruction: a Preliminary Study

TL;DR

This paper introduces a novel transformer-based masked sinogram model for computed tomography that leverages natural language processing techniques to improve image reconstruction under limited data conditions.

Contribution

It proposes a new foundation model approach for CT reconstruction by treating sinograms as sentences and applying masked modeling techniques.

Findings

Effective in reconstructing images with limited data

Demonstrates potential of transformer models in CT imaging

Provides a new framework for data-efficient CT reconstruction

Abstract

Computed Tomography (CT) is an imaging technique where information about an object are collected at different angles (called projections or scans). Then the cross-sectional image showing the internal structure of the slice is produced by solving an inverse problem. Limited by certain factors such as radiation dosage, projection angles, the produced images can be noisy or contain artifacts. Inspired by the success of transformer for natural language processing, the core idea of this preliminary study is to consider a projection of tomography as a word token, and the whole scan of the cross-section (A.K.A. sinogram) as a sentence in the context of natural language processing. Then we explore the idea of foundation model by training a masked sinogram model (MSM) and fine-tune MSM for various downstream applications including CT reconstruction under data collections restriction (e.g., photon-budget) and a data-driven solution to approximate solutions of the inverse problem for CT reconstruction. Models and data used in this study are available at https://github.com/lzhengchun/TomoTx.