Shihan Qiu1,2, Yuhua Chen1,2, Sen Ma1, Zhaoyang Fan1,3,4, Franklin G Moser5, Marcel M Maya5, Anthony G Christodoulou1,2, Yibin Xie1, Debiao Li1,2. 1. Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, USA. 2. Department of Bioengineering, UCLA, Los Angeles, California, USA. 3. Department of Radiology, University of Southern California, Los Angeles, California, USA. 4. Department of Radiation Oncology, University of Southern California, Los Angeles, California, USA. 5. Department of Imaging, Cedars-Sinai Medical Center, Los Angeles, California, USA.
Abstract
PURPOSE: To develop a deep-learning-based method to quantify multiple parameters in the brain from conventional contrast-weighted images. METHODS: Eighteen subjects were imaged using an MR Multitasking sequence to generate reference T1 and T2 maps in the brain. Conventional contrast-weighted images consisting of T1 MPRAGE, T1 GRE, and T2 FLAIR were acquired as input images. A U-Net-based neural network was trained to estimate T1 and T2 maps simultaneously from the contrast-weighted images. Six-fold cross-validation was performed to compare the network outputs with the MR Multitasking references. RESULTS: The deep-learning T1 /T2 maps were comparable with the references, and brain tissue structures and image contrasts were well preserved. A peak signal-to-noise ratio >32 dB and a structural similarity index >0.97 were achieved for both parameter maps. Calculated on brain parenchyma (excluding CSF), the mean absolute errors (and mean percentage errors) for T1 and T2 maps were 52.7 ms (5.1%) and 5.4 ms (7.1%), respectively. ROI measurements on four tissue compartments (cortical gray matter, white matter, putamen, and thalamus) showed that T1 and T2 values provided by the network outputs were in agreement with the MR Multitasking reference maps. The mean differences were smaller than ± 1%, and limits of agreement were within ± 5% for T1 and within ± 10% for T2 after taking the mean differences into account. CONCLUSION: A deep-learning-based technique was developed to estimate T1 and T2 maps from conventional contrast-weighted images in the brain, enabling simultaneous qualitative and quantitative MRI without modifying clinical protocols.
PURPOSE: To develop a deep-learning-based method to quantify multiple parameters in the brain from conventional contrast-weighted images. METHODS: Eighteen subjects were imaged using an MR Multitasking sequence to generate reference T1 and T2 maps in the brain. Conventional contrast-weighted images consisting of T1 MPRAGE, T1 GRE, and T2 FLAIR were acquired as input images. A U-Net-based neural network was trained to estimate T1 and T2 maps simultaneously from the contrast-weighted images. Six-fold cross-validation was performed to compare the network outputs with the MR Multitasking references. RESULTS: The deep-learning T1 /T2 maps were comparable with the references, and brain tissue structures and image contrasts were well preserved. A peak signal-to-noise ratio >32 dB and a structural similarity index >0.97 were achieved for both parameter maps. Calculated on brain parenchyma (excluding CSF), the mean absolute errors (and mean percentage errors) for T1 and T2 maps were 52.7 ms (5.1%) and 5.4 ms (7.1%), respectively. ROI measurements on four tissue compartments (cortical gray matter, white matter, putamen, and thalamus) showed that T1 and T2 values provided by the network outputs were in agreement with the MR Multitasking reference maps. The mean differences were smaller than ± 1%, and limits of agreement were within ± 5% for T1 and within ± 10% for T2 after taking the mean differences into account. CONCLUSION: A deep-learning-based technique was developed to estimate T1 and T2 maps from conventional contrast-weighted images in the brain, enabling simultaneous qualitative and quantitative MRI without modifying clinical protocols.
Authors: I Blystad; I Håkansson; A Tisell; J Ernerudh; Ö Smedby; P Lundberg; E-M Larsson Journal: AJNR Am J Neuroradiol Date: 2015-10-15 Impact factor: 3.825
Authors: Anthony G Christodoulou; Jaime L Shaw; Christopher Nguyen; Qi Yang; Yibin Xie; Nan Wang; Debiao Li Journal: Nat Biomed Eng Date: 2018-04-09 Impact factor: 25.671
Authors: Sen Ma; Nan Wang; Zhaoyang Fan; Marwa Kaisey; Nancy L Sicotte; Anthony G Christodoulou; Debiao Li Journal: Magn Reson Med Date: 2020-10-26 Impact factor: 4.668
Authors: Dan Ma; Vikas Gulani; Nicole Seiberlich; Kecheng Liu; Jeffrey L Sunshine; Jeffrey L Duerk; Mark A Griswold Journal: Nature Date: 2013-03-14 Impact factor: 49.962
Authors: Tianle Cao; Sen Ma; Nan Wang; Sara Gharabaghi; Yibin Xie; Zhaoyang Fan; Elliot Hogg; Chaowei Wu; Fei Han; Michele Tagliati; E Mark Haacke; Anthony G Christodoulou; Debiao Li Journal: Magn Reson Med Date: 2021-10-27 Impact factor: 3.737