AHP-Net: adaptive-hyper-parameter deep learning based image reconstruction method for multilevel low-dose CT

TL;DR

AHP-Net is a deep learning-based image reconstruction method that adaptively adjusts hyper-parameters to effectively handle multilevel low-dose CT scans with varying noise levels, improving image quality over existing methods.

Contribution

This work introduces AHP-Net, a novel adaptive hyper-parameter deep learning framework that unrolls a half-quadratic splitting scheme with learnable priors for multilevel LDCT reconstruction.

Findings

AHP-Net outperforms conventional MBIR techniques.

AHP-Net surpasses state-of-the-art deep learning methods.

AHP-Net effectively handles different noise levels in LDCT.

Abstract

Low-dose CT (LDCT) imaging is desirable in many clinical applications to reduce X-ray radiation dose to patients. Inspired by deep learning (DL), a recent promising direction of model-based iterative reconstruction (MBIR) methods for LDCT is via optimization-unrolling DL-regularized image reconstruction, where pre-defined image prior is replaced by learnable data-adaptive prior. However, LDCT is clinically multilevel, since clinical scans have different noise levels that depend of scanning site, patient size, and clinical task. Therefore, this work aims to develop an adaptive-hyper-parameter DL-based image reconstruction method (AHP-Net) that can handle multilevel LDCT of different noise levels. AHP-Net unrolls a half-quadratic splitting scheme with learnable image prior built on framelet filter bank, and learns a network that automatically adjusts the hyper-parameters for various noise levels. As a result, AHP-Net provides a single universal training model that can handle multilevel LDCT. Extensive experimental evaluations using clinical scans suggest that AHP-Net outperformed conventional MBIR techniques and state-of-the-art deep-learning-based methods for multilevel LDCT of different noise levels.