基于人工智能迭代重建算法（AIIR）重建的超低剂量CT在F-FDG全身PET/CT检查中的初步研究。
Ultra-low-dose CT reconstructed with the artificial intelligence iterative reconstruction algorithm (AIIR) in F-FDG total-body PET/CT examination: a preliminary study.
作者信息
Hu Yan, Zheng Zhe, Yu Haojun, Wang Jingyi, Yang Xinlan, Shi Hongcheng
机构信息
Department of Nuclear Medicine, Zhongshan Hospital, Fudan University, 180 Fenglin Rd, Shanghai, 200032, China.
Nuclear Medicine Institute of Fudan University, Shanghai, 200032, China.
出版信息
EJNMMI Phys. 2023 Jan 2;10(1):1. doi: 10.1186/s40658-022-00521-8.
PURPOSE
To investigate the feasibility of ultra-low-dose CT (ULDCT) reconstructed with the artificial intelligence iterative reconstruction (AIIR) algorithm in total-body PET/CT imaging.
METHODS
The study included both the phantom and clinical parts. An anthropomorphic phantom underwent CT imaging with ULDCT (10mAs) and standard-dose CT (SDCT) (120mAs), respectively. ULDCT was reconstructed with AIIR and hybrid iterative reconstruction (HIR) (expressed as ULDCT-AIIR and ULDCT-HIR), respectively, and SDCT was reconstructed with HIR (SDCT-HIR) as control. In the clinical part, 52 patients with malignant tumors underwent the total-body PET/CT scan. ULDCT with AIIR (ULDCT-AIIR) and HIR (ULDCT-HIR), respectively, was reconstructed for PET attenuation correction, followed by the SDCT reconstructed with HIR (SDCT-HIR) for anatomical location. PET/CT images' quality was qualitatively assessed by two readers. The CT, as well as the CT standard deviation (CT), SUV, SUV, and the SUV standard deviation (SUV), was recorded. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated and compared.
RESULTS
The image quality of ULDCT-HIR was inferior to the SDCT-HIR, but no significant difference was found between the ULDCT-AIIR and SDCT-HIR. The subjective score of ULDCT-AIIR in the neck, chest and lower limb was equivalent to that of SDCT-HIR. Besides the brain and lower limb, the change rates of CT in thyroid, neck muscle, lung, mediastinum, back muscle, liver, lumbar muscle, first lumbar spine and sigmoid colon were -2.15, -1.52, 0.66, 2.97, 0.23, 8.91, 0.06, -4.29 and 8.78%, respectively, while all CT of ULDCT-AIIR was lower than that of SDCT-HIR. Except for the brain, the CNR of ULDCT-AIIR was the same as the SDCT-HIR, but the SNR was higher. The change rates of SUV, SUV and SUV were within [Formula: see text] 3% in all ROIs. For the lesions, the SUV, SUV and TBR showed no significant difference between PET-AIIR and PET-HIR.
CONCLUSION
The SDCT-HIR could not be replaced by the ULDCT-AIIR at date, but the AIIR algorithm decreased the image noise and increased the SNR, which can be implemented under special circumstances in PET/CT examination.
目的
探讨采用人工智能迭代重建（AIIR）算法重建的超低剂量CT（ULDCT）在全身PET/CT成像中的可行性。
方法
研究包括体模和临床两部分。一个仿真人体模分别接受ULDCT（10mAs）和标准剂量CT（SDCT，120mAs）扫描。ULDCT分别采用AIIR和混合迭代重建（HIR）进行重建（分别表示为ULDCT-AIIR和ULDCT-HIR），SDCT采用HIR重建（SDCT-HIR）作为对照。在临床部分，52例恶性肿瘤患者接受全身PET/CT扫描。ULDCT分别采用AIIR（ULDCT-AIIR）和HIR（ULDCT-HIR）进行重建以用于PET衰减校正，然后采用HIR重建的SDCT（SDCT-HIR）用于解剖定位。由两名阅片者对PET/CT图像质量进行定性评估。记录CT值、CT标准差（CT）、SUV、SUV最大值以及SUV标准差（SUV）。计算并比较信噪比（SNR）和对比噪声比（CNR）。
结果
ULDCT-HIR的图像质量低于SDCT-HIR，但ULDCT-AIIR与SDCT-HIR之间未发现显著差异。ULDCT-AIIR在颈部、胸部和下肢的主观评分与SDCT-HIR相当。除脑和下肢外，甲状腺、颈部肌肉、肺、纵隔、背部肌肉、肝脏、腰部肌肉、第一腰椎和乙状结肠的CT值变化率分别为-2.15%、-1.52%、0.66%、2.97%、0.23%、8.91%、0.06%、-4.29%和8.78%，而ULDCT-AIIR的所有CT值均低于SDCT-HIR。除脑外，ULDCT-AIIR的CNR与SDCT-HIR相同，但SNR更高。所有感兴趣区（ROI）的SUV、SUV最大值和SUV标准差的变化率均在±3%以内。对于病变，PET-AIIR和PET-HIR之间的SUV、SUV最大值和肿瘤与本底比值（TBR）无显著差异。
结论
目前ULDCT-AIIR尚不能取代SDCT-HIR，但AIIR算法降低了图像噪声并提高了SNR，可在PET/CT检查的特殊情况下应用。
Zotero 插件