Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography
This study evaluated the feasibility of deep-learning-based image reconstruction (DLIR) on coronary computed tomography angiography (CCTA). By using a 20 cm water phantom, the noise reduction ratio and noise power spectrum were evaluated according to the different reconstruction methods. Then 46 pat...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/12/10/3501 |
| _version_ | 1797599658226221056 |
|---|---|
| author | Seul Ah Koo Yunsub Jung Kyoung A Um Tae Hoon Kim Ji Young Kim Chul Hwan Park |
| author_facet | Seul Ah Koo Yunsub Jung Kyoung A Um Tae Hoon Kim Ji Young Kim Chul Hwan Park |
| author_sort | Seul Ah Koo |
| collection | DOAJ |
| description | This study evaluated the feasibility of deep-learning-based image reconstruction (DLIR) on coronary computed tomography angiography (CCTA). By using a 20 cm water phantom, the noise reduction ratio and noise power spectrum were evaluated according to the different reconstruction methods. Then 46 patients who underwent CCTA were retrospectively enrolled. CCTA was performed using the 16 cm coverage axial volume scan technique. All CT images were reconstructed using filtered back projection (FBP); three model-based iterative reconstructions (MBIR) of 40%, 60%, and 80%; and three DLIR algorithms: low (L), medium (M), and high (H). Quantitative and qualitative image qualities of CCTA were compared according to the reconstruction methods. In the phantom study, the noise reduction ratios of MBIR-40%, MBIR-60%, MBIR-80%, DLIR-L, DLIR-M, and DLIR-H were 26.7 ± 0.2%, 39.5 ± 0.5%, 51.7 ± 0.4%, 33.1 ± 0.8%, 43.2 ± 0.8%, and 53.5 ± 0.1%, respectively. The pattern of the noise power spectrum of the DLIR images was more similar to FBP images than MBIR images. In a CCTA study, CCTA yielded a significantly lower noise index with DLIR-H reconstruction than with the other reconstruction methods. DLIR-H showed a higher SNR and CNR than MBIR (<i>p</i> < 0.05). The qualitative image quality of CCTA with DLIR-H was significantly higher than that of MBIR-80% or FBP. The DLIR algorithm was feasible and yielded a better image quality than the FBP or MBIR algorithms on CCTA. |
| first_indexed | 2024-03-11T03:37:21Z |
| format | Article |
| id | doaj.art-4d6ed664f2b54506afef1a6a3f058bd9 |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-11T03:37:21Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-4d6ed664f2b54506afef1a6a3f058bd92023-11-18T01:54:05ZengMDPI AGJournal of Clinical Medicine2077-03832023-05-011210350110.3390/jcm12103501Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography AngiographySeul Ah Koo0Yunsub Jung1Kyoung A Um2Tae Hoon Kim3Ji Young Kim4Chul Hwan Park5Department of Radiology and The Research Institute of Radiological Science, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul 06273, Republic of KoreaResearch Team, GE Healthcare Korea, Seoul 04637, Republic of KoreaResearch Team, GE Healthcare Korea, Seoul 04637, Republic of KoreaDepartment of Radiology and The Research Institute of Radiological Science, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul 06273, Republic of KoreaDepartment of Radiology and The Research Institute of Radiological Science, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul 06273, Republic of KoreaDepartment of Radiology and The Research Institute of Radiological Science, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul 06273, Republic of KoreaThis study evaluated the feasibility of deep-learning-based image reconstruction (DLIR) on coronary computed tomography angiography (CCTA). By using a 20 cm water phantom, the noise reduction ratio and noise power spectrum were evaluated according to the different reconstruction methods. Then 46 patients who underwent CCTA were retrospectively enrolled. CCTA was performed using the 16 cm coverage axial volume scan technique. All CT images were reconstructed using filtered back projection (FBP); three model-based iterative reconstructions (MBIR) of 40%, 60%, and 80%; and three DLIR algorithms: low (L), medium (M), and high (H). Quantitative and qualitative image qualities of CCTA were compared according to the reconstruction methods. In the phantom study, the noise reduction ratios of MBIR-40%, MBIR-60%, MBIR-80%, DLIR-L, DLIR-M, and DLIR-H were 26.7 ± 0.2%, 39.5 ± 0.5%, 51.7 ± 0.4%, 33.1 ± 0.8%, 43.2 ± 0.8%, and 53.5 ± 0.1%, respectively. The pattern of the noise power spectrum of the DLIR images was more similar to FBP images than MBIR images. In a CCTA study, CCTA yielded a significantly lower noise index with DLIR-H reconstruction than with the other reconstruction methods. DLIR-H showed a higher SNR and CNR than MBIR (<i>p</i> < 0.05). The qualitative image quality of CCTA with DLIR-H was significantly higher than that of MBIR-80% or FBP. The DLIR algorithm was feasible and yielded a better image quality than the FBP or MBIR algorithms on CCTA.https://www.mdpi.com/2077-0383/12/10/3501coronary computed tomographic angiographydeep learning-based image reconstructionimage quality |
| spellingShingle | Seul Ah Koo Yunsub Jung Kyoung A Um Tae Hoon Kim Ji Young Kim Chul Hwan Park Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography Journal of Clinical Medicine coronary computed tomographic angiography deep learning-based image reconstruction image quality |
| title | Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography |
| title_full | Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography |
| title_fullStr | Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography |
| title_full_unstemmed | Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography |
| title_short | Clinical Feasibility of Deep Learning-Based Image Reconstruction on Coronary Computed Tomography Angiography |
| title_sort | clinical feasibility of deep learning based image reconstruction on coronary computed tomography angiography |
| topic | coronary computed tomographic angiography deep learning-based image reconstruction image quality |
| url | https://www.mdpi.com/2077-0383/12/10/3501 |
| work_keys_str_mv | AT seulahkoo clinicalfeasibilityofdeeplearningbasedimagereconstructiononcoronarycomputedtomographyangiography AT yunsubjung clinicalfeasibilityofdeeplearningbasedimagereconstructiononcoronarycomputedtomographyangiography AT kyoungaum clinicalfeasibilityofdeeplearningbasedimagereconstructiononcoronarycomputedtomographyangiography AT taehoonkim clinicalfeasibilityofdeeplearningbasedimagereconstructiononcoronarycomputedtomographyangiography AT jiyoungkim clinicalfeasibilityofdeeplearningbasedimagereconstructiononcoronarycomputedtomographyangiography AT chulhwanpark clinicalfeasibilityofdeeplearningbasedimagereconstructiononcoronarycomputedtomographyangiography |