利用深度学习改进定量磁共振成像
Improving Quantitative Magnetic Resonance Imaging Using Deep Learning.
作者信息
Liu Fang
机构信息
Department of Radiology, Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts.
出版信息
Semin Musculoskelet Radiol. 2020 Aug;24(4):451-459. doi: 10.1055/s-0040-1709482. Epub 2020 Sep 29.
Abstract
Deep learning methods have shown promising results for accelerating quantitative musculoskeletal (MSK) magnetic resonance imaging (MRI) for T2 and T1ρ relaxometry. These methods have been shown to improve musculoskeletal tissue segmentation on parametric maps, allowing efficient and accurate T2 and T1ρ relaxometry analysis for monitoring and predicting MSK diseases. Deep learning methods have shown promising results for disease detection on quantitative MRI with diagnostic performance superior to conventional machine-learning methods for identifying knee osteoarthritis.
摘要
深度学习方法已在加速用于T2和T1ρ弛豫测量的定量肌肉骨骼（MSK）磁共振成像（MRI）方面显示出有前景的结果。这些方法已被证明可改善参数图上的肌肉骨骼组织分割，从而实现高效且准确的T2和T1ρ弛豫测量分析，用于监测和预测MSK疾病。深度学习方法在定量MRI疾病检测方面已显示出有前景的结果，其诊断性能优于用于识别膝关节骨关节炎的传统机器学习方法。
相似文献
1
Improving Quantitative Magnetic Resonance Imaging Using Deep Learning.利用深度学习改进定量磁共振成像
Semin Musculoskelet Radiol. 2020 Aug;24(4):451-459. doi: 10.1055/s-0040-1709482. Epub 2020 Sep 29.
2
Automatic Determination of the Need for Intravenous Contrast in Musculoskeletal MRI Examinations Using IBM Watson's Natural Language Processing Algorithm.使用 IBM Watson 的自然语言处理算法自动确定肌肉骨骼 MRI 检查中是否需要静脉造影。
J Digit Imaging. 2018 Apr;31(2):245-251. doi: 10.1007/s10278-017-0021-3.
3
Improving the Speed of MRI with Artificial Intelligence.利用人工智能提高磁共振成像速度
Semin Musculoskelet Radiol. 2020 Feb;24(1):12-20. doi: 10.1055/s-0039-3400265. Epub 2020 Jan 28.
4
Efficiency Improvement in a Busy Radiology Practice: Determination of Musculoskeletal Magnetic Resonance Imaging Protocol Using Deep-Learning Convolutional Neural Networks.繁忙放射科实践中的效率提升：使用深度学习卷积神经网络确定肌肉骨骼磁共振成像方案。
J Digit Imaging. 2018 Oct;31(5):604-610. doi: 10.1007/s10278-018-0066-y.
5
Rapid MR relaxometry using deep learning: An overview of current techniques and emerging trends.基于深度学习的快速磁共振弛豫定量成像：技术现状与未来趋势综述。
NMR Biomed. 2022 Apr;35(4):e4416. doi: 10.1002/nbm.4416. Epub 2020 Oct 15.
6
Quantitative Musculoskeletal Ultrasound.定量肌肉骨骼超声。
Semin Musculoskelet Radiol. 2020 Aug;24(4):367-374. doi: 10.1055/s-0040-1709720. Epub 2020 Sep 29.
7
Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade.人工智能在肌肉骨骼成像中的应用：未来十年的现实临床应用。
Skeletal Radiol. 2024 Sep;53(9):1849-1868. doi: 10.1007/s00256-024-04684-6. Epub 2024 Jun 20.
8
Quantification in Musculoskeletal Imaging Using Computational Analysis and Machine Learning: Segmentation and Radiomics.使用计算分析和机器学习进行肌肉骨骼成像的量化：分割与放射组学。
Semin Musculoskelet Radiol. 2020 Feb;24(1):50-64. doi: 10.1055/s-0039-3400268. Epub 2020 Jan 28.
9
Advancing musculoskeletal tumor diagnosis: Automated segmentation and predictive classification using deep learning and radiomics.推进肌肉骨骼肿瘤诊断：使用深度学习和放射组学进行自动分割和预测分类。
Comput Biol Med. 2024 Jun;175:108502. doi: 10.1016/j.compbiomed.2024.108502. Epub 2024 Apr 22.
10
Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet.深度学习辅助膝关节磁共振成像诊断：MRNet 的开发和回顾性验证。
PLoS Med. 2018 Nov 27;15(11):e1002699. doi: 10.1371/journal.pmed.1002699. eCollection 2018 Nov.
引用本文的文献
1
CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mapping.正确：用于运动校正定量R2*映射的深度展开框架。
J Math Imaging Vis. 2025 Apr;67(2). doi: 10.1007/s10851-025-01236-y. Epub 2025 Apr 2.
2
Deep learning-based acceleration of muscle water T2 mapping in patients with neuromuscular diseases by more than 50% - translating quantitative MRI from research to clinical routine.基于深度学习将神经肌肉疾病患者的肌肉水T2映射加速超50%——将定量MRI从研究转化为临床常规应用
PLoS One. 2025 Apr 16;20(4):e0318599. doi: 10.1371/journal.pone.0318599. eCollection 2025.
3
Relationship between Thyroid CT Density, Volume, and Future TSH Elevation: A 5-Year Follow-Up Study.甲状腺CT密度、体积与未来促甲状腺激素升高之间的关系：一项5年随访研究。
Life (Basel). 2023 Dec 6;13(12):2303. doi: 10.3390/life13122303.
4
SuperMAP: Deep ultrafast MR relaxometry with joint spatiotemporal undersampling.SuperMAP：联合时空欠采样的深度超快磁共振弛豫测量
Magn Reson Med. 2023 Jan;89(1):64-76. doi: 10.1002/mrm.29411. Epub 2022 Sep 21.
本文引用的文献
1
Rapid mono and biexponential 3D-T mapping of knee cartilage using variational networks.使用变分网络对膝关节软骨进行快速单指数和双指数 3D-T 映射。
Sci Rep. 2020 Nov 5;10(1):19144. doi: 10.1038/s41598-020-76126-x.
2
Fully Automated Diagnosis of Anterior Cruciate Ligament Tears on Knee MR Images by Using Deep Learning.利用深度学习对膝关节磁共振成像进行前交叉韧带撕裂的全自动诊断
Radiol Artif Intell. 2019 May 8;1(3):180091. doi: 10.1148/ryai.2019180091.
3
Automated cartilage and meniscus segmentation of knee MRI with conditional generative adversarial networks.基于条件生成对抗网络的膝关节磁共振成像中软骨和半月板的自动分割
Magn Reson Med. 2020 Jul;84(1):437-449. doi: 10.1002/mrm.28111. Epub 2019 Dec 2.
4
Deep Learning for Lesion Detection, Progression, and Prediction of Musculoskeletal Disease.用于肌肉骨骼疾病病变检测、进展及预测的深度学习
J Magn Reson Imaging. 2020 Dec;52(6):1607-1619. doi: 10.1002/jmri.27001. Epub 2019 Nov 25.
5
Rapid Knee MRI Acquisition and Analysis Techniques for Imaging Osteoarthritis.用于骨关节炎成像的快速膝关节磁共振成像采集与分析技术
J Magn Reson Imaging. 2020 Nov;52(5):1321-1339. doi: 10.1002/jmri.26991. Epub 2019 Nov 21.
6
Knee menisci segmentation and relaxometry of 3D ultrashort echo time cones MR imaging using attention U-Net with transfer learning.膝关节半月板分割和 3D 超短回波时间锥形磁共振成像弛豫度的注意力 U-Net 与迁移学习。
Magn Reson Med. 2020 Mar;83(3):1109-1122. doi: 10.1002/mrm.27969. Epub 2019 Sep 19.
7
Utility of deep learning super-resolution in the context of osteoarthritis MRI biomarkers.深度学习超分辨率在骨关节炎 MRI 生物标志物中的应用。
J Magn Reson Imaging. 2020 Mar;51(3):768-779. doi: 10.1002/jmri.26872. Epub 2019 Jul 16.
8
SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstruction.基于非相干结构采样增强神经网络的磁共振图像重建方法。
Magn Reson Med. 2019 Nov;82(5):1890-1904. doi: 10.1002/mrm.27827. Epub 2019 Jun 5.
9
Artificial intelligence to diagnose meniscus tears on MRI.人工智能诊断 MRI 半月板撕裂
Diagn Interv Imaging. 2019 Apr;100(4):243-249. doi: 10.1016/j.diii.2019.02.007. Epub 2019 Mar 28.
10
Diagnosing osteoarthritis from T maps using deep learning: an analysis of the entire Osteoarthritis Initiative baseline cohort.利用深度学习从 T 映射诊断骨关节炎：对整个骨关节炎倡议基线队列的分析。
Osteoarthritis Cartilage. 2019 Jul;27(7):1002-1010. doi: 10.1016/j.joca.2019.02.800. Epub 2019 Mar 21.
Zotero 插件