摘要【目的】探讨基于机器学习的迭代图像重建算法在骨骼系统磁共振(MRI)扫描中的应用价值。【方法】选取在中南大学湘雅二医院进行1.5 T MRI扫描的87例骨骼系统疾病患者,先进行常规序列扫描,再对其常规扫描的T1WI和T2WI等序列协议进行体素大小、激励次数等参数修改,将其扫描时间减少后再进行扫描,扫描后所获图像导入基于机器学习的迭代图像重建算法软件IQMR进行处理,将所获得的图像用定量和定性两种方法进行统计学分析。【结果】在扫描时间缩短30%的序列使用基于机器学习的迭代图像重建算法处理后,骨骼系统图像质量与常规成像序列图像质量比较,差异无统计学意义(P>0.05)。【结论】基于机器学习的迭代图像重建算法不仅可实现骨骼系统快速成像,并在快速成像的同时可得到与常规成像序列相似的图像质量,提高了工作效率。
Abstract：【Objective】To explore the application value of iterative image reconstruction algorithms based on machine learning in magnetic resonance imaging (MRI) scanning of the skeletal system. 【Methods】87 patients with skeletal system diseases who underwent 1.5T MRI scans at The Second Xiangya Hospital, Central South University were selected. First, routine sequence scans were performed, and then the sequence protocols of T1WI and T2WI were modified with parameters such as voxel size and excitation frequency. The scanning time was reduced before scanning. The images obtained after scanning were imported into the iterative image reconstruction algorithm software IQMR based on machine learning for processing. The obtained images were statistically analyzed using both quantitative and qualitative methods.【Results】After processing the sequence with a 30% reduction in scanning time using an iterative image reconstruction algorithm based on machine learning, there was no statistically significant difference in image quality between the skeletal system and conventional imaging sequences (P>0.05). 【Conclusion】The iterative image reconstruction algorithm based on machine learning can not only achieve fast imaging of bone systems, but also obtain image quality similar to conventional imaging sequences, thereby improving work efficiency.
胡佳袁, 杨湘雄. 基于机器学习的迭代图像重建算法在骨骼系统MRI扫描中的应用价值[J]. 医学临床研究, 2023, 40(12): 1846-1849.
HU Jiayuan,YANG Xiangxiong. The Application Value of Iterative Image Reconstruction Algorithm Based on Machine Learning in MRI Scanning in Skeletal System. JOURNAL OF CLINICAL RESEARCH, 2023, 40(12): 1846-1849.
[1] KATZ J N, ARANT K R, LOESER R F. Diagnosis and treatment of hip and knee osteoarthritis:a review[J].JAMA,2021,325(6):568-578.
[2] ARIYACHAIPANICH A, BAE W C, STATUM S, et al. Update on MRI pulse sequences for the knee: imaging of cartilage, meniscus, tendon, and hardware[J].Semin Musculoskelet Radiol,2017, 21(2): 45-62.
[3] DESHMANE A, GULANI V, GRISWOLD M A, et al. Parallel MR imaging[J].J Magn Reson Imaging,2012, 36(1): 55-72.
[4] LUSTIG M, DONOHO D, PAULY J M. Sparse MRI: the application of compressed sensing for rapid MR imaging[J].Magn Reson Med,2007, 58(6): 1182-1195.
[5] DELATTRE B M A, BOUDABBOUS S, HANSEN C, et al.Compressed sensing MRI of different organs: ready for clinical daily practice?[J].Eur Radiol,2020, 30(1): 308-319.
[6] JOHNSON P M, RECHT M P, KNOLL F. Improving the speed of MRI with artificial intelligence[J].Semin Musculoskelet Radiol,2020, 24(1): 12-20.
[7] WANG Y D, SONG Y, XIE H B, et al. Reconstruction of under-sampled magnetic resonance image based on convolutional neural network[J].Chin J Magn Reson Imaging,2018, 9(6): 453-459.
[8] BUSTIN A, FUIN N, BOTNAR R M, et al. From compressed-sensing to artificial intelligence-based cardiac MRI reconstruction[J].Front Cardiovasc Med,2020, 7: 17.
[9] 中国医学装备协会.中国医学装备发展状况与趋势 (2018)[M].北京:人民卫生出版社,2018.
[10] 汪黎君,毕帆,张力方,等.国产医疗设备成熟度调查与分析[J].中国医疗设备,2015,30(5):6-9.
[11] 付丽媛,梁永刚,陈自谦,等.磁共振成像系统质量控制检测及处置界限建立[J].中国医学装备,2018, 15(12):15-19.
2023, Vol. 40 
