An Accurate and Cost Effective Approach to Blood Cell Count

Abstract

Medical imaging brings up the methods and technique which enable us to take and analyse images of different disease and human body parts for diagnosing purposes. The old conventional methods used in hospital laboratories to detect and diagnose the problem were very slow and they had greater chances of error in it but medical imaging through different image processing techniques opened new, fast and costeffective ways to detect and recognize different diseases and make it easy to examine and diagnose the actual problem. Now a day's researchers are working on different computer vision applications for health industry. Such as segmentation of kidney from ultrasound images, Cancer Detection Using Pattern Recognition Technique, segmentation of brain images, etc. Fast and cost-effective blood cell counting has major importance in the medical world. The old conventional methods of blood cell counting under the microscope render unreliable and unacceptable results and put an unendurable amount of strain on the Clinical laboratory technicians. Even so there are latest hardware solutions such as the Heska'sHema'true hematology analyzer, but they are widely unavailable and very expensive machines and so the under developed countries like Pakistan are not resourceful to provide such an expensive solution of blood cell counting in every hospital laboratory in the country. As a solution regarding this problem, this research based paper proposed a fast and cost effective software-based alternative method to count accurate blood cells.

Improving reliability of live/dead cell counting through automated image mosaicing

“…For example, Mahmood and co-workers [63] exploit the Hough transform [64] to extract circular objects considered to be the cells. Other commonly used processing techniques involve watershed segmentation [65], image thresholding [66] and morphological operators [67]. Although all of these methods are appealing, they fail to discriminate accurately between cells of different shapes, live and dead cells and small aggregates.…”

Mobile based Automated Complete Blood Count (Auto-CBC) Analysis System from Blood Smeared Image

“…Indeed, it is a laborious task and may lead to human variation error. Instead of implementing the CBC analysis manually, there are few technologies used to count the blood cells in a specimen automatically, such as image-based cell counters [5], flow cytometers [6] and coulter counters [7]. However, these techniques still require expertise to operate it and the equipment for these methods are expensive.…”

Leukocyte subtypes classification by means of image processing

“…In a combination with a small camera this method can become a useful tool for doctors, providing them an instant access to the information about WBCs population at bedside of a patient. There are some studies that show efficient leukocyte identification [3], [4] and segmentation [5], [6] within microscopic images. However, these studies are focused on the leukocyte count without the classification of the leukocytes into subtypes.…”