Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model
In clinical environments, the quality of low-dose computerized tomography (LDCT) images is inevitably degraded by artifacts and noise. Accurate and clinically relevant image quality assessment (IQA) for LDCT images is crucial to provide appropriate medical care. However, due to the absence of refere...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10838566/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592953081593856 |
|---|---|
| author | Mo Shen Rongrong Sun Wen Ye |
| author_facet | Mo Shen Rongrong Sun Wen Ye |
| author_sort | Mo Shen |
| collection | DOAJ |
| description | In clinical environments, the quality of low-dose computerized tomography (LDCT) images is inevitably degraded by artifacts and noise. Accurate and clinically relevant image quality assessment (IQA) for LDCT images is crucial to provide appropriate medical care. However, due to the absence of reference images and inadequate understanding of the human visual system (HVS), there is currently a lack of effective IQA methods. To address this problem, this paper proposes a no-reference IQA method that emulates the perceptual characteristics of the HVS. The method is based on the use of sparse representation in conjunction with a just noticeable distortion (JND) model. Specifically, for each tested image, a patch-level JND map is first calculated to indicate the noticeable level of distortion in different regions. Subsequently, noticeable patches of the image are encoded via sparse representation, followed by max pooling to obtain sparse features. Finally, these sparse features, along with the sorted JND values, are combined as overall features into a regression model to predict an objective quality score. By combining two types of features, our method can measure the quality from the perspectives of both local spatial structures and visual distortion sensitivity. Our method is evaluated on the LDCTIQAC2023 database, and the experimental results demonstrate the effectiveness of our method, which correlates reasonably well with the radiologists’ subjective scores. |
| format | Article |
| id | doaj-art-bb1420c73ad84cd59da274b3d080be69 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-bb1420c73ad84cd59da274b3d080be692025-01-21T00:01:13ZengIEEEIEEE Access2169-35362025-01-0113104221043110.1109/ACCESS.2025.352888210838566Sparse Representation-Based LDCT Image Quality Assessment Using the JND ModelMo Shen0https://orcid.org/0009-0000-5244-1957Rongrong Sun1https://orcid.org/0009-0008-4993-3529Wen Ye2Shanghai Institute of Measurement and Testing Technology, Shanghai, ChinaShanghai Institute of Measurement and Testing Technology, Shanghai, ChinaShanghai Public Health Clinical Center, Shanghai, ChinaIn clinical environments, the quality of low-dose computerized tomography (LDCT) images is inevitably degraded by artifacts and noise. Accurate and clinically relevant image quality assessment (IQA) for LDCT images is crucial to provide appropriate medical care. However, due to the absence of reference images and inadequate understanding of the human visual system (HVS), there is currently a lack of effective IQA methods. To address this problem, this paper proposes a no-reference IQA method that emulates the perceptual characteristics of the HVS. The method is based on the use of sparse representation in conjunction with a just noticeable distortion (JND) model. Specifically, for each tested image, a patch-level JND map is first calculated to indicate the noticeable level of distortion in different regions. Subsequently, noticeable patches of the image are encoded via sparse representation, followed by max pooling to obtain sparse features. Finally, these sparse features, along with the sorted JND values, are combined as overall features into a regression model to predict an objective quality score. By combining two types of features, our method can measure the quality from the perspectives of both local spatial structures and visual distortion sensitivity. Our method is evaluated on the LDCTIQAC2023 database, and the experimental results demonstrate the effectiveness of our method, which correlates reasonably well with the radiologists’ subjective scores.https://ieeexplore.ieee.org/document/10838566/CT imagesimage quality assessmentsparse representationjust noticeable distortionhuman visual system |
| spellingShingle | Mo Shen Rongrong Sun Wen Ye Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model IEEE Access CT images image quality assessment sparse representation just noticeable distortion human visual system |
| title | Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model |
| title_full | Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model |
| title_fullStr | Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model |
| title_full_unstemmed | Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model |
| title_short | Sparse Representation-Based LDCT Image Quality Assessment Using the JND Model |
| title_sort | sparse representation based ldct image quality assessment using the jnd model |
| topic | CT images image quality assessment sparse representation just noticeable distortion human visual system |
| url | https://ieeexplore.ieee.org/document/10838566/ |
| work_keys_str_mv | AT moshen sparserepresentationbasedldctimagequalityassessmentusingthejndmodel AT rongrongsun sparserepresentationbasedldctimagequalityassessmentusingthejndmodel AT wenye sparserepresentationbasedldctimagequalityassessmentusingthejndmodel |