Automated detection of hematological abnormalities through classification of flow cytometric data patterns

Flow Cytometry analyzers have become trusted companions due to their ability to perform fast and accurate analyses of human blood. The aim of these analyses is to determine the possible existence of abnormalities in the blood that have been correlated with serious disease states, such as infectious mononucleosis, leukemia, and various cancers. Though these analyzers provide important feedback, it is always desired to improve the accuracy of the results. This is evidenced by the occurrences of misclassifications reported by some users of these devices. It is advantageous to provide a pattern interpretation framework that is able to provide better classification ability than is currently available. Toward this end, the purpose of this dissertation was to establish a feature extraction and pattern classification framework capable of providing improved accuracy for detecting specific hematological abnormalities in flow cytometric blood data. ^ This involved extracting a unique and powerful set of shift-invariant statistical features from the multi-dimensional flow cytometry data and then using these features as inputs to a pattern classification engine composed of an artificial neural network (ANN). The contribution of this method consisted of developing a descriptor matrix that can be used to reliably assess if a donor’s blood pattern exhibits a clinically abnormal level of variant lymphocytes, which are blood cells that are potentially indicative of disorders such as leukemia and infectious mononucleosis. ^ This study showed that the set of shift-and-rotation-invariant statistical features extracted from the eigensystem of the flow cytometric data pattern performs better than other commonly-used features in this type of disease detection, exhibiting an accuracy of 80.7%, a sensitivity of 72.3%, and a specificity of 89.2%. This performance represents a major improvement for this type of hematological classifier, which has historically been plagued by poor performance, with accuracies as low as 60% in some cases. This research ultimately shows that an improved feature space was developed that can deliver improved performance for the detection of variant lymphocytes in human blood, thus providing significant utility in the realm of suspect flagging algorithms for the detection of blood-related diseases.^

Understanding the Effect of Protein Tyrosine Phosphatase Receptor Type 0 on Mammalian Sensory Development: Behavioral Studies on PTPRO Knockout Mice

Nerve development, which includes axon outgrowth and guidance, is regulated by many protein families, including receptor protein tyrosine phosphatases (RPTP's).Protein tyrosine phosphatase receptor type 0 (PTPRO) is a type III RPTP that is important for axon growth and guidance, as observed in chicks and flies. In order to examine the effects ofPTPRO on mammalian development, standard behavioral tests were used to compare mice lacking the gene for PTPRO (ROKO mice) to wild-type (WT) mice. The ROKO mice showed a significant delay in reacting to a thermal noxious stimulus, hotplate analgesia, when compared to the WT mice suggesting deficient nociceptive function. In a rotarod test for proprioceptive function the ROKO mice exhibited a significant decrease in the amount of time spent on the rotating rod than did the WT mice. Additional proprioception tests were performed including the climb, step reflex, beam, and mesh walk tests. In the climb and step (place) test, the ROKO group had a significantly lower accuracy in performing the tests than did the WT mice. Thus, mice lacking the PTPRO gene showed behavioral deficiencies that reflect impairment in sensory function, specifically for nociception and proprioception.

Effects of Altered Prenatal Sensory Stimulation on Postnatal Contingency Learning in Bobwhite Quail Neonates (Colinus Virginianus)

Preterm infants are exposed to high levels of modified early sensory experience in the Neonatal Intensive Care Unit (NICU). Reports that preterm infants show deficits in contingency detection and learning when compared to full-term infants (Gekoski, Fagen, & Pearlman, 1984; Haley, Weinberg, & Grunau, 2006) suggest that their exposure to atypical amounts or types of sensory stimulation might contribute to deficits in these critical skills. Experimental modifications of sensory experience are severely limited with human fetuses and preterm infants, and previous studies with precocial bird embryos that develop in ovo have proven useful to assess the effects of modified perinatal sensory experience on subsequent perceptual and cognitive development. In the current study, I assessed whether increasing amounts of prenatal auditory or visual stimulation can interfere with quail neonates’ contingency detection and contingency learning in the days following hatching. Results revealed that augmented prenatal visual stimulation prior to hatching does not disrupt the ability of bobwhite chicks to recognize and prefer information learned in a contingent fashion, whereas augmented prenatal auditory stimulation disrupted the ability of chicks to benefit from contingently presented information. These results suggest that specific types of augmented prenatal stimulation that embryos receive during late prenatal period can impair the ability to learn and remember contingently presented information. These results provide testable developmental hypotheses, with the goal of improving the developmental care and management of preterm neonates in the NICU setting.