Robust T2 relaxometry with Hamiltonian MCMC for myelin water fraction estimation

Robust T2 relaxometry with Hamiltonian MCMC for myelin water fraction estimation. Pizzolato, M., Yu, T., Canales-Rodriguez, E. J., & Thiran, J. In In IEEE International Symposium on Biomedical Imaging (ISBI), Venice, Italy, Venice, Italy, 2019.
abstract bibtex

We present a voxel-wise Bayesian multi-compartment T2 relaxometry fitting method based on Hamiltonian Markov Chain Monte Carlo (HMCMC) sampling. The T2 spectrum is modeled as a mixture of truncated Gaussian components, which involves the estimation of parameters in a completely data-driven and voxel-based fashion, i.e. without fixing any parameters or imposing spatial regularization. We estimate each parameter as the expectation of the corre- sponding marginal distribution drawn from the joint posterior obtained with Hamiltonian sampling. We validate our scheme on synthetic and ex vivo data for which histology is available. We show that the proposed method enables a more robust parameter estimation than a state of the art point estimate based on differential evolution. Moreover, the proposed HMCMC-based myelin water fraction calculation reveals high spatial correlation with the histological counterpart.

@inproceedings{pizzolato2019isbi1,
    address = {Venice, Italy},
    title = {Robust T2 relaxometry with Hamiltonian MCMC for myelin water fraction estimation},
    abstract = {We present a voxel-wise Bayesian multi-compartment T2 relaxometry fitting method based on Hamiltonian Markov Chain Monte Carlo (HMCMC) sampling. The T2 spectrum is modeled as a mixture of truncated Gaussian components, which involves the estimation of parameters in a completely data-driven and voxel-based fashion, i.e. without fixing any parameters or imposing spatial regularization. We estimate each parameter as the expectation of the corre- sponding marginal distribution drawn from the joint posterior obtained with Hamiltonian sampling. We validate our scheme on synthetic and ex vivo data for which histology is available. We show that the proposed method enables a more robust parameter estimation than a state of the art point estimate based on differential evolution. Moreover, the proposed HMCMC-based myelin water fraction calculation reveals high spatial correlation with the histological counterpart.},
    booktitle = {In IEEE International Symposium on Biomedical Imaging (ISBI), Venice, Italy},
    author = {Pizzolato, Marco and Yu, Thomas and Canales-Rodriguez, Erick Jorge and Thiran, Jean-Philippe},
    year = {2019}
}

Downloads: 0

{"_id":"h5DWfNeGGpuKc4bMe","bibbaseid":"pizzolato-yu-canalesrodriguez-thiran-robustt2relaxometrywithhamiltonianmcmcformyelinwaterfractionestimation-2019","downloads":0,"creationDate":"2019-02-11T16:00:39.265Z","title":"Robust T2 relaxometry with Hamiltonian MCMC for myelin water fraction estimation","author_short":["Pizzolato, M.","Yu, T.","Canales-Rodriguez, E. J.","Thiran, J."],"year":2019,"bibtype":"inproceedings","biburl":"https://sinergiaconsortium.bitbucket.io/resources/bibtex/publications.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Venice, Italy","title":"Robust T2 relaxometry with Hamiltonian MCMC for myelin water fraction estimation","abstract":"We present a voxel-wise Bayesian multi-compartment T2 relaxometry fitting method based on Hamiltonian Markov Chain Monte Carlo (HMCMC) sampling. The T2 spectrum is modeled as a mixture of truncated Gaussian components, which involves the estimation of parameters in a completely data-driven and voxel-based fashion, i.e. without fixing any parameters or imposing spatial regularization. We estimate each parameter as the expectation of the corre- sponding marginal distribution drawn from the joint posterior obtained with Hamiltonian sampling. We validate our scheme on synthetic and ex vivo data for which histology is available. We show that the proposed method enables a more robust parameter estimation than a state of the art point estimate based on differential evolution. Moreover, the proposed HMCMC-based myelin water fraction calculation reveals high spatial correlation with the histological counterpart.","booktitle":"In IEEE International Symposium on Biomedical Imaging (ISBI), Venice, Italy","author":[{"propositions":[],"lastnames":["Pizzolato"],"firstnames":["Marco"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Thomas"],"suffixes":[]},{"propositions":[],"lastnames":["Canales-Rodriguez"],"firstnames":["Erick","Jorge"],"suffixes":[]},{"propositions":[],"lastnames":["Thiran"],"firstnames":["Jean-Philippe"],"suffixes":[]}],"year":"2019","bibtex":"@inproceedings{pizzolato2019isbi1,\n address = {Venice, Italy},\n title = {Robust T2 relaxometry with Hamiltonian MCMC for myelin water fraction estimation},\n abstract = {We present a voxel-wise Bayesian multi-compartment T2 relaxometry fitting method based on Hamiltonian Markov Chain Monte Carlo (HMCMC) sampling. The T2 spectrum is modeled as a mixture of truncated Gaussian components, which involves the estimation of parameters in a completely data-driven and voxel-based fashion, i.e. without fixing any parameters or imposing spatial regularization. We estimate each parameter as the expectation of the corre- sponding marginal distribution drawn from the joint posterior obtained with Hamiltonian sampling. We validate our scheme on synthetic and ex vivo data for which histology is available. We show that the proposed method enables a more robust parameter estimation than a state of the art point estimate based on differential evolution. Moreover, the proposed HMCMC-based myelin water fraction calculation reveals high spatial correlation with the histological counterpart.},\n booktitle = {In IEEE International Symposium on Biomedical Imaging (ISBI), Venice, Italy},\n author = {Pizzolato, Marco and Yu, Thomas and Canales-Rodriguez, Erick Jorge and Thiran, Jean-Philippe},\n year = {2019}\n}\n\n","author_short":["Pizzolato, M.","Yu, T.","Canales-Rodriguez, E. J.","Thiran, J."],"key":"pizzolato2019isbi1","id":"pizzolato2019isbi1","bibbaseid":"pizzolato-yu-canalesrodriguez-thiran-robustt2relaxometrywithhamiltonianmcmcformyelinwaterfractionestimation-2019","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["robust","relaxometry","hamiltonian","mcmc","myelin","water","fraction","estimation","pizzolato","yu","canales-rodriguez","thiran"],"keywords":[],"authorIDs":[],"dataSources":["wEGX6SMfTj4mEEPK9"]}