Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging

Abstract

We describe a new method to automatically discriminate between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls, based on multidimensional classification of hippocampal shape features. This approach uses spherical harmonics (SPHARM) coefficients to model the shape of the hippocampi, which are segmented from magnetic resonance images (MRI) using a fully automatic method that we previously developed. SPHARM coefficients are used as features in a classification procedure based on support vector machines (SVM). The most relevant features for classification are selected using a bagging strategy. We evaluate the accuracy of our method in a group of 23 patients with AD (10 males, 13 females, age ±standard-deviation (SD)=73±6 years, mini-mental score (MMS)=24.4±2.8), 23 patients with amnestic MCI (10 males, 13 females, age±SD=74±8 years, MMS=27.3±1.4) and 25 elderly healthy controls (13 males,12 females, age±SD=64±8 years), using leave-one-out cross-validation. For AD vs controls, we obtain a correct classification rate of 94%, a sensitivity of 96%, and a specificity of 92%. For MCI vs controls, we obtain a classification rate of 83%, a sensitivity of 83%, and a specificity of 84%. This accuracy is superior to that of hippocampal volumetry and is comparable to recently published SVM-based whole-brain classification methods, which relied on

Simultaneous segmentation and grading of anatomical structures for patient's classification: Application to Alzheimer's disease

“…The SEN, SPE, PPV and NPV obtained by SNIPE are competitive compared to the ten methods compared in Cuingnet et al (2010) involving voxel-based morphometry (VBM) (Ashburner and Friston, 2000), cortical thickness (Fischl et al, 1999), HC volume (Chupin et al, 2009b) and HC shape (Gerardin et al, 2009). In that comparison paper, the best VBM-based approach obtained 89% accuracy; the best method based on cortical thickness obtained 85% accuracy, the best approach using HC volume 74% accuracy and the method using HC shape 77% accuracy.…”

“…This limited capability to classify AD patients using the HC volume only, may be due to a simplification of the complex atrophy patterns to a volume -a simple scalar. Recently, several shape analysis methods have been proposed (Csernansky et al, 2005;Gerardin et al, 2009;Gutman et al, 2009) to capture detailed HC structural modifications in order to obtain a more accurate classification. At 77% in the comparison proposed by Cuingnet et al (2010), the approach proposed in Gerardin et al (2009) yields slightly better classification than a volumetric approach.…”

“…Recently, several shape analysis methods have been proposed (Csernansky et al, 2005;Gerardin et al, 2009;Gutman et al, 2009) to capture detailed HC structural modifications in order to obtain a more accurate classification. At 77% in the comparison proposed by Cuingnet et al (2010), the approach proposed in Gerardin et al (2009) yields slightly better classification than a volumetric approach. Therefore, development of new methods capable of estimating subtle anatomical modifications of HC appears to be a critical point to obtain better classification rate.…”

Towards earlier detection of Alzheimer's disease using magnetic resonance images

“…Methods have been proposed that use the hippocampal volume [26,27] or its shape [28] as features in the classification of MCI. The volumes of the entorhinal cortex [29] and the amygdala [30] have also been considered for the same purpose.…”

“…Most MRI studies on prodromal stages of AD focus on the large-scale analysis of gray matter structures. In particular, volume and shape changes at the level of the cortex [29], the hippocampi [27,28] and the amygdalae [30], or the cerebrospinal fluid (CSF) cavities such as the ventricles [103] have been widely explored as imaging markers of AD. However, recent studies have shown that the white matter is also affected at the early stages of the disease [104,105].…”