Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT: From Simulated to Real Data

TL;DR

This paper introduces LIRE++, a rotationally-equivariant, multiscale invertible neural network scheme for fast, memory-efficient CBCT reconstruction, demonstrating improved image quality on both simulated and real clinical data.

Contribution

LIRE++ is a novel end-to-end invertible scheme that incorporates rotational equivariance and multiscale reconstruction for enhanced CBCT imaging.

Findings

Achieved 1 dB PSNR improvement over baselines on synthetic data.

Reduced MAE by 10 Hounsfield Units on real clinical data.

Enabled fast training and inference with memory optimizations.

Abstract

Cone Beam CT (CBCT) is an important imaging modality nowadays, however lower image quality of CBCT compared to more conventional Computed Tomography (CT) remains a limiting factor in CBCT applications. Deep learning reconstruction methods are a promising alternative to classical analytical and iterative reconstruction methods, but applying such methods to CBCT is often difficult due to the lack of ground truth data, memory limitations and the need for fast inference at clinically-relevant resolutions. In this work we propose LIRE++, an end-to-end rotationally-equivariant multiscale learned invertible primal-dual scheme for fast and memory-efficient CBCT reconstruction. Memory optimizations and multiscale reconstruction allow for fast training and inference, while rotational equivariance improves parameter efficiency. LIRE++ was trained on simulated projection data from a fast quasi-Monte Carlo CBCT projection simulator that we developed as well. Evaluated on synthetic data, LIRE++ gave an average improvement of 1 dB in Peak Signal-to-Noise Ratio over alternative deep learning baselines. On real clinical data, LIRE++ improved the average Mean Absolute Error between the reconstruction and the corresponding planning CT by 10 Hounsfield Units with respect to current proprietary state-of-the-art hybrid deep-learning/iterative method.