Tags

Type your tag names separated by a space and hit enter

A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction.
Med Phys 2017; 44(10):e360-e375MP

Abstract

PURPOSE

Due to the potential risk of inducing cancer, radiation exposure by X-ray CT devices should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts typically occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high-quality reconstruction method from low-dose X-ray CT data has become a major research topic in the CT community. Conventional model-based de-noising approaches are, however, computationally very expensive, and image-domain de-noising approaches cannot readily remove CT-specific noise patterns. To tackle these problems, we want to develop a new low-dose X-ray CT algorithm based on a deep-learning approach.

METHOD

We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low-dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra- and inter- band correlations, our deep network can effectively suppress CT-specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance.

RESULTS

Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X-ray dose. In addition, we show that the wavelet-domain CNN is efficient when used to remove noise from low-dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 "Low-Dose CT Grand Challenge."

CONCLUSIONS

To the best of our knowledge, this work is the first deep-learning architecture for low-dose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model-based iterative reconstruction (MBIR) methods, has considerable potential to benefit from large data sets. Therefore, we believe that the proposed algorithm opens a new direction in the area of low-dose CT research.

Authors+Show Affiliations

Bio Imaging and Signal Processing Lab., Dept. of Bio and Brain Engineering, KAIST, Daejeon, Korea.Bio Imaging and Signal Processing Lab., Dept. of Bio and Brain Engineering, KAIST, Daejeon, Korea.Bio Imaging and Signal Processing Lab., Dept. of Bio and Brain Engineering, KAIST, Daejeon, Korea.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

29027238

Citation

Kang, Eunhee, et al. "A Deep Convolutional Neural Network Using Directional Wavelets for Low-dose X-ray CT Reconstruction." Medical Physics, vol. 44, no. 10, 2017, pp. e360-e375.
Kang E, Min J, Ye JC. A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Med Phys. 2017;44(10):e360-e375.
Kang, E., Min, J., & Ye, J. C. (2017). A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Medical Physics, 44(10), pp. e360-e375. doi:10.1002/mp.12344.
Kang E, Min J, Ye JC. A Deep Convolutional Neural Network Using Directional Wavelets for Low-dose X-ray CT Reconstruction. Med Phys. 2017;44(10):e360-e375. PubMed PMID: 29027238.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. AU - Kang,Eunhee, AU - Min,Junhong, AU - Ye,Jong Chul, PY - 2016/10/27/received PY - 2017/05/02/revised PY - 2017/05/04/accepted PY - 2017/10/14/entrez PY - 2017/10/14/pubmed PY - 2018/5/23/medline KW - convolutional neural network KW - deep learning KW - low-dose x-ray CT KW - wavelet transform SP - e360 EP - e375 JF - Medical physics JO - Med Phys VL - 44 IS - 10 N2 - PURPOSE: Due to the potential risk of inducing cancer, radiation exposure by X-ray CT devices should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts typically occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high-quality reconstruction method from low-dose X-ray CT data has become a major research topic in the CT community. Conventional model-based de-noising approaches are, however, computationally very expensive, and image-domain de-noising approaches cannot readily remove CT-specific noise patterns. To tackle these problems, we want to develop a new low-dose X-ray CT algorithm based on a deep-learning approach. METHOD: We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low-dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra- and inter- band correlations, our deep network can effectively suppress CT-specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance. RESULTS: Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X-ray dose. In addition, we show that the wavelet-domain CNN is efficient when used to remove noise from low-dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 "Low-Dose CT Grand Challenge." CONCLUSIONS: To the best of our knowledge, this work is the first deep-learning architecture for low-dose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model-based iterative reconstruction (MBIR) methods, has considerable potential to benefit from large data sets. Therefore, we believe that the proposed algorithm opens a new direction in the area of low-dose CT research. SN - 2473-4209 UR - https://www.unboundmedicine.com/medline/citation/29027238/A_deep_convolutional_neural_network_using_directional_wavelets_for_low_dose_X_ray_CT_reconstruction_ L2 - https://doi.org/10.1002/mp.12344 DB - PRIME DP - Unbound Medicine ER -