Disease classification: A probabilistic approach

Abstract

We describe a probabilistic technique for separating two populations whereby analysis is performed on affine-invariant representations of each patient. The method begins by converting each voxel from a high-dimensional diffusion weighted signal to a low-dimensional diffusion tensor representation. Three orthogonal measures that capture different aspects of the local tissue are derived from the tensor representation to form a feature vector. From these feature vectors, we form a probabilistic representation of each patient. This representation is affine invariant, thus obviating the need for registration of the images. We then use a Parzen window classifier to estimate the likelihood of a new patient belonging to either population. To demonstrate the technique, we apply it to the analysis of 22 first-episode schizophrenic patients and 20 normal control subjects. With leave-many-out cross validation, we find a detection rate of 90.91% (10% false positives).

Accelerometry-Based Home Monitoring for Detection of Nocturnal Hypermotor Seizures Based on Novelty Detection

“…Parzen density estimation is commonly used in the context of classification and novelty detection [11]. Rathi et al [16] and Rangayyan and Wu [15] modeled the distributions of two classes based on the Parzen window approach and classify instances based on the highest probability. Tarassenko et al [18,19] and Yeung and Chow [23] use the one-class classification which is the novelty or outlier detection.…”