Trimmed-likelihood estimation for focal lesions and tissue segmentation in multisequence MRI for multiple sclerosis.

Daniel García-Lorenzo (1, 2) , Sylvain Prima (1) , Douglas L. Arnold (2) , Louis D. Collins (2) , Christian Barillot (1)

1 VisAGeS - Vision, Action et Gestion d'informations en Santé
2 MNI - McConnell Brain Imaging Centre

We present a new automatic method for segmentation of multiple sclerosis (MS) lesions in magnetic resonance images. The method performs tissue classification using a model of intensities of the normal appearing brain tissues. In order to estimate the model, a trimmed likelihood estimator is initialized with a hierarchical random approach in order to be robust to MS lesions and other outliers present in real images. The algorithm is first evaluated with simulated images to assess the importance of the robust estimator in presence of outliers. The method is then validated using clinical data in which MS lesions were delineated manually by several experts. Our method obtains an average Dice similarity coefficient (DSC) of 0.65, which is close to the average DSC obtained by raters (0.66).

Mots clés: Segmentation; Multiple Sclerosis; MRI; EM; Gaussian Mixture Model

Domaines: Imagerie médicale; Ingénierie biomédicale

Daniel García-Lorenzo, Sylvain Prima, Douglas L. Arnold, Louis D. Collins, Christian Barillot. Trimmed-likelihood estimation for focal lesions and tissue segmentation in multisequence MRI for multiple sclerosis.. IEEE Transactions on Medical Imaging, 2011, 30 (8), pp.1455-67. ⟨10.1109/TMI.2011.2114671⟩. ⟨inserm-00590724⟩