Computer Aided Solution for Automatic Segmenting and Measurements of Blood Leucocytes Using Static Microscope Images

Abstract

Blood leucocytes segmentation in medical images is viewed as difficult process due to the variability of blood cells concerning their shape and size and the difficulty towards determining location of Blood Leucocytes. Physical analysis of blood tests to recognize leukocytes is tedious, time-consuming and liable to error because of the various morphological components of the cells. Segmentation of medical imagery has been considered as a difficult task because of complexity of images, and also due to the non-availability of leucocytes models which entirely captures the probable shapes in each structures and also incorporate cell overlapping, the expansive variety of the blood cells concerning their shape and size, various elements influencing the outer appearance of the blood leucocytes, and low Static Microscope Image disparity from extra issues outcoming about because of noise. We suggest a strategy towards segmentation of blood leucocytes using static microscope images which is a resultant of three prevailing systems of computer vision fiction: enhancing the image, Support vector machine for segmenting the image, and filtering out non ROI (region of interest) on the basis of Local binary patterns and texture features. Every one of these strategies are modified for blood leucocytes division issue, in this manner the subsequent techniques are very vigorous when compared with its individual segments. Eventually, we assess framework based by compare the outcome and manual division. The findings outcome from this study have shown a new approach that automatically segments the blood leucocytes and identify it from a static microscope images. Initially, the method uses a trainable segmentation procedure and trained support vector machine classifier to accurately identify the position of the ROI. After that, filtering out non ROI have proposed based on histogram analysis to avoid the non ROI and chose the right object. Finally, identify the blood leucocytes type using the texture feature. The performance of the foreseen approach has been tried in appearing differently in relation to the system against manual examination by a gynaecologist utilizing diverse scales. A total of 100 microscope images were used for the comparison, and the results showed that the proposed solution is a viable alternative to the manual segmentation method for accurately determining the ROI. We have evaluated the blood leucocytes identification using the ROI texture (LBP Feature). The identification accuracy in the technique used is about 95.3%., with 100 sensitivity and 91.66% specificity.

Automated Diagnosis of Leukemia: A Comprehensive Review

“…In future work, a combination of two or more segmentation techniques can be made to segment acute leukemia cells. The features selection and dimensional reduction techniques should be applied to achieve greater efficiency in the leukemia classification [90]. The methodology to select suitable and non-redundant features should be proposed that can detect the specific type of Leukemia.…”

Fully automatic model‐based segmentation and classification approach for MRI brain tumor using artificial neural networks

“…The local refinement error among two segments could be evaluated as follows [23][24][25][26][27] : Segmentation which is connected are thought to be steady, since they could have represented to the same picture or case divided at various scales.…”

“…On the off chance that there is no subset relationship, at that point the two areas overlap in a conflicting way. The local refinement error among two segments could be evaluated as follows [23][24][25][26][27] :…”

A Review on Traditional Machine Learning and Deep Learning Models for WBCs Classification in Blood Smear Images

“…Conventional techniques rely on manual analysis of WBCs in blood smear images, a time-consuming, challenging task, and prone to errors [6][7][8][9]. Automatic and CAD systems have a crucial role in clinical diagnosis and appropriate treatment [10][11][12][13]. Therefore, automatic analysis of WBCs in microscopic blood smear images is gaining popularity because it can decrease the workload on hematologists and provide quick, efficient, and accurate results to assist medical experts in the diagnostic process [14].…”