Abnormal Red Blood Cells Detection Using Adaptive Neuro-fuzzy System

Red blood cells features like size, shape, and volume are important factors in diagnosingrelated blood disorders like iron deficiency and anemia. This paper proposes a method todetect abnormality in red blood cells using cell microscopic images. Adaptive localthresholding and bounding box methods are used to extract inner and outer diameters of redcells. An adaptive network-based fuzzy inference system (ANFIS) is used to classify bloodsamples to normal and abnormal. Accuracy of the proposed method and area under ROCcurve are 96.6% and 0.9950 respectively.

Keywords:

Abnormal Red blood cells , anemia , microscopic images , adaptive local thresholding , adaptive neuro-fuzzy system