Image Quality Assessment for Magnetic Resonance Imaging
Image quality assessment (IQA) algorithms aim to reproduce the human’s perception of the image quality. The growing popularity of image enhancement, generation, and recovery models instigated the development of many methods to assess their performance. However, most IQA solutions are desi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10040654/ |
| _version_ | 1797905471886065664 |
|---|---|
| author | Sergey Kastryulin Jamil Zakirov Nicola Pezzotti Dmitry V. Dylov |
| author_facet | Sergey Kastryulin Jamil Zakirov Nicola Pezzotti Dmitry V. Dylov |
| author_sort | Sergey Kastryulin |
| collection | DOAJ |
| description | Image quality assessment (IQA) algorithms aim to reproduce the human’s perception of the image quality. The growing popularity of image enhancement, generation, and recovery models instigated the development of many methods to assess their performance. However, most IQA solutions are designed to predict image quality in the general domain, with the applicability to specific areas, such as medical imaging, remaining questionable. Moreover, the selection of these IQA metrics for a specific task typically involves intentionally induced distortions, such as manually added noise or artificial blurring; yet, the chosen metrics are then used to judge the output of real-life computer vision models. In this work, we aspire to fill these gaps by carrying out the most extensive IQA evaluation study for Magnetic Resonance Imaging (MRI) to date (14,700 subjective scores). We use outputs of neural network models trained to solve problems relevant to MRI, including image reconstruction in the scan acceleration, motion correction, and denoising. Our emphasis is on reflecting the radiologist’s perception of the reconstructed images, gauging the most diagnostically influential criteria for the quality of MRI scans: signal-to-noise ratio, contrast-to-noise ratio, and the presence of art efacts. Seven trained radiologists assess these distorted images, with their verdicts then correlated with 35 different image quality metrics (full-reference, no-reference, and distribution-based metrics considered). The top performers– DISTS, HaarPSI, VSI, and FIDVGG16– are found to be efficient across three proposed quality criteria, for all considered anatomies and the target tasks. |
| first_indexed | 2024-04-10T10:05:52Z |
| format | Article |
| id | doaj.art-8fc5b1b4524f4bb6b7568c796739ccd9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T10:05:52Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8fc5b1b4524f4bb6b7568c796739ccd92023-02-16T00:00:36ZengIEEEIEEE Access2169-35362023-01-0111141541416810.1109/ACCESS.2023.324346610040654Image Quality Assessment for Magnetic Resonance ImagingSergey Kastryulin0https://orcid.org/0000-0002-9381-0541Jamil Zakirov1Nicola Pezzotti2https://orcid.org/0000-0001-9554-4331Dmitry V. Dylov3https://orcid.org/0000-0003-2251-3221Philips Research, Moscow, RussiaSkolkovo Institute of Science and Technology, Moscow, RussiaPhilips Research, AE Eindhoven, The NetherlandsSkolkovo Institute of Science and Technology, Moscow, RussiaImage quality assessment (IQA) algorithms aim to reproduce the human’s perception of the image quality. The growing popularity of image enhancement, generation, and recovery models instigated the development of many methods to assess their performance. However, most IQA solutions are designed to predict image quality in the general domain, with the applicability to specific areas, such as medical imaging, remaining questionable. Moreover, the selection of these IQA metrics for a specific task typically involves intentionally induced distortions, such as manually added noise or artificial blurring; yet, the chosen metrics are then used to judge the output of real-life computer vision models. In this work, we aspire to fill these gaps by carrying out the most extensive IQA evaluation study for Magnetic Resonance Imaging (MRI) to date (14,700 subjective scores). We use outputs of neural network models trained to solve problems relevant to MRI, including image reconstruction in the scan acceleration, motion correction, and denoising. Our emphasis is on reflecting the radiologist’s perception of the reconstructed images, gauging the most diagnostically influential criteria for the quality of MRI scans: signal-to-noise ratio, contrast-to-noise ratio, and the presence of art efacts. Seven trained radiologists assess these distorted images, with their verdicts then correlated with 35 different image quality metrics (full-reference, no-reference, and distribution-based metrics considered). The top performers– DISTS, HaarPSI, VSI, and FIDVGG16– are found to be efficient across three proposed quality criteria, for all considered anatomies and the target tasks.https://ieeexplore.ieee.org/document/10040654/Image qualitydeep learningmetricsreconstruction qualityMRI |
| spellingShingle | Sergey Kastryulin Jamil Zakirov Nicola Pezzotti Dmitry V. Dylov Image Quality Assessment for Magnetic Resonance Imaging IEEE Access Image quality deep learning metrics reconstruction quality MRI |
| title | Image Quality Assessment for Magnetic Resonance Imaging |
| title_full | Image Quality Assessment for Magnetic Resonance Imaging |
| title_fullStr | Image Quality Assessment for Magnetic Resonance Imaging |
| title_full_unstemmed | Image Quality Assessment for Magnetic Resonance Imaging |
| title_short | Image Quality Assessment for Magnetic Resonance Imaging |
| title_sort | image quality assessment for magnetic resonance imaging |
| topic | Image quality deep learning metrics reconstruction quality MRI |
| url | https://ieeexplore.ieee.org/document/10040654/ |
| work_keys_str_mv | AT sergeykastryulin imagequalityassessmentformagneticresonanceimaging AT jamilzakirov imagequalityassessmentformagneticresonanceimaging AT nicolapezzotti imagequalityassessmentformagneticresonanceimaging AT dmitryvdylov imagequalityassessmentformagneticresonanceimaging |