Huawei Liu1, Emily Xie1, Helene Ratiney2, Michael Sdika2, and Yan Li1
1Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 2Univ. Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, Lyon, France
1Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 2Univ. Lyon, INSA-Lyon, Université Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm, Lyon, France
Deep learning approach for artifacts filtering was explored and applied on in vivo 7T MRSI datasets acquired from healthy controls and patients with various diseases. An AUC of 0.966 was consistently achieved with different inputs combinations. Ongoing work is in progress for better metrics.
Figure 1. The convolutional neuronal network diagram for taking 3 tiles separated real and magnitude spectra as inputs. The final output value indicates the probability for bad label.
Figure 2. Models with different spectra inputs and tiles and the tested ACC and AUC results. No difference was found between including or not tissue ratios.
