Tags

Type your tag names separated by a space and hit enter

Gradient regularized convolutional neural networks for low-dose CT image enhancement.
Phys Med Biol 2019; 64(16):165017PM

Abstract

The potential risks of x-ray to patients have transferred the public's attention from normal dose CT (NDCT) to low-dose CT (LDCT). However, simply lowering the radiation dose of the CT system will significantly degrade the quality of CT images such as noise and artifacts, which compromises the diagnostic performance. Hence, various methods have been proposed to solve this problem over the past decades. Although these methods have achieved impressive results, they also suffer from a drawback of smoothing image details after denoising, which makes it difficult for clinical diagnosis and treatment. To address this issue, this paper introduces a novel gradient regularization method for LDCT enhancement. Rather than common methods which only consider the pixel-wise gray value loss in the reconstruction procedure, we also take the image gradient loss into consideration to preserve image details. By combining the gradient regularization method and the convolutional neural network (CNN) framework, a gradient regularized convolutional neural network (GRCNN) is proposed to enhance LDCT images which has achieved promising performance in our experiments both visually and quantitatively.

Authors+Show Affiliations

Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University. Xi'an, Shaanxi, People's Republic of China.No affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info availableNo affiliation info available

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31433791

Citation

Gou, Shuiping, et al. "Gradient Regularized Convolutional Neural Networks for Low-dose CT Image Enhancement." Physics in Medicine and Biology, vol. 64, no. 16, 2019, p. 165017.
Gou S, Liu W, Jiao C, et al. Gradient regularized convolutional neural networks for low-dose CT image enhancement. Phys Med Biol. 2019;64(16):165017.
Gou, S., Liu, W., Jiao, C., Liu, H., Gu, Y., Zhang, X., ... Jiao, L. (2019). Gradient regularized convolutional neural networks for low-dose CT image enhancement. Physics in Medicine and Biology, 64(16), p. 165017. doi:10.1088/1361-6560/ab325e.
Gou S, et al. Gradient Regularized Convolutional Neural Networks for Low-dose CT Image Enhancement. Phys Med Biol. 2019 Aug 21;64(16):165017. PubMed PMID: 31433791.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Gradient regularized convolutional neural networks for low-dose CT image enhancement. AU - Gou,Shuiping, AU - Liu,Wei, AU - Jiao,Changzhe, AU - Liu,Haofeng, AU - Gu,Yu, AU - Zhang,Xiaopeng, AU - Lee,Jin, AU - Jiao,Licheng, Y1 - 2019/08/21/ PY - 2019/8/22/entrez SP - 165017 EP - 165017 JF - Physics in medicine and biology JO - Phys Med Biol VL - 64 IS - 16 N2 - The potential risks of x-ray to patients have transferred the public's attention from normal dose CT (NDCT) to low-dose CT (LDCT). However, simply lowering the radiation dose of the CT system will significantly degrade the quality of CT images such as noise and artifacts, which compromises the diagnostic performance. Hence, various methods have been proposed to solve this problem over the past decades. Although these methods have achieved impressive results, they also suffer from a drawback of smoothing image details after denoising, which makes it difficult for clinical diagnosis and treatment. To address this issue, this paper introduces a novel gradient regularization method for LDCT enhancement. Rather than common methods which only consider the pixel-wise gray value loss in the reconstruction procedure, we also take the image gradient loss into consideration to preserve image details. By combining the gradient regularization method and the convolutional neural network (CNN) framework, a gradient regularized convolutional neural network (GRCNN) is proposed to enhance LDCT images which has achieved promising performance in our experiments both visually and quantitatively. SN - 1361-6560 UR - https://www.unboundmedicine.com/medline/citation/31433791/Gradient_regularized_convolutional_neural_networks_for_low_dose_CT_image_enhancement_ L2 - https://doi.org/10.1088/1361-6560/ab325e DB - PRIME DP - Unbound Medicine ER -