Classification of fMRI data using dynamic time warping based functional connectivity analysis. Meszlényi, R., Peska, L., Gál, V., Vidnyánszky, Z., & Buza, K. In 2016 24th European Signal Processing Conference (EUSIPCO), pages 245-249, Aug, 2016. Paper doi abstract bibtex The synchronized spontaneous low frequency fluctuations of the BOLD signal, as captured by functional MRI measurements, is known to represent the functional connections of different brain areas. The aforementioned MRI measurements result in high-dimensional time series, the dimensions of which correspond to the activity of different brain regions. Recently we have shown that Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient. We have characterized the new metric's stability in multiple measurements, and between subjects in homogenous groups. In this paper we investigated the DTW metric's sensitivity and demonstrated that DTW-based models outperform correlation-based models in resting-state fMRI data classification tasks. Additionally, we show that functional connectivity networks resulting from DTW-based models as compared to the correlation-based models are more stable and sensitive to differences between healthy subjects and patient groups.
@InProceedings{7760247,
author = {R. Meszlényi and L. Peska and V. Gál and Z. Vidnyánszky and K. Buza},
booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)},
title = {Classification of fMRI data using dynamic time warping based functional connectivity analysis},
year = {2016},
pages = {245-249},
abstract = {The synchronized spontaneous low frequency fluctuations of the BOLD signal, as captured by functional MRI measurements, is known to represent the functional connections of different brain areas. The aforementioned MRI measurements result in high-dimensional time series, the dimensions of which correspond to the activity of different brain regions. Recently we have shown that Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient. We have characterized the new metric's stability in multiple measurements, and between subjects in homogenous groups. In this paper we investigated the DTW metric's sensitivity and demonstrated that DTW-based models outperform correlation-based models in resting-state fMRI data classification tasks. Additionally, we show that functional connectivity networks resulting from DTW-based models as compared to the correlation-based models are more stable and sensitive to differences between healthy subjects and patient groups.},
keywords = {biomedical MRI;brain;fluctuations;neurophysiology;signal classification;synchronisation;time series;fMRI data classification;dynamic time warping based functional connectivity analysis;synchronized spontaneous low-frequency fluctuations;functional MRI measurements;functional connections;brain areas;high-dimensional time series;brain regions;BOLD signals;DTW metric sensitivity;DTW-based models;correlation-based models;resting-state fMRI data classification tasks;functional connectivity networks;Time series analysis;Support vector machines;Time measurement;Correlation;Correlation coefficient;Brain models;fMRI;functional connectivity networks;dynamic time warping;classification},
doi = {10.1109/EUSIPCO.2016.7760247},
issn = {2076-1465},
month = {Aug},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2016/papers/1570255287.pdf},
}
Downloads: 0
{"_id":"aFuXMZFrFGhp6jq44","bibbaseid":"meszlnyi-peska-gl-vidnynszky-buza-classificationoffmridatausingdynamictimewarpingbasedfunctionalconnectivityanalysis-2016","authorIDs":[],"author_short":["Meszlényi, R.","Peska, L.","Gál, V.","Vidnyánszky, Z.","Buza, K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["R."],"propositions":[],"lastnames":["Meszlényi"],"suffixes":[]},{"firstnames":["L."],"propositions":[],"lastnames":["Peska"],"suffixes":[]},{"firstnames":["V."],"propositions":[],"lastnames":["Gál"],"suffixes":[]},{"firstnames":["Z."],"propositions":[],"lastnames":["Vidnyánszky"],"suffixes":[]},{"firstnames":["K."],"propositions":[],"lastnames":["Buza"],"suffixes":[]}],"booktitle":"2016 24th European Signal Processing Conference (EUSIPCO)","title":"Classification of fMRI data using dynamic time warping based functional connectivity analysis","year":"2016","pages":"245-249","abstract":"The synchronized spontaneous low frequency fluctuations of the BOLD signal, as captured by functional MRI measurements, is known to represent the functional connections of different brain areas. The aforementioned MRI measurements result in high-dimensional time series, the dimensions of which correspond to the activity of different brain regions. Recently we have shown that Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient. We have characterized the new metric's stability in multiple measurements, and between subjects in homogenous groups. In this paper we investigated the DTW metric's sensitivity and demonstrated that DTW-based models outperform correlation-based models in resting-state fMRI data classification tasks. Additionally, we show that functional connectivity networks resulting from DTW-based models as compared to the correlation-based models are more stable and sensitive to differences between healthy subjects and patient groups.","keywords":"biomedical MRI;brain;fluctuations;neurophysiology;signal classification;synchronisation;time series;fMRI data classification;dynamic time warping based functional connectivity analysis;synchronized spontaneous low-frequency fluctuations;functional MRI measurements;functional connections;brain areas;high-dimensional time series;brain regions;BOLD signals;DTW metric sensitivity;DTW-based models;correlation-based models;resting-state fMRI data classification tasks;functional connectivity networks;Time series analysis;Support vector machines;Time measurement;Correlation;Correlation coefficient;Brain models;fMRI;functional connectivity networks;dynamic time warping;classification","doi":"10.1109/EUSIPCO.2016.7760247","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2016/papers/1570255287.pdf","bibtex":"@InProceedings{7760247,\n author = {R. Meszlényi and L. Peska and V. Gál and Z. Vidnyánszky and K. Buza},\n booktitle = {2016 24th European Signal Processing Conference (EUSIPCO)},\n title = {Classification of fMRI data using dynamic time warping based functional connectivity analysis},\n year = {2016},\n pages = {245-249},\n abstract = {The synchronized spontaneous low frequency fluctuations of the BOLD signal, as captured by functional MRI measurements, is known to represent the functional connections of different brain areas. The aforementioned MRI measurements result in high-dimensional time series, the dimensions of which correspond to the activity of different brain regions. Recently we have shown that Dynamic Time Warping (DTW) distance can be used as a similarity measure between BOLD signals of brain regions as an alternative of the traditionally used correlation coefficient. We have characterized the new metric's stability in multiple measurements, and between subjects in homogenous groups. In this paper we investigated the DTW metric's sensitivity and demonstrated that DTW-based models outperform correlation-based models in resting-state fMRI data classification tasks. Additionally, we show that functional connectivity networks resulting from DTW-based models as compared to the correlation-based models are more stable and sensitive to differences between healthy subjects and patient groups.},\n keywords = {biomedical MRI;brain;fluctuations;neurophysiology;signal classification;synchronisation;time series;fMRI data classification;dynamic time warping based functional connectivity analysis;synchronized spontaneous low-frequency fluctuations;functional MRI measurements;functional connections;brain areas;high-dimensional time series;brain regions;BOLD signals;DTW metric sensitivity;DTW-based models;correlation-based models;resting-state fMRI data classification tasks;functional connectivity networks;Time series analysis;Support vector machines;Time measurement;Correlation;Correlation coefficient;Brain models;fMRI;functional connectivity networks;dynamic time warping;classification},\n doi = {10.1109/EUSIPCO.2016.7760247},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2016/papers/1570255287.pdf},\n}\n\n","author_short":["Meszlényi, R.","Peska, L.","Gál, V.","Vidnyánszky, Z.","Buza, K."],"key":"7760247","id":"7760247","bibbaseid":"meszlnyi-peska-gl-vidnynszky-buza-classificationoffmridatausingdynamictimewarpingbasedfunctionalconnectivityanalysis-2016","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2016/papers/1570255287.pdf"},"keyword":["biomedical MRI;brain;fluctuations;neurophysiology;signal classification;synchronisation;time series;fMRI data classification;dynamic time warping based functional connectivity analysis;synchronized spontaneous low-frequency fluctuations;functional MRI measurements;functional connections;brain areas;high-dimensional time series;brain regions;BOLD signals;DTW metric sensitivity;DTW-based models;correlation-based models;resting-state fMRI data classification tasks;functional connectivity networks;Time series analysis;Support vector machines;Time measurement;Correlation;Correlation coefficient;Brain models;fMRI;functional connectivity networks;dynamic time warping;classification"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2016url.bib","creationDate":"2021-02-13T17:31:51.951Z","downloads":0,"keywords":["biomedical mri;brain;fluctuations;neurophysiology;signal classification;synchronisation;time series;fmri data classification;dynamic time warping based functional connectivity analysis;synchronized spontaneous low-frequency fluctuations;functional mri measurements;functional connections;brain areas;high-dimensional time series;brain regions;bold signals;dtw metric sensitivity;dtw-based models;correlation-based models;resting-state fmri data classification tasks;functional connectivity networks;time series analysis;support vector machines;time measurement;correlation;correlation coefficient;brain models;fmri;functional connectivity networks;dynamic time warping;classification"],"search_terms":["classification","fmri","data","using","dynamic","time","warping","based","functional","connectivity","analysis","meszlényi","peska","gál","vidnyánszky","buza"],"title":"Classification of fMRI data using dynamic time warping based functional connectivity analysis","year":2016,"dataSources":["koSYCfyY2oQJhf2Tc","JiQJrC76kvCnC3mZd"]}