DISEASE CLASSIFICATION AND PREDICTION VIA SEMI-SUPERVISED DIMENSIONALITY REDUCTION

Abstract

We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalism of constrained matrix decomposition of [1] to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosed with Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.

Keywords: Alzheimer’s disease; Basis Learning; Matrix factorization; Mild Cognitive Impairment (MCI); Optimization; Semi-supervised Learning.

Fig. 1

Two examples of learned basis vectors shown in different sagittal cuts. The red color indicates one and blue (transparent) indicates zero.

Fig. 2

For different number of labeled samples, this graph compares different measures (AUC and accuracy) for Supervised Features (SF) and Semi-Supervised Features fed into a supervised classifier (SC) and a semi-supervised classifier (SSC). SSF(lap) indicates γ_I > 0 while SSF denotes γ_I = 0: (a) represents AD-CN accuracy; (b) indicates Area Under Curve (AUC) for the MCI subjects (converters vs non-converters).