Tags

Type your tag names separated by a space and hit enter

A convolutional neural network for ultra-low-dose CT denoising and emphysema screening.
Med Phys 2019; 46(9):3941-3950MP

Abstract

PURPOSE

Reducing dose level to achieve ALARA is an important task in diagnostic and therapeutic applications of computed tomography (CT) imaging. Effective image quality enhancement strategies are crucial to compensate for the degradation caused by dose reduction. In the past few years, deep learning approaches have demonstrated promising denoising performance on natural/synthetic images. This study tailors a neural network model for (ultra-)low-dose CT denoising, and assesses its performance in enhancing CT image quality and emphysema quantification.

METHODS

The noise statistics in low-dose CT images has its unique characteristics and differs from that used in general denoising models. In this study, we first simulate the paired ultra-low-dose and targeted high-quality image of reference, with a well-validated pipeline. These paired images are used to train a denoising convolutional neural network (DnCNN) with residual mapping. The performance of the DnCNN tailored to CT denoising (DnCNN-CT) is assessed over various dose reduction levels, with respect to both image quality and emphysema scoring quantification. The possible over-smoothing behavior of DnCNN and its impact on different subcohort of patients are also investigated.

RESULTS

Performance evaluation results showed that DnCNN-CT provided significant image quality enhancement, especially for very-low-dose level. With DnCNN-CT denoising on 3%-dose cases, the peak signal-to-noise ratio improved by 8 dB and the structure similarity index increased by 0.15. This outperformed the original DnCNN and the state-of-the-art nonlocal-mean-type denoising scheme. Emphysema mask was also investigated, where lung voxels of abnormally low attenuation coefficient were marked as potential emphysema. Emphysema mask generated after DnCNN-CT denoising on 3%-dose image was demonstrated to agree well with that from the full-dose reference. Despite over-smoothing in DnCNN denoising, which contributed to slight underestimation of emphysema score compared to the reference, such minor overcorrection did not affect clinical conclusions. The proposed method provided effective detection for cases with appreciable emphysema while serving as a reasonable correction for normal cases without emphysema.

CONCLUSIONS

This work provides a tailored DnCNN for (ultra-)low-dose CT denoising, and demonstrates significant improvement on both the image quality and the clinical emphysema quantification accuracy over various dose levels. The clinical conclusion of emphysema obtained from the denoised low-dose images agrees well with that from the full-dose ones.

Authors+Show Affiliations

Department of Radiation Oncology, University of California, Los Angeles, CA, 90095, USA.Departments of Biomedical Physics and Radiology, University of California, Los Angeles, CA, 90095, USA.Department of Radiation Oncology, University of California, Los Angeles, CA, 90095, USA.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

31220358

Citation

Zhao, Tingting, et al. "A Convolutional Neural Network for Ultra-low-dose CT Denoising and Emphysema Screening." Medical Physics, vol. 46, no. 9, 2019, pp. 3941-3950.
Zhao T, McNitt-Gray M, Ruan D. A convolutional neural network for ultra-low-dose CT denoising and emphysema screening. Med Phys. 2019;46(9):3941-3950.
Zhao, T., McNitt-Gray, M., & Ruan, D. (2019). A convolutional neural network for ultra-low-dose CT denoising and emphysema screening. Medical Physics, 46(9), pp. 3941-3950. doi:10.1002/mp.13666.
Zhao T, McNitt-Gray M, Ruan D. A Convolutional Neural Network for Ultra-low-dose CT Denoising and Emphysema Screening. Med Phys. 2019;46(9):3941-3950. PubMed PMID: 31220358.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - A convolutional neural network for ultra-low-dose CT denoising and emphysema screening. AU - Zhao,Tingting, AU - McNitt-Gray,Michael, AU - Ruan,Dan, Y1 - 2019/07/17/ PY - 2019/03/05/received PY - 2019/05/03/revised PY - 2019/05/21/accepted PY - 2019/6/21/pubmed PY - 2019/6/21/medline PY - 2019/6/21/entrez KW - deep network KW - emphasema screening KW - low-dose CT KW - quantitative imaging SP - 3941 EP - 3950 JF - Medical physics JO - Med Phys VL - 46 IS - 9 N2 - PURPOSE: Reducing dose level to achieve ALARA is an important task in diagnostic and therapeutic applications of computed tomography (CT) imaging. Effective image quality enhancement strategies are crucial to compensate for the degradation caused by dose reduction. In the past few years, deep learning approaches have demonstrated promising denoising performance on natural/synthetic images. This study tailors a neural network model for (ultra-)low-dose CT denoising, and assesses its performance in enhancing CT image quality and emphysema quantification. METHODS: The noise statistics in low-dose CT images has its unique characteristics and differs from that used in general denoising models. In this study, we first simulate the paired ultra-low-dose and targeted high-quality image of reference, with a well-validated pipeline. These paired images are used to train a denoising convolutional neural network (DnCNN) with residual mapping. The performance of the DnCNN tailored to CT denoising (DnCNN-CT) is assessed over various dose reduction levels, with respect to both image quality and emphysema scoring quantification. The possible over-smoothing behavior of DnCNN and its impact on different subcohort of patients are also investigated. RESULTS: Performance evaluation results showed that DnCNN-CT provided significant image quality enhancement, especially for very-low-dose level. With DnCNN-CT denoising on 3%-dose cases, the peak signal-to-noise ratio improved by 8 dB and the structure similarity index increased by 0.15. This outperformed the original DnCNN and the state-of-the-art nonlocal-mean-type denoising scheme. Emphysema mask was also investigated, where lung voxels of abnormally low attenuation coefficient were marked as potential emphysema. Emphysema mask generated after DnCNN-CT denoising on 3%-dose image was demonstrated to agree well with that from the full-dose reference. Despite over-smoothing in DnCNN denoising, which contributed to slight underestimation of emphysema score compared to the reference, such minor overcorrection did not affect clinical conclusions. The proposed method provided effective detection for cases with appreciable emphysema while serving as a reasonable correction for normal cases without emphysema. CONCLUSIONS: This work provides a tailored DnCNN for (ultra-)low-dose CT denoising, and demonstrates significant improvement on both the image quality and the clinical emphysema quantification accuracy over various dose levels. The clinical conclusion of emphysema obtained from the denoised low-dose images agrees well with that from the full-dose ones. SN - 2473-4209 UR - https://www.unboundmedicine.com/medline/citation/31220358/A_convolutional_neural_network_for_ultra_low_dose_CT_denoising_and_emphysema_screening_ L2 - https://doi.org/10.1002/mp.13666 DB - PRIME DP - Unbound Medicine ER -