Self-supervised inter- and intra-slice correlation learning for low-dose CT image restoration without ground truth

作者：

Highlights：

• Training a CNN-based denoiser with LDCT images and without FDCT references.

• Inter- and intra-slice correlation incorporated into self-supervised learning.

• Online finetuning to further improve denoising performance.

• Retrospective study with LDCT patients to explore clinical applicability.

摘要

•Training a CNN-based denoiser with LDCT images and without FDCT references.•Inter- and intra-slice correlation incorporated into self-supervised learning.•Online finetuning to further improve denoising performance.•Retrospective study with LDCT patients to explore clinical applicability.

论文关键词：Low-dose CT,Image denoising,Self-supervised learning,Intra-slice correlation,Inter-slice correlation,Online finetuning

论文评审过程：Received 27 February 2022, Revised 12 May 2022, Accepted 3 July 2022, Available online 8 July 2022, Version of Record 29 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118072