Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey

Since 2016, deep learning (DL) has advanced tomographic imaging with remarkable successes, especially in low-dose computed tomography (LDCT) imaging. Despite being driven by big data, the LDCT denoising and pure end-to-end reconstruction networks often suffer from the black-box nature and major issues, such as instabilities, which are major barriers to applying DL methods in LDCT applications. An emerging trend is to integrate imaging physics and models into deep networks, enabling a hybridization of physics-/model-based and data-driven elements. In this article, we systematically review the physics-/model-based data-driven methods for LDCT, summarize the loss functions and training strategies, evaluate the performance of different methods, and discuss relevant issues and future directions.

Automated summary

Since 2016, deep learning has made remarkable progress in tomographic imaging, particularly in low-dose computed tomography (LDCT). However, the black-box nature and instabilities of LDCT denoising and end-to-end reconstruction networks hinder the application of DL methods in LDCT. A recent trend is to integrate imaging physics and models into deep networks, allowing for a combination of physics-/model-based and data-driven elements. This article provides a systematic review of physics-/model-based data-driven methods for LDCT, including loss functions, training strategies, performance evaluation, and future directions.