AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography
(1) To investigate whether interventional cone-beam computed tomography (cbCT) could benefit from AI denoising, particularly with respect to patient body mass index (BMI); (2) From 1 January 2016 to 1 January 2022, 100 patients with liver-directed interventions and peri-procedural cbCT were included...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Tomography |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2379-139X/8/2/75 |
| _version_ | 1827599300398415872 |
|---|---|
| author | Andreas S. Brendlin Arne Estler David Plajer Adrian Lutz Gerd Grözinger Malte N. Bongers Ilias Tsiflikas Saif Afat Christoph P. Artzner |
| author_facet | Andreas S. Brendlin Arne Estler David Plajer Adrian Lutz Gerd Grözinger Malte N. Bongers Ilias Tsiflikas Saif Afat Christoph P. Artzner |
| author_sort | Andreas S. Brendlin |
| collection | DOAJ |
| description | (1) To investigate whether interventional cone-beam computed tomography (cbCT) could benefit from AI denoising, particularly with respect to patient body mass index (BMI); (2) From 1 January 2016 to 1 January 2022, 100 patients with liver-directed interventions and peri-procedural cbCT were included. The unenhanced mask run and the contrast-enhanced fill run of the cbCT were reconstructed using weighted filtered back projection. Additionally, each dataset was post-processed using a novel denoising software solution. Place-consistent regions of interest measured signal-to-noise ratio (SNR) per dataset. Corrected mixed-effects analysis with BMI subgroup analyses compared objective image quality. Multiple linear regression measured the contribution of “Radiation Dose”, “Body-Mass-Index”, and “Mode” to SNR. Two radiologists independently rated diagnostic confidence. Inter-rater agreement was measured using Spearman correlation (r); (3) SNR was significantly higher in the denoised datasets than in the regular datasets (<i>p</i> < 0.001). Furthermore, BMI subgroup analysis showed significant SNR deteriorations in the regular datasets for higher patient BMI (<i>p</i> < 0.001), but stable results for denoising (<i>p</i> > 0.999). In regression, only denoising contributed positively towards SNR (0.6191; 95%CI 0.6096 to 0.6286; <i>p</i> < 0.001). The denoised datasets received overall significantly higher diagnostic confidence grades (<i>p</i> = 0.010), with good inter-rater agreement (r ≥ 0.795, <i>p</i> < 0.001). In a subgroup analysis, diagnostic confidence deteriorated significantly for higher patient BMI (<i>p</i> < 0.001) in the regular datasets but was stable in the denoised datasets (<i>p</i> ≥ 0.103).; (4) AI denoising can significantly enhance image quality in interventional cone-beam CT and effectively mitigate diagnostic confidence deterioration for rising patient BMI. |
| first_indexed | 2024-03-09T04:09:53Z |
| format | Article |
| id | doaj.art-a4feae00cd424cb3836984217cb00c36 |
| institution | Directory Open Access Journal |
| issn | 2379-1381 2379-139X |
| language | English |
| last_indexed | 2024-03-09T04:09:53Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Tomography |
| spelling | doaj.art-a4feae00cd424cb3836984217cb00c362023-12-03T14:01:16ZengMDPI AGTomography2379-13812379-139X2022-04-018293394710.3390/tomography8020075AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed TomographyAndreas S. Brendlin0Arne Estler1David Plajer2Adrian Lutz3Gerd Grözinger4Malte N. Bongers5Ilias Tsiflikas6Saif Afat7Christoph P. Artzner8Department of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, GermanyDepartment of Diagnostic and Interventional Radiology, Eberhard-Karls University, D-72076 Tuebingen, Germany(1) To investigate whether interventional cone-beam computed tomography (cbCT) could benefit from AI denoising, particularly with respect to patient body mass index (BMI); (2) From 1 January 2016 to 1 January 2022, 100 patients with liver-directed interventions and peri-procedural cbCT were included. The unenhanced mask run and the contrast-enhanced fill run of the cbCT were reconstructed using weighted filtered back projection. Additionally, each dataset was post-processed using a novel denoising software solution. Place-consistent regions of interest measured signal-to-noise ratio (SNR) per dataset. Corrected mixed-effects analysis with BMI subgroup analyses compared objective image quality. Multiple linear regression measured the contribution of “Radiation Dose”, “Body-Mass-Index”, and “Mode” to SNR. Two radiologists independently rated diagnostic confidence. Inter-rater agreement was measured using Spearman correlation (r); (3) SNR was significantly higher in the denoised datasets than in the regular datasets (<i>p</i> < 0.001). Furthermore, BMI subgroup analysis showed significant SNR deteriorations in the regular datasets for higher patient BMI (<i>p</i> < 0.001), but stable results for denoising (<i>p</i> > 0.999). In regression, only denoising contributed positively towards SNR (0.6191; 95%CI 0.6096 to 0.6286; <i>p</i> < 0.001). The denoised datasets received overall significantly higher diagnostic confidence grades (<i>p</i> = 0.010), with good inter-rater agreement (r ≥ 0.795, <i>p</i> < 0.001). In a subgroup analysis, diagnostic confidence deteriorated significantly for higher patient BMI (<i>p</i> < 0.001) in the regular datasets but was stable in the denoised datasets (<i>p</i> ≥ 0.103).; (4) AI denoising can significantly enhance image quality in interventional cone-beam CT and effectively mitigate diagnostic confidence deterioration for rising patient BMI.https://www.mdpi.com/2379-139X/8/2/75cone beam computed tomographyAI (artificial intelligence)image quality enhancement |
| spellingShingle | Andreas S. Brendlin Arne Estler David Plajer Adrian Lutz Gerd Grözinger Malte N. Bongers Ilias Tsiflikas Saif Afat Christoph P. Artzner AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography Tomography cone beam computed tomography AI (artificial intelligence) image quality enhancement |
| title | AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography |
| title_full | AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography |
| title_fullStr | AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography |
| title_full_unstemmed | AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography |
| title_short | AI Denoising Significantly Enhances Image Quality and Diagnostic Confidence in Interventional Cone-Beam Computed Tomography |
| title_sort | ai denoising significantly enhances image quality and diagnostic confidence in interventional cone beam computed tomography |
| topic | cone beam computed tomography AI (artificial intelligence) image quality enhancement |
| url | https://www.mdpi.com/2379-139X/8/2/75 |
| work_keys_str_mv | AT andreassbrendlin aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT arneestler aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT davidplajer aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT adrianlutz aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT gerdgrozinger aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT maltenbongers aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT iliastsiflikas aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT saifafat aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography AT christophpartzner aidenoisingsignificantlyenhancesimagequalityanddiagnosticconfidenceininterventionalconebeamcomputedtomography |