Study of the quantitative evaluation factors for a deep learning-based improved magnetic resonance imaging

被引:1
作者
Yoo, Denis [1 ]
Rah, C. J. [1 ]
Lee, Eric [1 ]
Kim, J. H. [1 ]
Min, Byung Jun [2 ]
Kim, Eun Ho [3 ]
机构
[1] Artificial Intelligent Res Lab, Sheung Wan, Talos, Hong Kong 999077, Peoples R China
[2] Chungbuk Natl Univ Hosp, Dept Radiat Oncol, Cheongju 28644, South Korea
[3] Daegu Catholic Univ, Sch Med, Dept Biochem, Daegu 38430, South Korea
基金
新加坡国家研究基金会;
关键词
Evaluation factor; Traditional-GAN; Cyclic-GAN; BEAM COMPUTED-TOMOGRAPHY; GUIDED RADIOTHERAPY; MRI; VERIFICATION; ENHANCEMENT; GENERATION; IMAGES;
D O I
10.1007/s40042-021-00291-z
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Our research focused on the feasibility of improving the low-field T2 magnetic resonance (MR) images in terms of using a complex and in-depth learning-related algorithm. Set of unpaired images (T2-weighted 0.06 T MR image and 1.5 T MR image for separate individuals) were utilized in two clinical trials/sequences. The trials were conducted to identify deformations in a 1.5 T MR image according to the 0.06 T MR image to fit the image and size of the unpaired set. Afterwards, the cyclic-generative adversarial network (GAN) was applied to produce an artificial MR image of the 0.06 T MR image with reference to the original or the deformed 1.5 T MR image. In the end, an improved 0.06 T MR image was produced using the traditional GAN supplemented by the artificial MR image. T2 and flair MR images were verified for matching T1 and T2 testing models in the context of the traditional GAN. The outcomes relating to the optimized trial based on the improved MR image indicated a measurable improvement of the signal with a positive relationship between the original and the improved images. Quantitative variables were applied to assess the quality of the images, along with other settings, such as the signal improvement ratio and the signal-to-noise ratio (SNR), as well as the variable between the original and the improved MR images. The combination of assessment variables demonstrated that T2 photographs were better in terms of the T1 testing model compared to the T2 testing model.
引用
收藏
页码:885 / 893
页数:9
相关论文
共 31 条
[1]   Mid-space-independent deformable image registration [J].
Aganj, Iman ;
Iglesias, Juan Eugenio ;
Reuter, Martin ;
Sabuncu, Mert Rory ;
Fischl, Bruce .
NEUROIMAGE, 2017, 152 :158-170
[2]  
Al-Manea A, 2007, IFMBE PROC, V15, P255
[3]  
De Deene Y, 2000, MAGN RESON MED, V43, P116, DOI 10.1002/(SICI)1522-2594(200001)43:1<116::AID-MRM14>3.0.CO
[4]  
2-5
[5]   The Value of Magnetic Resonance Imaging for Radiotherapy Planning [J].
Dirix, Piet ;
Haustermans, Karin ;
Vandecaveye, Vincent .
SEMINARS IN RADIATION ONCOLOGY, 2014, 24 (03) :151-159
[6]   Automatic Substitute Computed Tomography Generation and Contouring for Magnetic Resonance Imaging (MRI)-Alone External Beam Radiation Therapy From Standard MRI Sequences [J].
Dowling, Jason A. ;
Sun, Jidi ;
Pichler, Peter ;
Rivest-Henault, David ;
Ghose, Soumya ;
Richardson, Haylea ;
Wratten, Chris ;
Martin, Jarad ;
Arm, Jameen ;
Best, Leah ;
Chandra, Shekhar S. ;
Fripp, Jurgen ;
Menk, Frederick W. ;
Greer, Peter B. .
INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS, 2015, 93 (05) :1144-1153
[7]   Cone beam computed tomography guided treatment delivery and planning verification for magnetic resonance imaging only radiotherapy of the brain [J].
Edmund, Jens M. ;
Andreasen, Daniel ;
Mahmood, Faisal ;
Van Leemput, Koen .
ACTA ONCOLOGICA, 2015, 54 (09) :1496-1500
[8]   A voxel-based investigation for MRI-only radiotherapy of the brain using ultra short echo times [J].
Edmund, Jens M. ;
Kjer, Hans M. ;
Van Leemput, Koen ;
Hansen, Rasmus H. ;
Andersen, Jon A. L. ;
Andreasen, Daniel .
PHYSICS IN MEDICINE AND BIOLOGY, 2014, 59 (23) :7501-7519
[9]   Intra-fractional uncertainties in cone-beam CT based image-guided radiotherapy (IGRT) of pulmonary tumors [J].
Guckenberger, Matthias ;
Meyer, Juergen ;
Wilbert, Juergen ;
Richter, Anne ;
Baier, Kurt ;
Mueller, Gerd ;
Flentje, Michael .
RADIOTHERAPY AND ONCOLOGY, 2007, 83 (01) :57-64
[10]   MR-based synthetic CT generation using a deep convolutional neural network method [J].
Han, Xiao .
MEDICAL PHYSICS, 2017, 44 (04) :1408-1419