Semi-supervised pattern classification of medical images: Application to mild cognitive impairment (MCI)

摘要: Many progressive disorders are characterized by unclear or transient diagnoses for specific subgroups of patients. Commonly used supervised pattern recognition methodology may not be the most suitable approach to deriving image-based biomarkers in such cases, as it relies on availability categorically labeled data (e.g., patients and controls). In this paper, we explore potential semi-supervised classification provide absence precise diagnostic information some individuals. We employ support vector machines (SVM) apply them problem classifying MR brain images with uncertain diagnoses. examine patterns serial scans ADNI participants mild cognitive impairment (MCI), propose that sufficient follow-up evaluations individuals MCI, strategy is potentially more appropriate than fully-supervised paradigm employed up date.