@inproceedings{a59a612fefab45759642d8f2a25b3a09,
title = "Self-trained Deep Convolutional Neural Network for Noise Reduction in CT",
abstract = "Supervised deep convolutional neural network (CNN)-based methods have been actively used in clinical CT to reduce image noise. The networks of these methods are typically trained using paired high- and low-quality data from a large number of patients and/or phantom images. This training process is tedious, and the network trained under a given condition may not be generalizable to patient images acquired and reconstructed at different conditions. In this paper, we propose a self-trained deep CNN (ST_CNN) method which does not rely on pre-existing training datasets. The training is accomplished using extensive data augmentation through projection domain and the inference is applied to the data itself. Preliminary evaluation on patient images demonstrated that the proposed method could achieve similar image quality in comparison with conventional deep CNN denoising methods pre-trained on external datasets.",
keywords = "Computed tomography (CT), convolutional neural network (CNN), deep learning, low-dose CT, supervised training",
author = "Zhongxing Zhou and Akitoshi Inoue and McCollough, {Cynthia H.} and Lifeng Yu",
note = "Publisher Copyright: {\textcopyright} 2022 SPIE.; 7th International Conference on Image Formation in X-Ray Computed Tomography ; Conference date: 12-06-2022 Through 16-06-2022",
year = "2022",
doi = "10.1117/12.2646717",
language = "English (US)",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Stayman, {Joseph Webster}",
booktitle = "7th International Conference on Image Formation in X-Ray Computed Tomography",
}