SAVER: Stochastic Adaptive Variance-Driven Exploration and Reconstruction for Low-Dose Computed Tomography

2026-07-04

AI Summary

This work proposes an adaptive data acquisition framework to reduce CT radiation dose while preserving image quality, overcoming the limitations of conventional fixed-angle sampling. By dynamically selecting optimal projection angles based on the statistical variance of acquired projection data, the method integrates Softmax-based stochastic scheduling with simulated annealing to prioritize high-information directions while maintaining essential exploration. It represents the first integration of variance-driven adaptive sampling with a stochastic exploration mechanism, enabling a patient-specific, data-driven acquisition strategy tailored to individual anatomical structures. Experiments on eight phantoms demonstrate that the proposed approach significantly improves reconstruction fidelity compared to traditional random sampling, particularly for highly anisotropic structures, and exhibits robust performance under strong noise conditions.

Abstract

Computed Tomography (CT) is indispensable in clinical diagnostics, yet minimizing radiation dose without compromising image quality remains a critical challenge. Conventional low-dose protocols often rely on fixed, uniform angular sampling, independent of the underlying structural complexity of organs of individual patients. We propose ``Stochastic Adaptive Variance-Driven Exploration and Reconstruction'' (SAVER), an adaptive data acquisition framework that selects projection angles in real-time based on the statistical variance of acquired data. Utilizing a Softmax-based stochastic scheduling scheme with simulated annealing, SAVER prioritizes directions with high structural information while maintaining necessary exploration. Numerical experiments across 8 diverse phantoms demonstrate that SAVER achieves consistently higher reconstruction fidelity than conventional random sampling, particularly for objects with high structural anisotropy. Furthermore, the proposed method exhibits robust performance under significant measurement noise. By dynamically reallocating radiation dose to the most informative projections, SAVER provides a mathematically-grounded approach to maximize diagnostic quality per unit of radiation dose, marking a shift toward sample-dependent, data-driven CT acquisition.

Problem

• low-dose CT
• radiation dose reduction
• adaptive sampling
• image quality
• structural complexity

Innovation

• adaptive sampling
• low-dose CT
• variance-driven exploration
• stochastic scheduling
• data-driven reconstruction