Age Estimation from fMRI Data Using Recurrent Neural Network
Finding a biomarker that indicates the subject’s age is one of the most important topics in biology. Several recent studies tried to extract a biomarker from brain imaging data including fMRI data. However, most of them focused on MRI data, which do not provide dynamics and lack attempts to apply re...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/2/749 |
| _version_ | 1797496093774184448 |
|---|---|
| author | Yunfei Gao Albert No |
| author_facet | Yunfei Gao Albert No |
| author_sort | Yunfei Gao |
| collection | DOAJ |
| description | Finding a biomarker that indicates the subject’s age is one of the most important topics in biology. Several recent studies tried to extract a biomarker from brain imaging data including fMRI data. However, most of them focused on MRI data, which do not provide dynamics and lack attempts to apply recently proposed deep learning models. We propose a deep neural network model that estimates the age of a subject from fMRI images using a recurrent neural network (RNN), more precisely, a gated recurrent unit (GRU). However, applying neural networks is not trivial due to the high dimensional nature of fMRI data. In this work, we propose a novel preprocessing technique using the Automated Anatomical Labeling (AAL) atlas, which significantly reduces the input dimension. The proposed dimension reduction technique allows us to train our model with 640 training and validation samples from different projects under mean squared error (MSE). Finally, we obtain the correlation value of 0.905 between the predicted age and the actual age on 155 test samples. The proposed model estimates the age within the range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>±</mo><mn>12</mn></mrow></semantics></math></inline-formula> on most of the test samples. Our model is written in Python and is freely available for download. |
| first_indexed | 2024-03-10T01:58:45Z |
| format | Article |
| id | doaj.art-4c4a042bd8d740e58b88c7ab05c6fb40 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T01:58:45Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4c4a042bd8d740e58b88c7ab05c6fb402023-11-23T12:52:07ZengMDPI AGApplied Sciences2076-34172022-01-0112274910.3390/app12020749Age Estimation from fMRI Data Using Recurrent Neural NetworkYunfei Gao0Albert No1Department of Electronic and Electrical Engineering, Hongik University, Seoul 04066, KoreaDepartment of Electronic and Electrical Engineering, Hongik University, Seoul 04066, KoreaFinding a biomarker that indicates the subject’s age is one of the most important topics in biology. Several recent studies tried to extract a biomarker from brain imaging data including fMRI data. However, most of them focused on MRI data, which do not provide dynamics and lack attempts to apply recently proposed deep learning models. We propose a deep neural network model that estimates the age of a subject from fMRI images using a recurrent neural network (RNN), more precisely, a gated recurrent unit (GRU). However, applying neural networks is not trivial due to the high dimensional nature of fMRI data. In this work, we propose a novel preprocessing technique using the Automated Anatomical Labeling (AAL) atlas, which significantly reduces the input dimension. The proposed dimension reduction technique allows us to train our model with 640 training and validation samples from different projects under mean squared error (MSE). Finally, we obtain the correlation value of 0.905 between the predicted age and the actual age on 155 test samples. The proposed model estimates the age within the range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>±</mo><mn>12</mn></mrow></semantics></math></inline-formula> on most of the test samples. Our model is written in Python and is freely available for download.https://www.mdpi.com/2076-3417/12/2/749age estimationfunctional magnetic resonance imagingrecurrent neural networktransformer |
| spellingShingle | Yunfei Gao Albert No Age Estimation from fMRI Data Using Recurrent Neural Network Applied Sciences age estimation functional magnetic resonance imaging recurrent neural network transformer |
| title | Age Estimation from fMRI Data Using Recurrent Neural Network |
| title_full | Age Estimation from fMRI Data Using Recurrent Neural Network |
| title_fullStr | Age Estimation from fMRI Data Using Recurrent Neural Network |
| title_full_unstemmed | Age Estimation from fMRI Data Using Recurrent Neural Network |
| title_short | Age Estimation from fMRI Data Using Recurrent Neural Network |
| title_sort | age estimation from fmri data using recurrent neural network |
| topic | age estimation functional magnetic resonance imaging recurrent neural network transformer |
| url | https://www.mdpi.com/2076-3417/12/2/749 |
| work_keys_str_mv | AT yunfeigao ageestimationfromfmridatausingrecurrentneuralnetwork AT albertno ageestimationfromfmridatausingrecurrentneuralnetwork |