Imaging foundation model for universal enhancement of non-ideal measurement CT

TL;DR

This paper introduces TAMP, a universal imaging foundation model trained on simulated data, which significantly enhances non-ideal measurement CT images across diverse settings, improving clinical usability.

Contribution

The paper presents TAMP, the first foundation model for NICT enhancement, pre-trained on millions of simulated images, with a parameter-efficient fine-tuning strategy for clinical adaptation.

Findings

TAMP outperforms existing methods in image quality and clinical acceptability.

Effective across various NICT settings, defect levels, and body regions.

Validated by radiologists and real-world data.

Abstract

Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have been used to enhance NICT images, their reliance on large training datasets and limited generalizability across diverse settings hinder practical use. We propose the multi-scale integrated Transformer AMPlifier (TAMP), the first imaging foundation model for universal NICT enhancement. Pre-trained on 10.8 million physics-driven simulated NICT images, TAMP generalizes effectively across various NICT settings, defect degrees, and body regions. Moreover, a parameter-efficient fine-tuning strategy enables TAMP to adapt to specific clinical scenarios using only few slices. Extensive experiments, including radiologists and real-world validations, demonstrate that TAMP consistently improves image quality and clinical acceptability, underscoring its significant potential to advance CT imaging and broaden NICT applications in clinical practice.