Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptation
Quality assessment and artifact detection in functional magnetic resonance imaging (fMRI) data is essential for clinical applications and brain research. Subject head motion remains the main source of artifacts - even the tiniest head movement can perturb the structural and functional data derived f...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2023-12-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | https://www.computeroptics.ru/eng/KO/Annot/KO47-6/470617e.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832580264282292224 |
|---|---|
| author | N.S. Davydov V.V. Evdokimova P.G. Serafimovich V.I. Protsenko A.G. Khramov A.V. Nikonorov |
| author_facet | N.S. Davydov V.V. Evdokimova P.G. Serafimovich V.I. Protsenko A.G. Khramov A.V. Nikonorov |
| author_sort | N.S. Davydov |
| collection | DOAJ |
| description | Quality assessment and artifact detection in functional magnetic resonance imaging (fMRI) data is essential for clinical applications and brain research. Subject head motion remains the main source of artifacts - even the tiniest head movement can perturb the structural and functional data derived from the fMRI. In this paper, we propose an end-to-end neural network technology for detecting step anomalies with training on partially synthetic data with adaptation to a specific small set of real data. A procedure for generating a synthetic dataset for training and a module for automated labeling of real data is developed. A recurrent neural network model for detecting step anomalies is proposed. A method for the model adaptation to a small set of real data based on one-step meta-learning is developed. An experimental verification of the accuracy is carried out in the problem of detecting step anomalies using a sliding window of 10, 15, and 24 pixels. The experiments have shown the proposed technology to provide the detection of stepwise anomalies with an accuracy of 0.9546. |
| format | Article |
| id | doaj-art-6403e18b638a4b7996efdb77c7a7af4c |
| institution | Kabale University |
| issn | 0134-2452 2412-6179 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj-art-6403e18b638a4b7996efdb77c7a7af4c2025-01-30T11:08:20ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792023-12-01476991100110.18287/2412-6179-CO-1337Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptationN.S. Davydov0V.V. Evdokimova1P.G. Serafimovich2V.I. Protsenko3A.G. Khramov4A.V. Nikonorov5IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RAS; Samara National Research UniversityIPSI RAS – Branch of the FSRC "Crystallography and Photonics" RAS; Samara National Research UniversityIPSI RAS – Branch of the FSRC "Crystallography and Photonics" RAS; Samara National Research UniversitySamara National Research University; IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RASSamara National Research University; IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RASSamara National Research University; IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RASQuality assessment and artifact detection in functional magnetic resonance imaging (fMRI) data is essential for clinical applications and brain research. Subject head motion remains the main source of artifacts - even the tiniest head movement can perturb the structural and functional data derived from the fMRI. In this paper, we propose an end-to-end neural network technology for detecting step anomalies with training on partially synthetic data with adaptation to a specific small set of real data. A procedure for generating a synthetic dataset for training and a module for automated labeling of real data is developed. A recurrent neural network model for detecting step anomalies is proposed. A method for the model adaptation to a small set of real data based on one-step meta-learning is developed. An experimental verification of the accuracy is carried out in the problem of detecting step anomalies using a sliding window of 10, 15, and 24 pixels. The experiments have shown the proposed technology to provide the detection of stepwise anomalies with an accuracy of 0.9546.https://www.computeroptics.ru/eng/KO/Annot/KO47-6/470617e.htmlrecurrent neural networksanomaly detectionsignal analysisfunctional magnetic resonance imagingmeta-learning |
| spellingShingle | N.S. Davydov V.V. Evdokimova P.G. Serafimovich V.I. Protsenko A.G. Khramov A.V. Nikonorov Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptation Компьютерная оптика recurrent neural networks anomaly detection signal analysis functional magnetic resonance imaging meta-learning |
| title | Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptation |
| title_full | Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptation |
| title_fullStr | Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptation |
| title_full_unstemmed | Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptation |
| title_short | Neural network for step anomaly detection in head motion during fMRI using meta-learning adaptation |
| title_sort | neural network for step anomaly detection in head motion during fmri using meta learning adaptation |
| topic | recurrent neural networks anomaly detection signal analysis functional magnetic resonance imaging meta-learning |
| url | https://www.computeroptics.ru/eng/KO/Annot/KO47-6/470617e.html |
| work_keys_str_mv | AT nsdavydov neuralnetworkforstepanomalydetectioninheadmotionduringfmriusingmetalearningadaptation AT vvevdokimova neuralnetworkforstepanomalydetectioninheadmotionduringfmriusingmetalearningadaptation AT pgserafimovich neuralnetworkforstepanomalydetectioninheadmotionduringfmriusingmetalearningadaptation AT viprotsenko neuralnetworkforstepanomalydetectioninheadmotionduringfmriusingmetalearningadaptation AT agkhramov neuralnetworkforstepanomalydetectioninheadmotionduringfmriusingmetalearningadaptation AT avnikonorov neuralnetworkforstepanomalydetectioninheadmotionduringfmriusingmetalearningadaptation |