تقرير
Predicting brain-age from raw T(1)-weighted magnetic resonance imaging data using 3D convolutional neural networks
العنوان: | Predicting brain-age from raw T(1)-weighted magnetic resonance imaging data using 3D convolutional neural networks |
---|---|
المؤلفون: | Fisch, L., Ernsting, J., Winter, N.R., Holstein, V., Leenings, R., Beisemann, M., Sarink, K., Emden, D., Opel, N., Redlich, R., Repple, J., Grotegerd, D., Meinert, S., Wulms, N., Minnerup, H., Hirsch, J.G., Niendorf, T., Endemann, B., Bamberg, F., Kröncke, T., Peters, A., Bülow, R., Völzke, H., von Stackelberg, O., Sowade, R.F., Umutlu, L., Schmidt, B., Caspers, S., Kugel, H., Baune, B.T., Kircher, T., Risse, B., Dannlowski, U., Berger, K., Hahn, T. |
بيانات النشر: | Cornell University |
سنة النشر: | 2021 |
المجموعة: | Max-Delbrueck-Center for Molecular Medicine, Berlin: MDC Repository |
مصطلحات موضوعية: | Cardiovascular and Metabolic Diseases, Technology Platforms, Topic 3: Integrative Biomedicine |
الوصف: | Age prediction based on Magnetic Resonance Imaging (MRI) data of the brain is a biomarker to quantify the progress of brain diseases and aging. Current approaches rely on preparing the data with multiple preprocessing steps, such as registering voxels to a standardized brain atlas, which yields a significant computational overhead, hampers widespread usage and results in the predicted brain-age to be sensitive to preprocessing parameters. Here we describe a 3D Convolutional Neural Network (CNN) based on the ResNet architecture being trained on raw, non-registered T(1)-weighted MRI data of N=10,691 samples from the German National Cohort and additionally applied and validated in N=2,173 samples from three independent studies using transfer learning. For comparison, state-of-the-art models using preprocessed neuroimaging data are trained and validated on the same samples. The 3D CNN using raw neuroimaging data predicts age with a mean average deviation of 2.84 years, outperforming the state-of-the-art brain-age models using preprocessed data. Since our approach is invariant to preprocessing software and parameter choices, it enables faster, more robust and more accurate brain-age modeling. |
نوع الوثيقة: | report |
اللغة: | unknown |
العلاقة: | Predicting brain-age from raw T(1)-weighted magnetic resonance imaging data using 3D convolutional neural networks. Fisch, L. and Ernsting, J. and Winter, N.R. and Holstein, V. and Leenings, R. and Beisemann, M. and Sarink, K. and Emden, D. and Opel, N. and Redlich, R. and Repple, J. and Grotegerd, D. and Meinert, S. and Wulms, N. and Minnerup, H. and Hirsch, J.G. and Niendorf, T. and Endemann, B. and Bamberg, F. and Kröncke, T. and Peters, A. and Bülow, R. and Völzke, H. and von Stackelberg, O. and Sowade, R.F. and Umutlu, L. and Schmidt, B. and Caspers, S. and Kugel, H. and Baune, B.T. and Kircher, T. and Risse, B. and Dannlowski, U. and Berger, K. and Hahn, T. arXiv : 2103.11695. 22 March 2021 |
الإتاحة: | http://edoc.mdc-berlin.de/20173Test/ https://edoc.mdc-berlin.de/20173Test/ https://arxiv.org/abs/2103.11695Test |
رقم الانضمام: | edsbas.C96B4E4C |
قاعدة البيانات: | BASE |
الوصف غير متاح. |