Chromatographic Pattern Classification

• Published in: IEEE transactions on biomedical engineering Vol. 55; no. 6; pp. 1687 - 1696
• Main Authors: Sousa, AntÓnio V., MendonÇa, Ana Maria, Campilho, AurÉlio
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2008; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Background noise; Chromatographic pattern features; chromatographic profiles; Chromatography; Chromatography, Thin Layer - methods; classification; Decision trees; Degenerative diseases; Diagnosis, Computer-Assisted - methods; Filtering; Gaussian noise; Genetics; hierarchical classifier; Humans; Hydrolases - urine; Lysosomal Storage Diseases - diagnosis; Lysosomal Storage Diseases - urine; Noise reduction; Noise robustness; Pattern classification; Pattern Recognition, Automated - methods; Reproducibility of Results; Senior members; Sensitivity and Specificity; Studies; Urinalysis - methods; chromatographic profiles; chromatographic pattern features; classification; hierarchical classifier
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2008.919852

In this paper, we propose and evaluate methodologies for the classification of images from thin-layer chromatography. Each individual sample is characterized by an intensity profile that is further represented into a feature space. The first steps of this process aim at obtaining a robust estimate of the intensity profile by filtering noise, reducing the influence of background changes, and by fitting a mixture of Gaussians. The resulting profiles are represented by a set of appropriate features trying to characterize the state of nature, here spread out over four classes, one for normal subjects and the other three corresponding to lysosomal diseases, which are disorders responsible for severe nerve degeneration. For classification purposes, a novel solution based on a hierarchical structure is proposed. The main conclusion of this paper is that an automatically generated decision tree presents better results than more conventional solutions, being able to deal with the natural imbalance of the data that, as consequence of the rarity of lysosomal disorders, has very few representative cases in the disease classes when compared with the normal population.