Graph of hippocampal subfields grading for Alzheimer's disease prediction

Kilian Hett (1, 2) , Vinh-Thong Ta (3) , José V Manjón (4) , Pierrick Coupé (2)

1 CNRS - Centre National de la Recherche Scientifique
2 LaBRI - Laboratoire Bordelais de Recherche en Informatique
3 Bordeaux INP - Institut Polytechnique de Bordeaux
4 UPV - Universitat Politècnica de València = Universitad Politecnica de Valencia = Polytechnic University of Valencia

Numerous methods have been proposed to capture early hippocampus alterations caused by Alzheimer's disease. Among them, patch-based grading approach showed its capability to capture subtle structural alterations. This framework applied on hippocampus obtains state-of-the-art results for AD detection but is limited for its prediction compared to the same approaches based on whole-brain analysis. We assume that this limitation could come from the fact that hippocam-pus is a complex structure divided into different subfields. Indeed, it has been shown that AD does not equally impact hippocampal subfields. In this work, we propose a graph-based representation of the hippocampal subfields alterations based on patch-based grading feature. The strength of this approach comes from better modeling of the interrelated alterations through the different hippocampal subfields. Thus, we show that our novel method obtains similar results than state-of-the-art approaches based on whole-brain analysis with improving by 4 percent points of accuracy patch-based grading methods based on hippocampus.

Mots clés: Alzheimer's disease classification; Graph-based method; Hippocampal subfields; Mild Cognitive Impairment; Patch-based grading

Domaines: Imagerie médicale; Neurosciences; Machine Learning [stat.ML]

Kilian Hett, Vinh-Thong Ta, José V Manjón, Pierrick Coupé. Graph of hippocampal subfields grading for Alzheimer's disease prediction. Machine Learning in Medical Imaging (MICCAI), Sep 2018, Granada, Spain. ⟨hal-01859257⟩