Two fully automatic restoration-segmentation algorithms are proposed for the processing of biased magnetic resonance images. A first approach is based on an expectation-maximization procedure, where the initial conditions for the class distribution parameters and the number of classes are obtained, without any a priori knowledge, from a mode-based analysis of the biased image. A second approach relies completely on the mode-based analysis to update the number of classes and distribution parameters in every iteration. Both methods give accurate results even for overlapping distributions distorted by a gain factor of up to 40%. The possibility of having automatic initial conditions provides an important enhancement to previously reported methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Automatic correction of bias field in magnetic resonance images


    Beteiligte:
    Garza-Jinich, M. (Autor:in) / Yanez, O. (Autor:in) / Medina, V. (Autor:in) / Meer, P. (Autor:in)


    Erscheinungsdatum :

    01.01.1999


    Format / Umfang :

    123482 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Automatic Correction of Bias Field in Magnetic Resonance Images

    Garza-Jinich, M. / Medina, V. / Meer, P. et al. | British Library Conference Proceedings | 1999


    Performance Evaluation of Parametric Bias Field Correction

    Zagorodnov, V. / Hansen, M. F. | British Library Conference Proceedings | 2005


    A Correction Algorithm for Automatic Pavement Detection Data Bias

    Li, Li / Yu, Jia-Hui / Yang, Kun et al. | TIBKAT | 2021


    Performance evaluation of parametric bias field correction

    Zagorodnov, V. / Hansen, M.F. | IEEE | 2005


    Mosaic Image Segmentation with Bias Field Correction

    Yang, G. Z. / Myerson, S. / Chabat, F. C. et al. | British Library Conference Proceedings | 1999