Metal artifact reduction combined with deep learning image reconstruction algorithm for CT image quality optimization: a phantom study

• Published in: PeerJ (San Francisco, CA) Vol. 13; p. e19516
• Main Authors: Zou, Huachun, Wang, Zonghuo, Guo, Mengya, Peng, Kun, Zhou, Jian, Zhou, Lili, Fan, Bing
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 04.06.2025; PeerJ, Inc; PeerJ Inc
• Subjects: Algorithms; Artificial intelligence; Cardiology; Computational Science; Computed tomography; CT imaging; Data Mining and Machine Learning; Data Science; Deep Learning; Deep learning image reconstruction; Diagnostic performance; Humans; Image processing; Image Processing, Computer-Assisted - methods; Image quality; Image reconstruction; Lung nodules; Machine learning; Medical imaging; Medical research; Metal artifact reduction; Metals; Nodules; Optimization; Pacemakers; Phantoms, Imaging; Quantitative analysis; Radiation; Radiation Dosage; Radiographic Image Interpretation, Computer-Assisted - methods; Radiology and Medical Imaging; Signal to noise ratio; Software; Statistical analysis; Tomography, X-Ray Computed - methods; Transplants & implants; South Dakota; United States > US; Image quality; CT; Diagnostic performance; Deep learning image reconstruction; Metal artifact reduction
• ISSN: 2167-8359; 2167-8359; 2376-5992
• DOI: 10.7717/peerj.19516

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. 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. Quantitatively, the deep learning image recognition (DLIR) algorithm or high tube voltages exhibited lower noise compared to the ASIR-V or low tube voltages (  < 0.001). AI of images with MAR or high tube voltages was significantly lower than that of images without MAR or low tube voltages (  < 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 (  = 0.143). Only the 70 kVp 3 mSv protocol demonstrated statistically significant differences in SNR for artifact-impaired PNs (  = 0.041). The f and f 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. The MAR algorithm combined with DLIR-H can reduce metal artifacts and enhance the overall image quality, particularly at high kVp tube voltages.