Joint Reconstruction of Multi-contrast MR Images for Multiple Sclerosis Lesion Segmentation
Dokumenttyp:
Konferenzbeitrag
Autor(en):
Gómez, PA.; Sperl, JI.; Sprenger, T.; Metzler-Baddeley, C.; Jones, DK.; Saemann, P.; Czisch, M.; Menzel, MI.; Menze, B.
Abstract:
A joint reconstruction framework for multi-contrast MR im- ages is presented and evaluated. The evaluation takes place in function of quality criteria based on reconstruction results and performance in the automatic segmentation of Multiple Sclerosis (MS) lesions. We show that joint reconstruction can effectively recover artificially corrupted images and is robust to noise.