- Abstract viewed - 101 times
- 12103-01 downloaded - 64 times
Affiliations
D. M.U. Sabino
nstituto de Física de Sao Carlos
L. F. Costa
Instituto de Física de Sao Carlos
S. L.R. Martins
Centro de Medicina Diagnóstica Fleury
R. T. Calado
Centro de Terapia Celular e Departamento de Clínica Médica - FMRP - USP
M. A. Zago
Centro de Terapia Celular e Departamento de Clínica Médica - FMRP - USP
How to Cite
Automatic leukemia diagnosis
Vol 12 No 1 (2003)
Published: Dec 1, 2003
Abstract
Despite the great demand for blood smear analysis in Brazil and worldwide, relatively few efforts have been directed to the automation of this important problem. This paper presents a prototype of a semi-automatic leukemia diagnosis program. emphasizing basic stops in pattern recognition as segmentation, filtering, and feature extraction. A supervised learning process segments blood smear images into four regions of interest: nucleus, cytoplasm, erythrocytes and plasma according to their color. Then, the measurements are performed, both general such as perimeter, area, factor for, circularity as well as innovative measures as curvature, skeletons, and multiscale fractal dimensión, which can provide more objective subsidy for diagnosis.