Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study
Background Aiming to evaluate the effects of the smart metal artifact reduction (MAR) algorithm and combinations of various scanning parameters, including radiation dose levels, tube voltage, and reconstruction algorithms, on metal artifact reduction and overall image quality, to identify the optima...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-06-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/19516.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849727780583899136 |
|---|---|
| author | Huachun Zou Zonghuo Wang Mengya Guo Kun Peng Jian Zhou Lili Zhou Bing Fan |
| author_facet | Huachun Zou Zonghuo Wang Mengya Guo Kun Peng Jian Zhou Lili Zhou Bing Fan |
| author_sort | Huachun Zou |
| collection | DOAJ |
| description | Background Aiming to evaluate the effects of the smart metal artifact reduction (MAR) algorithm and combinations of various scanning parameters, including radiation dose levels, tube voltage, and reconstruction algorithms, on metal artifact reduction and overall image quality, to identify the optimal protocol for clinical application. Methods A phantom with a pacemaker was examined using standard dose (effective dose (ED): 3 mSv) and low dose (ED: 0.5 mSv), with three scan voltages (70, 100, and 120 kVp) selected for each dose. Raw data were reconstructed using 50% adaptive statistical iterative reconstruction-V (ASIR-V), ASIR-V with MAR, high-strength deep learning image reconstruction (DLIR-H), and DLIR-H with MAR. Quantitative analyses (artifact index (AI), noise, signal-to-noise ratio (SNR) of artifact-impaired pulmonary nodules (PNs), and noise power spectrum (NPS) of artifact-free regions) and qualitative evaluation were performed. Results Quantitatively, the deep learning image recognition (DLIR) algorithm or high tube voltages exhibited lower noise compared to the ASIR-V or low tube voltages (p < 0.001). AI of images with MAR or high tube voltages was significantly lower than that of images without MAR or low tube voltages (p < 0.001). No significant difference was observed in AI between low-dose images with 120 kVp DLIR-H MAR and standard-dose images with 70 kVp ASIR-V MAR (p = 0.143). Only the 70 kVp 3 mSv protocol demonstrated statistically significant differences in SNR for artifact-impaired PNs (p = 0.041). The fpeak and favg values were similar across various scenarios, indicating that the MAR algorithm did not alter the image texture in artifact-free regions. The qualitative results of the extent of metal artifacts, the confidence in diagnosing artifact-impaired PNs, and the overall image quality were generally consistent with the quantitative results. Conclusion The MAR algorithm combined with DLIR-H can reduce metal artifacts and enhance the overall image quality, particularly at high kVp tube voltages. |
| format | Article |
| id | doaj-art-d4e5bfcbaec34534b1828b2180712919 |
| institution | DOAJ |
| issn | 2167-8359 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj-art-d4e5bfcbaec34534b1828b21807129192025-08-20T03:09:45ZengPeerJ Inc.PeerJ2167-83592025-06-0113e1951610.7717/peerj.19516Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom studyHuachun Zou0Zonghuo Wang1Mengya Guo2Kun Peng3Jian Zhou4Lili Zhou5Bing Fan6School of Medical and Information Engineering, Gannan Medical University, Ganzhou, ChinaDepartment of Radiology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaCT Imaging Research Center, GE Healthcare China, Beijing, ChinaDepartment of Radiology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaDepartment of Radiology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaSchool of Medical and Information Engineering, Gannan Medical University, Ganzhou, ChinaDepartment of Radiology, Jiangxi Provincial People’s Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, ChinaBackground Aiming to evaluate the effects of the smart metal artifact reduction (MAR) algorithm and combinations of various scanning parameters, including radiation dose levels, tube voltage, and reconstruction algorithms, on metal artifact reduction and overall image quality, to identify the optimal protocol for clinical application. Methods A phantom with a pacemaker was examined using standard dose (effective dose (ED): 3 mSv) and low dose (ED: 0.5 mSv), with three scan voltages (70, 100, and 120 kVp) selected for each dose. Raw data were reconstructed using 50% adaptive statistical iterative reconstruction-V (ASIR-V), ASIR-V with MAR, high-strength deep learning image reconstruction (DLIR-H), and DLIR-H with MAR. Quantitative analyses (artifact index (AI), noise, signal-to-noise ratio (SNR) of artifact-impaired pulmonary nodules (PNs), and noise power spectrum (NPS) of artifact-free regions) and qualitative evaluation were performed. Results Quantitatively, the deep learning image recognition (DLIR) algorithm or high tube voltages exhibited lower noise compared to the ASIR-V or low tube voltages (p < 0.001). AI of images with MAR or high tube voltages was significantly lower than that of images without MAR or low tube voltages (p < 0.001). No significant difference was observed in AI between low-dose images with 120 kVp DLIR-H MAR and standard-dose images with 70 kVp ASIR-V MAR (p = 0.143). Only the 70 kVp 3 mSv protocol demonstrated statistically significant differences in SNR for artifact-impaired PNs (p = 0.041). The fpeak and favg values were similar across various scenarios, indicating that the MAR algorithm did not alter the image texture in artifact-free regions. The qualitative results of the extent of metal artifacts, the confidence in diagnosing artifact-impaired PNs, and the overall image quality were generally consistent with the quantitative results. Conclusion The MAR algorithm combined with DLIR-H can reduce metal artifacts and enhance the overall image quality, particularly at high kVp tube voltages.https://peerj.com/articles/19516.pdfDeep learning image reconstructionMetal artifact reductionCTImage qualityDiagnostic performance |
| spellingShingle | Huachun Zou Zonghuo Wang Mengya Guo Kun Peng Jian Zhou Lili Zhou Bing Fan Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study PeerJ Deep learning image reconstruction Metal artifact reduction CT Image quality Diagnostic performance |
| title | Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study |
| title_full | Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study |
| title_fullStr | Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study |
| title_full_unstemmed | Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study |
| title_short | Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study |
| title_sort | metal artifact reduction combined with deep learning image reconstruction algorithm for ct image quality optimization a phantom study |
| topic | Deep learning image reconstruction Metal artifact reduction CT Image quality Diagnostic performance |
| url | https://peerj.com/articles/19516.pdf |
| work_keys_str_mv | AT huachunzou metalartifactreductioncombinedwithdeeplearningimagereconstructionalgorithmforctimagequalityoptimizationaphantomstudy AT zonghuowang metalartifactreductioncombinedwithdeeplearningimagereconstructionalgorithmforctimagequalityoptimizationaphantomstudy AT mengyaguo metalartifactreductioncombinedwithdeeplearningimagereconstructionalgorithmforctimagequalityoptimizationaphantomstudy AT kunpeng metalartifactreductioncombinedwithdeeplearningimagereconstructionalgorithmforctimagequalityoptimizationaphantomstudy AT jianzhou metalartifactreductioncombinedwithdeeplearningimagereconstructionalgorithmforctimagequalityoptimizationaphantomstudy AT lilizhou metalartifactreductioncombinedwithdeeplearningimagereconstructionalgorithmforctimagequalityoptimizationaphantomstudy AT bingfan metalartifactreductioncombinedwithdeeplearningimagereconstructionalgorithmforctimagequalityoptimizationaphantomstudy |