黄碧云,马卓雅,陈振涛,丁佳,冉孟新,刘世琛,李仕广,段庆红
HUANG Biyun,MA Zhuoya,CHEN Zhentao,DING Jia,RAN Mengxin,LIU Shichen,LI Shiguang,DUAN Qinghong

• 1:贵州医科大学医学影像学院
• 2:佳能医疗系统中国有限公司影像部
• 3:贵州医科大学附属肿瘤医院影像科
• 4:贵阳市第二人民医院影像科

摘要(Abstract)：

目的 探讨磁共振成像(MRI)深度学习重建(DLR)对乳腺T_2加权(T_2WI)脂肪抑制序列扫描时间及图像质量的影响。方法 招募30名女性志愿者为研究对象，采用平均采集次数(NAQ)为1和2的T_2WI脂肪抑制序列行乳腺MRI扫描，扫描时间分别为217 s和421 s,扫描完成获得Routine NAQ1和Routine NAQ2图像，Routine NAQ1组图像行DLR重建获DLR NAQ1图像，分析比较3组图像的信噪比(SNR)、对比噪声比(CNR)及临床医生主观定性评价资料。结果 女性志愿者DLR NAQ1图像的SNR及CNR优于Routine NAQ1和Routine NAQ2图像(P<0.001),图像整体质量评分均优于Routine NAQ1和Routine NAQ2图像(P<0.001)。结论 MRI DLR可缩短乳腺T_2WI脂肪抑制序列的扫描时间，提高图像质量。
Objective To investigate the impact of deep learning reconstruction(DLR) in magnetic resonance imaging(MRI) on scan time and image quality of breast T_2-weighted(T_2WI) fat suppression sequence. Methods Thirty female volunteers were recruited as research subjects. Breast MRI scan was performed using T_2WI fat suppression sequence with an average number of acquisition(NAQ) of 1 and 2 as well as scan time of 217 s and 421 s, respectively. After scanning, Routine NAQ1 and Routine NAQ2 images were obtained. DLR was run on Routine NAQ1 image group to obtain DLR NAQ1 images. Signal-to-noise ratio(SNR) and contrast-to-noise ratio(CNR) of the images as well as the subjective and qualitative evaluation data from clinicians were analyzed and compared among three groups. Results SNR and CNR of DLR NAQ1 images of female volunteers were better than those of Routine NAQ1 and Routine NAQ2 images(P<0.001), and the overall quality score of the images is better than that of both Route NAQ1 and Route NAQ2 images(P<0.001). Conclusion DLR in MRI can shorten scan time of breast T_2WI fat suppression sequence and improve image quality.

关键词(KeyWords)： 磁共振成像;深度学习重建;脂肪抑制;平均采集次数;乳腺;扫描效率
magnetic resonance imaging;deep learning reconstruction;at suppression;average number of acquisitions;breast;scan efficiency

Abstract:

Keywords:

基金项目(Foundation): 贵州省科技计划项目(黔科合基础-ZK[2023]一般006,黔科合支撑[2021]一般451)

作者(Author): 黄碧云,马卓雅,陈振涛,丁佳,冉孟新,刘世琛,李仕广,段庆红
HUANG Biyun,MA Zhuoya,CHEN Zhentao,DING Jia,RAN Mengxin,LIU Shichen,LI Shiguang,DUAN Qinghong

DOI: 10.19367/j.cnki.2096-8388.2024.06.016

参考文献(References)：

• [1] 国家卫生健康委员会医政医管局.乳腺癌诊疗指南(2022年版)[J].中华肿瘤杂志，2023,45(10):803-833.
• [2] SIEGEL R L,GIAQUINTO A N,JEMAL A.Cancer statistics,2024 [J].CA:A Cancer Journal for Clinicians,2024,74(1):12-49.
• [3] ARNOLD M,MORGAN E,RUMGAY H,et al.Current and future burden of breast cancer:global statistics for 2020 and 2040 [J].Breast,2022,66:15-23.
• [4] 何思怡，李贺，曹毛毛，等.全球及我国女性乳腺癌疾病负担年龄分布及变化趋势[J].中国肿瘤，2023,32(1):1-7.
• [5] 李彦娟，张祥，冯京华，等.超声与磁共振诊断乳腺癌的临床价值比较[J].中国超声医学杂志，2020,36(10):891-894.
• [6] 冯雯，刘欣然，卢星如，等.不同功能磁共振成像技术在乳腺癌中的应用进展 [J].磁共振成像，2024,15(1):217-223.
• [7] 张松，邹利光.乳腺癌磁共振分子成像的研究进展 [J].中国医学影像技术，2011,27(03):627-630.
• [8] HEACOCK L,MELSAETHER A N,HELLER S L,et al.Evaluation of a known breast cancer using an abbreviated breast MRI protocol:correlation of imaging characteristics and pathology with lesion detection and conspicuity [J].European Journal of Radiology,2016,85(4):815-823.
• [9] ARPONEN O,MASARWAH A,SUTELA A,et al.Incidentally detected enhancing lesions found in breast MRI:analysis of apparent diffusion coefficient and T2 signal intensity significantly improves specificity [J].European Radiology,2016,26(12):4361-4370.
• [10]HELLER S L,MOY L.MRI breast screening revisited [J].Journal of Magnetic Resonance Imaging,2019,49(5):1212-1221.
• [11]杨正汉，冯逢，郑卓肇，等.磁共振成像技术指南(第二版)[M].北京：中国协和医科大学出版社，2023:149-156.
• [12]RUIZ-FLORES L,WHITMAN G J,LE-PETROSS H ,et al.Variation in technical quality of breast MRI [J].Academic Radiology,2020,27(4):468-475.
• [13]GASSENMAIER S,AFAT S,NICKEL D,et al.Deep learning-accelerated T2-weighted imaging of the prostate:Reduction of acquisition time and improvement of image quality [J].European Journal of Radiology,2021,137:109600.
• [14]KIM B,LEE C M,JANG J K,et al.Deep learning-based imaging reconstruction for MRI after neoadjuvant chemoradiotherapy for rectal cancer:effects on image quality and assessment of treatment response [J].Abdominal Radiology (New York),2023,48(1):201-210.
• [15]EL-REWAIDY H,FAHMY A S,PASHAKHANLOO F,et al.Multi-domain convolutional neural network (MD-CNN) for radial reconstruction of dynamic cardiac MRI [J].Magnetic Resonance in Medicine,2021,85(3):1195-1208.
• [16]GHODRATI V,BYDDER M,BEDAYAT A,et al.Temporally aware volumetric generative adversarial network-based MR image reconstruction with simultaneous respiratory motion compensation:Initial feasibility in 3D dynamic cine cardiac MRI [J].Magnetic Resonance in Medicine,2021,86(5):2666-2683.
• [17]HAUPTMANN A,ARRIDDGE S,LUCKA F,et al.Real-time cardiovascular MR with spatio-temporal artifact suppression using deep learning-proof of concept in congenital heart disease [J].Magnetic Resonance in Medicine,2019,81(2):1143-1156.
• [18]OSHIMA S,FUSHIMI Y,MIYAKE K K,et al.Denoising approach with deep learning-based reconstruction for neuromelanin-sensitive MRI:image quality and diagnostic performance [J].Japanese Journal of Radiology,2023,41(11):1216-1225.
• [19]范婧，杨文洁，王梦真，等.深度学习重建算法在低管电压冠状动脉CT血管成像中的应用 [J].诊断学理论与实践，2022,21(3):374-379.
• [20]KRUPA K,BEKIESIńSKA-FIGATOWSKA M.Artifacts in magnetic resonance imaging[J].Pol J Radiol,2015 ,80:93-106.
• [21]CUI L,SONG Y,WANG Y,et al.Motion artifact reduction for magnetic resonance imaging with deep learning and k-space analysis[J].PLoS One,2023,18(1):e0278668.
• [22]LIU L,YIN B,SHE K K,et al.Role of quantitative analysis of T2 relaxation time in differentiating benign from malignant breast lesions[J].The Journal of International Medical Research,2018,46(5):1928-1935.
• [23]赵应满，袁利.MRI脂肪抑制技术在乳腺肿瘤诊断中的应用[J].实用放射学杂志，2007(12):1685-1687.
• [24]陈文静，牟伟，张文馨，等.平扫T2脂肪抑制序列图像纹理可提高诊断乳腺良恶性结节的准确率 [J].分子影像学杂志，2019,42(4):453-456.
• [25]GRISWOLD M A,BLAIMER M,BREUER F,et al.Parallel magnetic resonance imaging using the GRAPPA operator formalism [J].Magnetic Resonance in Medicine,2005,(54):1553-1556.
• [26]王丽丽，边传振，张朋.缩短MRI检查时间的相关技术进展[J].中国医疗设备，2022,37(11):170-175.
• [27]OBAMA Y,OHNO Y,YAMAMOTO K,et al.MR imaging for shoulder diseases:Effect of compressed sensing and deep learning reconstruction on examination time and imaging quality compared with that of parallel imaging [J].Magn Reson Imaging,2022,94:56-63.
• [28]KIM M,KIM H S,KIM H J,et al.Thin-slice pituitary MRI with deep learning-based reconstruction:diagnostic performance in a postoperative setting [J].Radiology,2021,298(1):114-122.
• [29]WANG X,MA J,BHOSALE P,et al.Novel deep learning-based noise reduction technique for prostate magnetic resonance imaging [J].Abdominal Radiology (New York),2021,46(7):3378-3386.
• [30]YASAKA K,TANISHIMA T,OHTAKE Y,et al.Deep learning reconstruction for the evaluation of neuroforaminal stenosis using 1.5T cervical spine MRI:comparison with 3T MRI without deep learning reconstruction [J].Neuroradiology,2022,64(10):2077-2083.

文章评论(Comment)：