Cargando…
Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising
BACKGROUND: Deep learning has been successfully applied to low‐dose CT (LDCT) denoising. But the training of the model is very dependent on an appropriate loss function. Existing denoising models often use per‐pixel loss, including mean abs error (MAE) and mean square error (MSE). This ignores the d...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10476999/ https://www.ncbi.nlm.nih.gov/pubmed/37571834 http://dx.doi.org/10.1002/acm2.14113 |
_version_ | 1785101054062362624 |
---|---|
author | Wang, Zhenchuan Liu, Minghui Cheng, Xuan Zhu, Jinqi Wang, Xiaomin Gong, Haigang Liu, Ming Xu, Lifeng |
author_facet | Wang, Zhenchuan Liu, Minghui Cheng, Xuan Zhu, Jinqi Wang, Xiaomin Gong, Haigang Liu, Ming Xu, Lifeng |
author_sort | Wang, Zhenchuan |
collection | PubMed |
description | BACKGROUND: Deep learning has been successfully applied to low‐dose CT (LDCT) denoising. But the training of the model is very dependent on an appropriate loss function. Existing denoising models often use per‐pixel loss, including mean abs error (MAE) and mean square error (MSE). This ignores the difference in denoising difficulty between different regions of the CT images and leads to the loss of large texture information in the generated image. PURPOSE: In this paper, we propose a new hybrid loss function that adapts to the noise in different regions of CT images to balance the denoising difficulty and preserve texture details, thus acquiring CT images with high‐quality diagnostic value using LDCT images, providing strong support for condition diagnosis. METHODS: We propose a hybrid loss function consisting of weighted patch loss (WPLoss) and high‐frequency information loss (HFLoss). To enhance the model's denoising ability of the local areas which are difficult to denoise, we improve the MAE to obtain WPLoss. After the generated image and the target image are divided into several patches, the loss weight of each patch is adaptively and dynamically adjusted according to its loss ratio. In addition, considering that texture details are contained in the high‐frequency information of the image, we use HFLoss to calculate the difference between CT images in the high‐frequency information part. RESULTS: Our hybrid loss function improves the denoising performance of several models in the experiment, and obtains a higher peak signal‐to‐noise ratio (PSNR) and structural similarity index (SSIM). Moreover, through visual inspection of the generated results of the comparison experiment, the proposed hybrid function can effectively suppress noise and retain image details. CONCLUSIONS: We propose a hybrid loss function for LDCT image denoising, which has good interpretation properties and can improve the denoising performance of existing models. And the validation results of multiple models using different datasets show that it has good generalization ability. By using this loss function, high‐quality CT images with low radiation are achieved, which can avoid the hazards caused by radiation and ensure the disease diagnosis for patients. |
format | Online Article Text |
id | pubmed-10476999 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | John Wiley and Sons Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-104769992023-09-05 Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising Wang, Zhenchuan Liu, Minghui Cheng, Xuan Zhu, Jinqi Wang, Xiaomin Gong, Haigang Liu, Ming Xu, Lifeng J Appl Clin Med Phys Medical Imaging BACKGROUND: Deep learning has been successfully applied to low‐dose CT (LDCT) denoising. But the training of the model is very dependent on an appropriate loss function. Existing denoising models often use per‐pixel loss, including mean abs error (MAE) and mean square error (MSE). This ignores the difference in denoising difficulty between different regions of the CT images and leads to the loss of large texture information in the generated image. PURPOSE: In this paper, we propose a new hybrid loss function that adapts to the noise in different regions of CT images to balance the denoising difficulty and preserve texture details, thus acquiring CT images with high‐quality diagnostic value using LDCT images, providing strong support for condition diagnosis. METHODS: We propose a hybrid loss function consisting of weighted patch loss (WPLoss) and high‐frequency information loss (HFLoss). To enhance the model's denoising ability of the local areas which are difficult to denoise, we improve the MAE to obtain WPLoss. After the generated image and the target image are divided into several patches, the loss weight of each patch is adaptively and dynamically adjusted according to its loss ratio. In addition, considering that texture details are contained in the high‐frequency information of the image, we use HFLoss to calculate the difference between CT images in the high‐frequency information part. RESULTS: Our hybrid loss function improves the denoising performance of several models in the experiment, and obtains a higher peak signal‐to‐noise ratio (PSNR) and structural similarity index (SSIM). Moreover, through visual inspection of the generated results of the comparison experiment, the proposed hybrid function can effectively suppress noise and retain image details. CONCLUSIONS: We propose a hybrid loss function for LDCT image denoising, which has good interpretation properties and can improve the denoising performance of existing models. And the validation results of multiple models using different datasets show that it has good generalization ability. By using this loss function, high‐quality CT images with low radiation are achieved, which can avoid the hazards caused by radiation and ensure the disease diagnosis for patients. John Wiley and Sons Inc. 2023-08-11 /pmc/articles/PMC10476999/ /pubmed/37571834 http://dx.doi.org/10.1002/acm2.14113 Text en © 2023 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, LLC on behalf of The American Association of Physicists in Medicine. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Medical Imaging Wang, Zhenchuan Liu, Minghui Cheng, Xuan Zhu, Jinqi Wang, Xiaomin Gong, Haigang Liu, Ming Xu, Lifeng Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising |
title | Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising |
title_full | Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising |
title_fullStr | Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising |
title_full_unstemmed | Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising |
title_short | Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising |
title_sort | self‐adaption and texture generation: a hybrid loss function for low‐dose ct denoising |
topic | Medical Imaging |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10476999/ https://www.ncbi.nlm.nih.gov/pubmed/37571834 http://dx.doi.org/10.1002/acm2.14113 |
work_keys_str_mv | AT wangzhenchuan selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising AT liuminghui selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising AT chengxuan selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising AT zhujinqi selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising AT wangxiaomin selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising AT gonghaigang selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising AT liuming selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising AT xulifeng selfadaptionandtexturegenerationahybridlossfunctionforlowdosectdenoising |