Fractional-gradient Sparsity with Autoencoding Sequential Deep Image Prior for 3D CT Reconstruction

2026-05-23

AI Summary

This work addresses the degradation in image quality in 3D CT reconstruction caused by incomplete data or noise, as well as the high computational cost and inter-slice inconsistency of existing Deep Image Prior (DIP) methods when extended to three dimensions. To overcome these limitations, the authors propose FAST-DIP, a novel framework that integrates a sequential autoencoding DIP architecture with fractional-order ℓ₁/ℓ₂ gradient sparsity regularization along the Z-axis to explicitly model inter-slice structural dependencies. Leveraging the Kurdyka–Łojasiewicz property, an alternating minimization algorithm is devised with provable convergence guarantees. This study presents the first integration of fractional-order regularization with sequential DIP for 3D CT reconstruction, achieving significantly improved reconstruction quality and slice consistency while maintaining computational efficiency, thereby outperforming current DIP-based approaches.

Abstract

3D volumetric reconstruction from incomplete or noisy measurements is a fundamental problem in medical imaging and computational tomography. Deep image prior (DIP)-based methods have recently shown strong capability for solving inverse problems without requiring large training datasets. However, directly extending DIP to 3D reconstruction by fully 3D networks can incur high computational cost, while slice-by-slice 2D DIP approaches may lead to inter-slice inconsistencies due to the lack of explicit regularization along the third direction. In this paper, we propose a novel volumetric reconstruction framework, Fractional-gradient Autoencoding Sequential Tomography DIP (FAST-DIP), which integrates input-adaptive sequential deep image prior modeling of slices with fractional sparsity regularization to capture inter-slice dependencies. Specifically, we introduce a fractionall1/l2-based sparsity prior on the gradients along the slice (z) direction to explicitly enforce inter-slice structural consistency. We further provide theoretical analysis of the proposed alternating minimization algorithm under the majorization-minimization (MM) framework, establishing monotonic descent of the objective function and convergence to a critical point under the Kurdyka-Lojasiewicz (KL) property. Experimental results for 3D X-ray computed tomography (CT) reconstruction demonstrate that the proposed method improved reconstruction quality and structural consistency compared with existing DIP-based approaches.

Problem

• 3D CT reconstruction
• Deep image prior
• Inter-slice consistency
• Inverse problems
• Fractional sparsity

Innovation

• fractional sparsity
• deep image prior
• 3D CT reconstruction
• inter-slice consistency
• sequential modeling