1. Diagnosis of Diabetes Mellitus by Extraction of Morphological Features of Red Blood Cells Using an Artificial Neural Network
- Author
-
Vinupritha Palanisamy and Anburajan Mariamichael
- Subjects
Adult ,Male ,Pathology ,medicine.medical_specialty ,Erythrocytes ,Endocrinology, Diabetes and Metabolism ,medicine.medical_treatment ,02 engineering and technology ,010402 general chemistry ,Sensitivity and Specificity ,01 natural sciences ,Endocrinology ,Diabetes mellitus ,Diabetes Mellitus ,Image Processing, Computer-Assisted ,Internal Medicine ,medicine ,Humans ,Artificial neural network ,business.industry ,Insulin ,Metabolic disorder ,Significant difference ,General Medicine ,Middle Aged ,021001 nanoscience & nanotechnology ,medicine.disease ,0104 chemical sciences ,medicine.anatomical_structure ,Blood smear ,Hyperglycemias ,Female ,Neural Networks, Computer ,0210 nano-technology ,Pancreas ,business - Abstract
Background and Aim: Diabetes mellitus is a metabolic disorder characterized by varying hyperglycemias either due to insufficient secretion of insulin by the pancreas or improper utilization of glucose. The study was aimed to investigate the association of morphological features of erythrocytes among normal and diabetic subjects and its gender-based changes and thereby to develop a computer aided tool to diagnose diabetes using features extracted from RBC. Materials and Methods: The study involved 138 normal and 144 diabetic subjects. The blood was drawn from the subjects and the blood smear prepared was digitized using Zeiss fluorescent microscope. The digitized images were pre-processed and texture segmentation was performed to extract the various morphological features. The Pearson correlation test was performed and subsequently, classification of subjects as normal and diabetes was carried out by a neural network classifier based on the features that demonstrated significance at the level of P
- Published
- 2016
- Full Text
- View/download PDF