Metamyelocyte Nucleus Classification Using a Set of Morphologic Templates

Abstract

Laboratory tests and clinical analysis is a must to confirm or reject some medical diagnosis. Common analytical fields of knowledge are: Hematology, Clinical biochemistry, Urology, Microbiology among others. This work is for the clinical field of Hematology where detection of immature leukocytes on peripheral blood sample is part of a clinical test of relevance for detection of certain types of cancer. Hematologists distinguish metamyelocytes by their characteristic kidney shape of its nucleus. A novel approach for metamyelocyte classification uses a set of morphological templates. By transforming a pixel based contour to a contour region, morphological templates, the classification becomes a matter of sequence searching on a symbolic string. Using a ten image set for testing, the results are 100% correct. This is very promising, but further extensive set of images could lead to adding and/or modifying morphological templates.