TY - GEN

T1 - Local appearance features for robust MRI brain structure segmentation across scanning protocols

AU - Achterberg, H.C.

AU - Poot, Dirk H. J.

AU - van der Lijn, Fedde

AU - Vernooij, Meike W.

AU - Ikram, M. Arfan

AU - Niessen, Wiro J.

AU - de Bruijne, Marleen

PY - 2013

Y1 - 2013

N2 - Segmentation of brain structures in magnetic resonance images is an important task in neuro image analysis. Several papers on this topic have shown the benefit of supervised classification based on local appearance features, often combined with atlas-based approaches. These methods require a representative annotated training set and therefore often do not perform well if the target image is acquired on a different scanner or with a different acquisition protocol than the training images. Assuming that the appearance of the brain is determined by the underlying brain tissue distribution and that brain tissue classification can be performed robustly for images obtained with different protocols, we propose to derive appearance features from brain-tissue density maps instead of directly from the MR images. We evaluated this approach on hippocampus segmentation in two sets of images acquired with substantially different imaging protocols and on different scanners. While a combination of conventional appearance features trained on data from a different scanner with multiatlas segmentation performed poorly with an average Dice overlap of 0.698, the local appearance model based on the new acquisition-independent features significantly improved (0.783) over atlas-based segmentation alone (0.728).

AB - Segmentation of brain structures in magnetic resonance images is an important task in neuro image analysis. Several papers on this topic have shown the benefit of supervised classification based on local appearance features, often combined with atlas-based approaches. These methods require a representative annotated training set and therefore often do not perform well if the target image is acquired on a different scanner or with a different acquisition protocol than the training images. Assuming that the appearance of the brain is determined by the underlying brain tissue distribution and that brain tissue classification can be performed robustly for images obtained with different protocols, we propose to derive appearance features from brain-tissue density maps instead of directly from the MR images. We evaluated this approach on hippocampus segmentation in two sets of images acquired with substantially different imaging protocols and on different scanners. While a combination of conventional appearance features trained on data from a different scanner with multiatlas segmentation performed poorly with an average Dice overlap of 0.698, the local appearance model based on the new acquisition-independent features significantly improved (0.783) over atlas-based segmentation alone (0.728).

UR - http://www.scopus.com/inward/record.url?scp=84878296192&partnerID=8YFLogxK

U2 - 10.1117/12.2006038

DO - 10.1117/12.2006038

M3 - Article in proceedings

AN - SCOPUS:84878296192

SN - 9780819494436

T3 - Progress in Biomedical Optics and Imaging

BT - Medical Imaging 2013

A2 - Ourselin, Sebastien

A2 - Haynor, David R.

PB - SPIE - International Society for Optical Engineering

Y2 - 10 February 2013 through 12 February 2013

ER -