1
|
Ries A, Dorosti T, Thalhammer J, Sasse D, Sauter A, Meurer F, Benne A, Lasser T, Pfeiffer F, Schaff F, Pfeiffer D. Improving image quality of sparse-view lung tumor CT images with U-Net. Eur Radiol Exp 2024; 8:54. [PMID: 38698099 PMCID: PMC11065797 DOI: 10.1186/s41747-024-00450-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Accepted: 02/09/2024] [Indexed: 05/05/2024] Open
Abstract
BACKGROUND We aimed to improve the image quality (IQ) of sparse-view computed tomography (CT) images using a U-Net for lung metastasis detection and determine the best tradeoff between number of views, IQ, and diagnostic confidence. METHODS CT images from 41 subjects aged 62.8 ± 10.6 years (mean ± standard deviation, 23 men), 34 with lung metastasis, 7 healthy, were retrospectively selected (2016-2018) and forward projected onto 2,048-view sinograms. Six corresponding sparse-view CT data subsets at varying levels of undersampling were reconstructed from sinograms using filtered backprojection with 16, 32, 64, 128, 256, and 512 views. A dual-frame U-Net was trained and evaluated for each subsampling level on 8,658 images from 22 diseased subjects. A representative image per scan was selected from 19 subjects (12 diseased, 7 healthy) for a single-blinded multireader study. These slices, for all levels of subsampling, with and without U-Net postprocessing, were presented to three readers. IQ and diagnostic confidence were ranked using predefined scales. Subjective nodule segmentation was evaluated using sensitivity and Dice similarity coefficient (DSC); clustered Wilcoxon signed-rank test was used. RESULTS The 64-projection sparse-view images resulted in 0.89 sensitivity and 0.81 DSC, while their counterparts, postprocessed with the U-Net, had improved metrics (0.94 sensitivity and 0.85 DSC) (p = 0.400). Fewer views led to insufficient IQ for diagnosis. For increased views, no substantial discrepancies were noted between sparse-view and postprocessed images. CONCLUSIONS Projection views can be reduced from 2,048 to 64 while maintaining IQ and the confidence of the radiologists on a satisfactory level. RELEVANCE STATEMENT Our reader study demonstrates the benefit of U-Net postprocessing for regular CT screenings of patients with lung metastasis to increase the IQ and diagnostic confidence while reducing the dose. KEY POINTS • Sparse-projection-view streak artifacts reduce the quality and usability of sparse-view CT images. • U-Net-based postprocessing removes sparse-view artifacts while maintaining diagnostically accurate IQ. • Postprocessed sparse-view CTs drastically increase radiologists' confidence in diagnosing lung metastasis.
Collapse
Affiliation(s)
- Annika Ries
- Chair of Biomedical Physics, Department of Physics, School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany
- Munich Institute of Biomedical Engineering, Technical University of Munich, 85748, Garching, Germany
| | - Tina Dorosti
- Chair of Biomedical Physics, Department of Physics, School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany.
- Munich Institute of Biomedical Engineering, Technical University of Munich, 85748, Garching, Germany.
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany.
| | - Johannes Thalhammer
- Chair of Biomedical Physics, Department of Physics, School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany
- Munich Institute of Biomedical Engineering, Technical University of Munich, 85748, Garching, Germany
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany
- Institute for Advanced Study, Technical University of Munich, 85748, Garching, Germany
| | - Daniel Sasse
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany
| | - Andreas Sauter
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany
| | - Felix Meurer
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany
| | - Ashley Benne
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany
- Institute for Advanced Study, Technical University of Munich, 85748, Garching, Germany
| | - Tobias Lasser
- Munich Institute of Biomedical Engineering, Technical University of Munich, 85748, Garching, Germany
- Computational Imaging and Inverse Problems, Department of Computer Science, School of Computation, Information, and Technology, Technical University of Munich, 85748, Garching, Germany
| | - Franz Pfeiffer
- Chair of Biomedical Physics, Department of Physics, School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany
- Munich Institute of Biomedical Engineering, Technical University of Munich, 85748, Garching, Germany
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany
- Institute for Advanced Study, Technical University of Munich, 85748, Garching, Germany
| | - Florian Schaff
- Chair of Biomedical Physics, Department of Physics, School of Natural Sciences, Technical University of Munich, Garching, 85748, Germany
- Munich Institute of Biomedical Engineering, Technical University of Munich, 85748, Garching, Germany
| | - Daniela Pfeiffer
- Department of Diagnostic and Interventional Radiology, School of Medicine, Klinikum Rechts Der Isar, Technical University of Munich, 81675, Munich, Germany
- Institute for Advanced Study, Technical University of Munich, 85748, Garching, Germany
| |
Collapse
|
2
|
Xu N, Ding H, Tang R, Li X, Zhang Z, Lv H, Dai C, Qiu X, Huang Y, Han X, Wang GP, Liu Y, Gong S, Yang Z, Wang Z, Zhao P. Comparative study of the sensitivity of ultra-high-resolution CT and high-resolution CT in the diagnosis of isolated fenestral otosclerosis. Insights Imaging 2023; 14:211. [PMID: 38015307 PMCID: PMC10684447 DOI: 10.1186/s13244-023-01562-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2023] [Accepted: 11/05/2023] [Indexed: 11/29/2023] Open
Abstract
PURPOSE To compare the diagnostic sensitivity of ultra-high-resolution computed tomography (U-HRCT) and HRCT in isolated fenestral otosclerosis (IFO). METHODS A retrospective analysis was conducted on 85 patients (85 ears) diagnosed with IFO between October 2020 and November 2022. U-HRCT (0.1 mm thickness) was performed for 20 ears, HRCT (0.67 mm thickness) for 45 ears, and both for 20 ears. The images were evaluated by general radiologists and neuroradiologists who were blinded to the diagnosis and surgical information. The diagnostic sensitivity of U-HRCT and HRCT for detecting IFO was compared between the two groups. RESULTS Excellent inter-observer agreement existed between the two neuroradiologists (Cohen's κ coefficient 0.806, 95% CI 0.692-0.920), with good agreement between the general radiologists (Cohen's κ coefficient 0.680, 95% CI 0.417-0.943). U-HRCT had a sensitivity of 100% (40/40 ears) for neuroradiologists and 87.5% (35/40 ears) for general radiologists, significantly higher than HRCT (89.2% [58/65 ears] for neuroradiologists; 41.5% [27/65 ears] for general radiologists) (p = 0.042, p' < 0.000). General radiologists' sensitivity with HRCT was significantly lower compared to neuroradiologists (p < 0.000), but no significant difference was observed when general radiologists switched to U-HRCT (p = 0.152). Among the 20 ears that underwent both examinations, U-HRCT detected lesions smaller than 1 mm in 5 ears, whereas HRCT's sensitivity for neuroradiologists was 40% (2/5 ears), significantly lower than for lesions larger than 1 mm (93.3%, 14/15 ears, p = 0.032). CONCLUSION U-HRCT exhibits higher sensitivity than HRCT in diagnosing IFO, suggesting its potential as a screening tool for suspected otosclerosis patients. CRITICAL RELEVANCE STATEMENT Ultra-high-resolution computed tomography has the potential to become a screening tool in patients with suspected otosclerosis and to bridge the diagnostic accuracy gap between general radiologists and neuroradiologists. KEY POINTS • U-HRCT exhibits higher sensitivity than HRCT in the diagnosis of IFO. • U-HRCT has a significant advantage in the detection of less than 1 mm IFO. • U-HRCT has the potential to be used for screening of patients with suspected otosclerosis.
Collapse
Affiliation(s)
- Ning Xu
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Heyu Ding
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Ruowei Tang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Xiaoshuai Li
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Zhengyu Zhang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Han Lv
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Chihang Dai
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Xiaoyu Qiu
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Yan Huang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Xu Han
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Guo-Peng Wang
- Department of Otorhinolaryngology Head and Neck Surgery, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Yuhe Liu
- Department of Otorhinolaryngology Head and Neck Surgery, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Shusheng Gong
- Department of Otorhinolaryngology Head and Neck Surgery, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Zhenghan Yang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China
| | - Zhenchang Wang
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China.
| | - Pengfei Zhao
- Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yongan Road, Xicheng District, Beijing, 100050, China.
| |
Collapse
|