Automated Analysis of Flow Cytometry Data for B-Cell Lymphoma

Date

2016-05

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Flow cytometry, a powerful tool for the diagnosis of hematolymphoid malignancies including B-cell lymphomas, is an innovative technique that measures the fluorescence of suspended cells. Traditionally, the method of evaluating the research and clinical study of flow cytometry data is done by the process of manual gating along with a review by pathologists using their accumulated knowledge. The problem with manual processing is that it is labor-intensive, time-consuming, and subject to human error. Although several computerized methods are available for flow cytometry data processing, most of the current automatic techniques have not been fully developed. In this dissertation, based on the discoveries found in my research, a computational model is proposed to detect B-lymphocyte neoplasms using flow cytometry data by building healthy and sick profiles. The technique is based on using a cell-capture rate that is defined to measure the fitness of a test subject using a particular profile. By examining the cell-capture rate of a test case with all profiles, the disease type can be determined. To strengthen the system, a confidence level of diagnosis is defined to assist the physician in making a better decision. This technique is validated by comparing the diagnosis result, given by the proposed algorithm, with the hospital’s information. In addition, this method is also tested by analyzing test cases of minimal residual disease, obtained from a group of patients with fewer B-cell lymphoma cells. When patients exhibits this condition, the difficulty of automated diagnosis is greatly increased. Finally, the validity of the automated system is supported by the strong correlation between the results from the automated system diagnosis and the conventional manual process.

Description

Keywords

Flow Cytometry, Minimal Residual Disease, Computational Model, B-cell lymphoma

Citation

Portions of this document appear in: Shih, Ming-Chih, Shou-Hsuan Stephen Huang, and Chung-Che Jeff Chang. "A multidimensional flow cytometry data classification." In 2009 Ninth IEEE International Conference on Bioinformatics and Bioengineering, pp. 356-359. IEEE, 2009. DOI: doi.ieeecomputersociety.org/10.1109/BIBE.2009.20; and in: Shih, M. C., R. Donohue, L. Zhang, C. C. Chang, S. H. Huang, and Y. Zu. "An automatic diagnosis of several types of lymphoma by flow cytometry data." In LABORATORY INVESTIGATION, vol. 92, pp. 368A-368A. 75 VARICK ST, 9TH FLR, NEW YORK, NY 10013-1917 USA: NATURE PUBLISHING GROUP, 2012; and in: Shih, M. C., R. Donohue, L. Zhang, C. C. Chang, S. H. Huang, and Y. Zu. "An automatic diagnosis of several types of lymphoma by flow cytometry data." In LABORATORY INVESTIGATION, vol. 92, pp. 368A-368A. 75 VARICK ST, 9TH FLR, NEW YORK, NY 10013-1917 USA: NATURE PUBLISHING GROUP, 2012; and in: Shih, Ming-Chih, Shou-Hsuan Stephen Huang, Rachel Donohue, Chung-Che Chang, and Youli Zu. "Automatic B cell lymphoma detection using flow cytometry data." BMC genomics 14, no. 7 (2013): S1. DOI: 10.1186/1471-2164-14-S7-S1; and in: Shih, Ming Chih, Stephen Huang, Shou Hsuan, Ramesh Bhagat, and Youli Zu. "Validation of a computational B-cell lymphoma analysis by flow cytometry data." In The International Society for Computers and Their Applications (ISCA). 2015.