Detection of Sickle Cell Anemia Through Contour Evidence Extraction and Estimation

Diagnosis of sickle cell anemia by manual visual inspection through microscope is time consuming and causes human errors. Observational errors occur mostly due to overlapping of cells in blood smear image. Here, an automatic segmentation approach is introduced which isolates sickle cells from all other cells within a blood sample. The proposed system is an approach to find the elliptically shaped sickle cells through geometric feature extraction and contour based segmentation to isolate sickle cells. This technique is a method of isolating sickle cells from other cells within blood sample using cell morphology. A combined approach of extraction of seed points, contour extraction and estimation of contours is used for separation of sickle cells from red blood cells. The methods used for the extraction of seed points are by Ultimate Erosion for Convex Sets and Fast Radial Symmetry transform. The contour evidence is extracted by associating edges of the cells to the seed points. The overlapping and clustered cells in image are identified using ellipse fitting method for contour estimation. Using the seed points and the contour extraction, the edges of the cells are estimated. The lines joining the shape of cells are drawn through estimation of shape of contour. This eliminates cells other than elliptical shaped cells. The proposed system can successfully isolate sickle cells from healthy blood cells within the blood smear image. This automated system has a better accuracy and faster computation speed compared to the existing methods for the detection of sickle cells. This identification methodology helps the health professionals for faster diagnosis.

RBC Classification in Blood Smear Image using Neural Network

Biomedical image processing becomes an emerging field due to automation in the field of medical science with the help of image processing techniques. In medical science it is very much essential to diagnosis a disease accurately and efficiently. Most of the disease which deals with the blood test report for diagnosis of the disease. This paper proposed a computer vision based method which extract the Red Blood Cells (RBC) from a blood smear image and classify it whether normal or abnormal. Then it will count the normal RBC as well as abnormal RBC. This method works in two parts, one is segmentation of blood cell and other is classification and counting of segmented blood cells using neural network. The Neural network trained and classified using shape and moment invariant features because this features are invariant to translation, scaling and rotation. The proposed method performs well and gives about 90 percent of correct result.