Unpaired low-dose computed tomography image denoising using a progressive cyclical convolutional neural network
© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine..
BACKGROUND: Reducing the radiation dose from computed tomography (CT) can significantly reduce the radiation risk to patients. However, low-dose CT (LDCT) suffers from severe and complex noise interference that affects subsequent diagnosis and analysis. Recently, deep learning-based methods have shown superior performance in LDCT image-denoising tasks. However, most methods require many normal-dose and low-dose CT image pairs, which are difficult to obtain in clinical applications. Unsupervised methods, on the other hand, are more general.
PURPOSE: Deep learning methods based on GAN networks have been widely used for unsupervised LDCT denoising, but the additional memory requirements of the model also hinder its further clinical application. To this end, we propose a simpler multi-stage denoising framework trained using unpaired data, the progressive cyclical convolutional neural network (PCCNN), which can remove the noise from CT images in latent space.
METHODS: Our proposed PCCNN introduces a noise transfer model that transfers noise from LDCT to normal-dose CT (NDCT), denoised CT images generated from unpaired CT images, and noisy CT images. The denoising framework also contains a progressive module that effectively removes noise through multi-stage wavelet transforms without sacrificing high-frequency components such as edges and details.
RESULTS: Compared with seven LDCT denoising algorithms, we perform a quantitative and qualitative evaluation of the experimental results and perform ablation experiments on each network module and loss function. On the AAPM dataset, compared with the contrasted unsupervised methods, our denoising framework has excellent denoising performance increasing the peak signal-to-noise ratio (PSNR) from 29.622 to 30.671, and the structural similarity index (SSIM) was increased from 0.8544 to 0.9199. The PCCNN denoising results were relatively optimal and statistically significant. In the qualitative result comparison, PCCNN without introducing additional blurring and artifacts, the resulting image has higher resolution and complete detail preservation, and the overall structural texture of the image is closer to NDCT. In visual assessments, PCCNN achieves a relatively balanced result in noise suppression, contrast retention, and lesion discrimination.
CONCLUSIONS: Extensive experimental validation shows that our scheme achieves reconstruction results comparable to supervised learning methods and has performed well in image quality and medical diagnostic acceptability.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:51 |
---|---|
Enthalten in: |
Medical physics - 51(2024), 2 vom: 20. Feb., Seite 1289-1312 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Li, Qing [VerfasserIn] |
---|
Links: |
---|
Anmerkungen: |
Date Completed 14.02.2024 Date Revised 14.02.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1002/mp.16331 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM353480606 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM353480606 | ||
003 | DE-627 | ||
005 | 20240214232645.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1002/mp.16331 |2 doi | |
028 | 5 | 2 | |a pubmed24n1292.xml |
035 | |a (DE-627)NLM353480606 | ||
035 | |a (NLM)36841936 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Li, Qing |e verfasserin |4 aut | |
245 | 1 | 0 | |a Unpaired low-dose computed tomography image denoising using a progressive cyclical convolutional neural network |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 14.02.2024 | ||
500 | |a Date Revised 14.02.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine. | ||
520 | |a BACKGROUND: Reducing the radiation dose from computed tomography (CT) can significantly reduce the radiation risk to patients. However, low-dose CT (LDCT) suffers from severe and complex noise interference that affects subsequent diagnosis and analysis. Recently, deep learning-based methods have shown superior performance in LDCT image-denoising tasks. However, most methods require many normal-dose and low-dose CT image pairs, which are difficult to obtain in clinical applications. Unsupervised methods, on the other hand, are more general | ||
520 | |a PURPOSE: Deep learning methods based on GAN networks have been widely used for unsupervised LDCT denoising, but the additional memory requirements of the model also hinder its further clinical application. To this end, we propose a simpler multi-stage denoising framework trained using unpaired data, the progressive cyclical convolutional neural network (PCCNN), which can remove the noise from CT images in latent space | ||
520 | |a METHODS: Our proposed PCCNN introduces a noise transfer model that transfers noise from LDCT to normal-dose CT (NDCT), denoised CT images generated from unpaired CT images, and noisy CT images. The denoising framework also contains a progressive module that effectively removes noise through multi-stage wavelet transforms without sacrificing high-frequency components such as edges and details | ||
520 | |a RESULTS: Compared with seven LDCT denoising algorithms, we perform a quantitative and qualitative evaluation of the experimental results and perform ablation experiments on each network module and loss function. On the AAPM dataset, compared with the contrasted unsupervised methods, our denoising framework has excellent denoising performance increasing the peak signal-to-noise ratio (PSNR) from 29.622 to 30.671, and the structural similarity index (SSIM) was increased from 0.8544 to 0.9199. The PCCNN denoising results were relatively optimal and statistically significant. In the qualitative result comparison, PCCNN without introducing additional blurring and artifacts, the resulting image has higher resolution and complete detail preservation, and the overall structural texture of the image is closer to NDCT. In visual assessments, PCCNN achieves a relatively balanced result in noise suppression, contrast retention, and lesion discrimination | ||
520 | |a CONCLUSIONS: Extensive experimental validation shows that our scheme achieves reconstruction results comparable to supervised learning methods and has performed well in image quality and medical diagnostic acceptability | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a complementary feature fusion module | |
650 | 4 | |a cross-latitude interactive mixed attention | |
650 | 4 | |a low-dose CT denoising | |
650 | 4 | |a multi-level wavelet transformation | |
650 | 4 | |a progressive cyclical convolutional neural network | |
700 | 1 | |a Li, Runrui |e verfasserin |4 aut | |
700 | 1 | |a Li, Saize |e verfasserin |4 aut | |
700 | 1 | |a Wang, Tao |e verfasserin |4 aut | |
700 | 1 | |a Cheng, Yubin |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Shuming |e verfasserin |4 aut | |
700 | 1 | |a Wu, Wei |e verfasserin |4 aut | |
700 | 1 | |a Zhao, Juanjuan |e verfasserin |4 aut | |
700 | 1 | |a Qiang, Yan |e verfasserin |4 aut | |
700 | 1 | |a Wang, Long |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Medical physics |d 1974 |g 51(2024), 2 vom: 20. Feb., Seite 1289-1312 |w (DE-627)NLM000294748 |x 2473-4209 |7 nnns |
773 | 1 | 8 | |g volume:51 |g year:2024 |g number:2 |g day:20 |g month:02 |g pages:1289-1312 |
856 | 4 | 0 | |u http://dx.doi.org/10.1002/mp.16331 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 51 |j 2024 |e 2 |b 20 |c 02 |h 1289-1312 |