Automated Assessment of Erythrocyte Disorders Using Artificial Neural Network
- 1 August 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21627843,p. 776-780
Abstract
In this paper, we employ artificial neural network (ANN) together with image analysis techniques to automate the assessment of erythrocyte disorders using blood parameters such as red blood cell (RBC) count, hemoglobin (Hgb) level, and mean corpuscular hemoglobin (MCH). The neural network is trained using 800 blood sample images collected from the Prince George-EC, Hospital. The images are captured using a high-resolution digital camera mounted on a microscope. The red, green, and blue values of each image are fed as the input of the neural network. The Hospital RBC, Hgb values of the samples measured using hydrodynamic focused analyzer (CELL-DYN 3200 System) are provided as the target values during training. Several variations of the back propagation-learning algorithm were applied for training. The trained network is tested against 200 blood samples. The output results are compared with those of Hospital laboratory and found to be near identical, most of which are within 5% margin of error, and are much significantly better than those published. The proposed method is simple, fast, accurate, and can be a crucial step in automating laboratory reportingKeywords
This publication has 6 references indexed in Scilit:
- Direct neural network application for automated cell recognitionCytometry Part A, 2003
- Determination of hemoglobin levels in the finger using near infrared spectroscopyClinical and Laboratory Haematology, 2003
- Artificial neural network-aided image analysis system for cell countingCytometry, 1999
- Generalized region growing operator with optimal scanning: application to segmentation of breast cancer imagesJournal of Microscopy, 1997
- Nuclear pattern recognition by two-parameter texture analysisComputer Methods and Programs in Biomedicine, 1996
- Pattern recognition and classification of images of biological macromolecules using artificial neural networksBiophysical Journal, 1994