CT sinogram‐consistency learning for metal‐induced beam hardening correction

TLDR

Metal implants cause sinogram inconsistencies that lead to streaking and shading artifacts, and conventional regularization methods struggle to exploit diverse CT data, whereas deep learning offers a promising alternative. The study proposes a sinogram‑consistency learning approach to mitigate beam‑hardening artifacts in polychromatic CT. Using simulated training data and implant‑type‑specific models, the method learns to remove metal‑induced beam hardening along the metal trace, and is evaluated on pelvis CT scans with simulated hip prostheses to demonstrate selective feature extraction. The deep‑learning model successfully corrects sinogram inconsistencies, achieving beam‑hardening reduction in CT and representing the first such sinogram‑correction method.

Abstract

This paper proposes a sinogram-consistency learning method to deal with beam hardening-related artifacts in polychromatic computerized tomography (CT). The presence of highly attenuating materials in the scan field causes an inconsistent sinogram that does not match the range space of the Radon transform. When the mismatched data are entered into the range space during CT reconstruction, streaking and shading artifacts are generated owing to the inherent nature of the inverse Radon transform METHODS: The proposed learning method aims to repair inconsistent sinogram by removing the primary metal-induced beam hardening factors along the metal trace in the sinogram. Taking account of the fundamental difficulty in obtaining sufficient training data in a medical environment, the learning method is designed to use simulated training data and a patient's implant type-specific learning model is used to simplify the learning process.The feasibility of the proposed method is investigated using a dataset, consisting of real CT scans of pelvises containing simulated hip prostheses. The anatomical areas in training and test data are different, in order to demonstrate that the proposed method extracts the beam hardening features, selectively. The results show that our method successfully corrects sinogram inconsistency by extracting beam hardening sources by means of deep learning.This paper proposed a deep learning method of sinogram correction for beam hardening reduction in CT for the first time. Conventional methods for beam hardening reduction are based on regularizations, and have the fundamental drawback of being not easily able to use manifold CT images, while a deep learning approach has the potential to do so.