1.西安交通大学第一附属医院医学影像科,西安 710061
2.西安交通大学第一附属医院PET-CT室,西安 710061
Received:17 April 2025,
Published Online:18 November 2025,
移动端阅览
曹乐,刘翔,樊钢练等.深度学习重建算法和自适应统计迭代重建对上腹部增强CT图像噪声和纹理的比较研究[J].重庆医科大学学报,
Cao Le,Liu Xiang,Fan Ganglian,et al.Effect of deep learning reconstruction algorithm versus adaptive statistical iterative reconstruction-V on image noise and texture in upper abdominal contrast-enhanced CT[J].Journal of Chongqing Medical University,
曹乐,刘翔,樊钢练等.深度学习重建算法和自适应统计迭代重建对上腹部增强CT图像噪声和纹理的比较研究[J].重庆医科大学学报, DOI:10.13406/j.cnki.cyxb..
Cao Le,Liu Xiang,Fan Ganglian,et al.Effect of deep learning reconstruction algorithm versus adaptive statistical iterative reconstruction-V on image noise and texture in upper abdominal contrast-enhanced CT[J].Journal of Chongqing Medical University, DOI:10.13406/j.cnki.cyxb..
目的
2
比较深度学习重建算法(deep learning reconstruction algorithm,DLIR)与自适应统计迭代重建(adaptive statistical iterative reconstruction-V,ASIR-V)对上腹部增强计算机断层扫描(computed tomography,CT)图像噪声和纹理的影响。
方法
2
回顾性分析40例上腹部增强CT图像,分别采用ASIR-V的10%、30%、50%、70%和90% 5个等级,深度学习重建的低、中、高(DLIR-L、DLIR-M、DLIR-H)3个等级重建1.25 mm图像。客观评价肝实质、脾脏、椎旁肌肉的CT值及噪声,计算肝实质、脾脏和椎旁肌肉的CT值偏度系数以反映图像纹理;主观评价使用图像噪声、图像对比度、失真伪影和使用5点离散视觉量表评估图像噪声纹理。
结果
2
2种重建算法中,肝实质、脾脏和椎旁肌肉的图像噪声均随重建强度的增加而降低;ASIR-V图像的CT值偏度随重建百分比增加而增大,而DLIR图像的CT值偏度随重建强度增加而保持不变或减小,且低于ASIR-V图像,70%和90%的ASIR-V图像出现“太光滑”和“斑点”现象。而DLIR主观评分在失真伪影和噪声纹理方面明显高于ASIR-V。
结论
2
DLIR能在不改变图像噪声纹理的情况下有效降低图像噪声。
Objective
2
To investigate the effect of deep learning image reconstruction(DLIR) versus adaptive statistical iterative reconstruction-V(ASIR-V) on image noise and texture in upper abdominal contrast-enhanced CT.
Methods
2
A retrospective analysis was performed for the upper abdominal contrast-enhanced CT images of 40 patients,and images were reconstructed at 1.25 mm slice thickness using 10,30%,50%,70%,and 90% ASIR-V and DLIR at low(DLIR-L),medium(DLIR-M),and high(DLIR-H) settings. For objective evaluation,the CT values and noise of liver parenchyma,spleen,and paravertebral muscle were measured,and the skewness coefficients of the CT values for these structures were calculated to reflect image texture; for subjective evaluation,image noise,image contrast,distortion artifacts,and a 5-point discrete visual scale were used to assess image noise and texture.
Results
2
For both reconstruction algorithms,image noise in liver parenchyma,spleen,and paravertebral muscle decreased with the increase in reconstruction strength. The skewness of CT values on ASIR-V increased with the increase in reconstruction percentage,while the skewness of CT values on DLIR remained unchanged or decreased with the increase in reconstruction strength and was lower than that on ASIR-V images. The 70% and 90% ASIR-V images appeared to be “too smooth” and “speckled”. However,the subjective score of DLIR was significantly higher than that of ASIR-V in terms of distortion artifacts and noise texture.
Conclusion
2
DLIR can effectively reduce image noise without changing image noise texture.
Brenner DJ , Hall EJ . Computed tomography: an increasing source of radiation exposure [J ] . N Engl J Med , 2007 , 357 ( 22 ): 2277 - 2284 .
Patlas MN . Ultra low dose CT for non-traumatic abdominal emergencies:Current challenges and opportunities [J ] . Diagn Interv Imaging , 2021 , 102 ( 6 ): 335 - 336 .
Larsen NE , Mikkelsen E , Knudsen AR , et al . Low-dose CT for diagnosing intestinal obstruction and pneumoperitoneum; need for retakes and diagnostic accuracy [J ] . Acta Radiol Open , 2021 , 10 ( 3 ): 2058460121989313 .
李 婧 , 张 莹 . 多层螺旋CT低剂量与图像质量相关性的研究 [J ] . 医疗装备 , 2009 , 22 ( 5 ): 11 - 15 .
Li J , Zhang Y . The relativity study between low radiation dose and image quality in multi-detector spiral CT [J ] . Chin J Med Device , 2009 , 22 ( 5 ): 11 - 15 .
Einstein SA , Rong XJ , Jensen CT , et al . Quantification and homogenization of image noise between two CT scanner models [J ] . J Appl Clin Med Phys , 2020 , 21 ( 1 ): 174 - 178 .
Noël PB , Fingerle AA , Renger B , et al . Initial performance characterization of a clinical noise-suppressing reconstruction algorithm for MDCT [J ] . AJR Am J Roentgenol , 2011 , 197 ( 6 ): 1404 - 1409 .
孙记航 , 杨利新 , 唐晓璐 , 等 . 应用深度学习图像重建算法提升多发性大动脉炎患儿增强CT血管壁测量精度的研究 [J ] . 中华放射学杂志 , 2021 , 55 ( 12 ): 1308 - 1312 .
Sun JH , Yang LX , Tang XL , et al . Application of a deep learning image reconstruction algorithm to improve the measurement accuracy of vessel wall thickening in pediatric patients with Takayasu arteritis [J ] . Chinese Journal of Radiology , 2021 , 55 ( 12 ): 1308 - 1312 .
张 超 , 董 栋 , 王铭君 , 等 . 深度学习图像重建算法在提高CCTA图像质量中的临床价值研究 [J ] . 临床放射学杂志 , 2021 , 40 ( 6 ): 1126 - 1130 .
Zhang C , Dong D , Wang MJ , et al . Clinical application value of deep learning image reconstruction algorithm in improving CCTA image quality [J ] . J Clin Radiol , 2021 , 40 ( 6 ): 1126 - 1130 .
Brady SL , Trout AT , Somasundaram E , et al . Improving image quality and reducing radiation dose for pediatric CT by using deep learning reconstruction [J ] . Radiology , 2021 , 298 ( 1 ): 180 - 188 .
Nam JG , Hong JH , Kim DS , et al . Deep learning reconstruction for contrast-enhanced CT of the upper abdomen:similar image quality with lower radiation dose in direct comparison with iterative reconstruction [J ] . Eur Radiol , 2021 , 31 ( 8 ): 5533 - 5543 .
Cao L , Liu X , Li JY , et al . A study of using a deep learning image reconstruction to improve the image quality of extremely low-dose contrast-enhanced abdominal CT for patients with hepatic lesions [J ] . Br J Radiol , 2021 , 94 ( 1118 ): 20201086 .
Nam JG , Ahn C , Choi H , et al . Image quality of ultralow-dose chest CT using deep learning techniques:potential superiority of vendor-agnostic post-processing over vendor-specific techniques [J ] . Eur Radiol , 2021 , 31 ( 7 ): 5139 - 5147 .
Abadi E , Sanders J , Samei E . Patient-specific quantification of image quality:an automated technique for measuring the distribution of organ Hounsfield units in clinical chest CT images [J ] . Med Phys , 2017 , 44 ( 9 ): 4736 - 4746 .
Mergen V , Racine D , Jungblut L , et al . Virtual noncontrast abdominal imaging with photon-counting detector CT [J ] . Radiology , 2022 , 305 ( 1 ): 107 - 115 .
余晓锷 , 高海英 , 蔡凡伟 , 等 . 基于噪声功率谱的CT图像噪声评价 [J ] . 中国医学影像技术 , 2014 , 30 ( 8 ): 1243 - 1246 .
YU XE , Gao HY , Cai FW , et al . Noise power spectrum-based evaluation of CT image noise [J ] . Chin J Med Imag Technol , 2014 , 30 ( 8 ): 1243 - 1246 .
Riederer SJ , Pelc NJ , Chesler DA . The noise power spectrum in computed X-ray tomography [J ] . Phys Med Biol , 1978 , 23 ( 3 ): 446 - 454 .
Pan T , Hasegawa A , Luo D , et al . Technical Note:Impact on central frequency and noise magnitude ratios by advanced CT image reconstruction techniques [J ] . Med Phys , 2020 , 47 ( 2 ): 480 - 487 .
Mileto A , Guimaraes LS , McCollough CH , et al . State of the art in abdominal CT:the limits of iterative reconstruction algorithms [J ] . Radiology , 2019 , 293 ( 3 ): 491 - 503 .
Willemink MJ , Noël PB . The evolution of image reconstruction for CT-from filtered back projection to artificial intelligence [J ] . Eur Radiol , 2019 , 29 ( 5 ): 2185 - 2195 .
Lell MM , Kachelrieß M . Recent and upcoming technological developments in computed tomography:high speed,low dose,deep learning,multienergy [J ] . Invest Radiol , 2020 , 55 ( 1 ): 8 - 19 .
Singh R , Wu WW , Wang G , et al . Artificial intelligence in image reconstruction:the change is here [J ] . Phys Med , 2020 , 79 : 113 - 125 .
曹 乐 , 刘 翔 , 程燕南 , 等 . 深度学习重建算法在提高门静脉CT图像质量中的应用研究 [J ] . 西安交通大学学报(医学版) , 2022 , 43 ( 6 ): 912 - 917 .
Cao L , Liu X , Cheng YN , et al . Deep learning reconstruction algorithm in improving portal vein CT image quality [J ] . J Xi’an Jiaotong Univ Med Sci , 2022 , 43 ( 6 ): 912 - 917 .
Cao L , Liu X , Qu TT , et al . Improving spatial resolution and diagnostic confidence with thinner slice and deep learning image reconstruction in contrast-enhanced abdominal CT [J ] . Eur Radiol , 2023 , 33 ( 3 ): 1603 - 1611 .
Greffier J , Hamard A , Pereira F , et al . Image quality and dose reduction opportunity of deep learning image reconstruction algorithm for CT:a phantom study [J ] . Eur Radiol , 2020 , 30 ( 7 ): 3951 - 3959 .
Higaki T , Nakamura Y , Zhou J , et al . Deep learning reconstruction at CT:phantom study of the image characteristics [J ] . Acad Radiol , 2020 , 27 ( 1 ): 82 - 87 .
Singh R , Digumarthy SR , Muse VV , et al . Image quality and lesion detection on deep learning reconstruction and iterative reconstruction of submillisievert chest and abdominal CT [J ] . AJR Am J Roentgenol , 2020 , 214 ( 3 ): 566 - 573 .
Tamura A , Mukaida E , Ota Y , et al . Superior objective and subjective image quality of deep learning reconstruction for low-dose abdominal CT imaging in comparison with model-based iterative reconstruction and filtered back projection [J ] . Br J Radiol , 2021 , 94 ( 1123 ): 20201357 .
Jensen CT , Gupta S , Saleh MM , et al . Reduced-dose deep learning reconstruction for abdominal CT of liver metastases [J ] . Radiology , 2022 , 303 ( 1 ): 90 - 98 .
Cao JJ , Mroueh N , Mercaldo N , et al . Detectability of hypoattenuating liver lesions with deep learning CT reconstruction:a phantom and patient study [J ] . Radiology , 2024 , 313 ( 1 ): e232749 .
Caruso D , De Santis D , Del Gaudio A , et al . Low-dose liver CT:image quality and diagnostic accuracy of deep learning image reconstruction algorithm [J ] . Eur Radiol , 2024 , 34 ( 4 ): 2384 - 239
0
Views
1
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621
