A Weighted Multi-Sequence Markov Model For Brain Lesion Segmentation

Florence Forbes, Senan Doyle, Daniel Garcia–Lorenzo, Christian Barillot, Michel Dojat
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:225-232, 2010.

Abstract

We propose a technique for fusing the output of multiple Magnetic Resonance (MR) sequences to robustly and accurately segment brain lesions. It is based on an augmented multi-sequence Hidden Markov model that includes additional weight variables to account for the relative importance and control the impact of each sequence. The augmented framework has the advantage of allowing 1) the incorporation of expert knowledge on the a priori relevant information content of each sequence and 2) a weighting scheme which is modified adaptively according to the data and the segmentation task under consideration. The model, applied to the detection of multiple sclerosis and stroke lesions shows promising results.

Cite this Paper

BibTeX
@InProceedings{pmlr-v9-forbes10a, title = {A Weighted Multi-Sequence Markov Model For Brain Lesion Segmentation}, author = {Forbes, Florence and Doyle, Senan and Garcia–Lorenzo, Daniel and Barillot, Christian and Dojat, Michel}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {225--232}, year = {2010}, editor = {Teh, Yee Whye and Titterington, Mike}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v9/forbes10a/forbes10a.pdf}, url = {https://proceedings.mlr.press/v9/forbes10a.html}, abstract = {We propose a technique for fusing the output of multiple Magnetic Resonance (MR) sequences to robustly and accurately segment brain lesions. It is based on an augmented multi-sequence Hidden Markov model that includes additional weight variables to account for the relative importance and control the impact of each sequence. The augmented framework has the advantage of allowing 1) the incorporation of expert knowledge on the a priori relevant information content of each sequence and 2) a weighting scheme which is modified adaptively according to the data and the segmentation task under consideration. The model, applied to the detection of multiple sclerosis and stroke lesions shows promising results.} }
Endnote
%0 Conference Paper %T A Weighted Multi-Sequence Markov Model For Brain Lesion Segmentation %A Florence Forbes %A Senan Doyle %A Daniel Garcia–Lorenzo %A Christian Barillot %A Michel Dojat %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-forbes10a %I PMLR %P 225--232 %U https://proceedings.mlr.press/v9/forbes10a.html %V 9 %X We propose a technique for fusing the output of multiple Magnetic Resonance (MR) sequences to robustly and accurately segment brain lesions. It is based on an augmented multi-sequence Hidden Markov model that includes additional weight variables to account for the relative importance and control the impact of each sequence. The augmented framework has the advantage of allowing 1) the incorporation of expert knowledge on the a priori relevant information content of each sequence and 2) a weighting scheme which is modified adaptively according to the data and the segmentation task under consideration. The model, applied to the detection of multiple sclerosis and stroke lesions shows promising results.
RIS
TY - CPAPER TI - A Weighted Multi-Sequence Markov Model For Brain Lesion Segmentation AU - Florence Forbes AU - Senan Doyle AU - Daniel Garcia–Lorenzo AU - Christian Barillot AU - Michel Dojat BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-forbes10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 9 SP - 225 EP - 232 L1 - http://proceedings.mlr.press/v9/forbes10a/forbes10a.pdf UR - https://proceedings.mlr.press/v9/forbes10a.html AB - We propose a technique for fusing the output of multiple Magnetic Resonance (MR) sequences to robustly and accurately segment brain lesions. It is based on an augmented multi-sequence Hidden Markov model that includes additional weight variables to account for the relative importance and control the impact of each sequence. The augmented framework has the advantage of allowing 1) the incorporation of expert knowledge on the a priori relevant information content of each sequence and 2) a weighting scheme which is modified adaptively according to the data and the segmentation task under consideration. The model, applied to the detection of multiple sclerosis and stroke lesions shows promising results. ER -
APA
Forbes, F., Doyle, S., Garcia–Lorenzo, D., Barillot, C. & Dojat, M.. (2010). A Weighted Multi-Sequence Markov Model For Brain Lesion Segmentation. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 9:225-232 Available from https://proceedings.mlr.press/v9/forbes10a.html.

Related Material