Recent Advances in Analytical Techniques

Author(s): Hafeez Ullah*, Munir Akhtar and Muhammad Ramzan Khawar

DOI: 10.2174/9789815036930122050005

Qualitative and Quantitative Investigation of Bio Tissues using Microscopy and Data Mining

Pp: 93-158 (66)

Buy Chapters
  • * (Excluding Mailing and Handling)

Recent Advances in Analytical Techniques

Volume: 5

Qualitative and Quantitative Investigation of Bio Tissues using Microscopy and Data Mining

Author(s): Hafeez Ullah*, Munir Akhtar and Muhammad Ramzan Khawar

Pp: 93-158 (66)

DOI: 10.2174/9789815036930122050005

* (Excluding Mailing and Handling)

Abstract

The effects of glucose and salt on white blood cells, red blood cells, and
platelets (PLTs) in the blood of a leukemic patient by using a white light microscope
have been investigated for different concentrations (0 mM to 500 mM) of glucose and
salt. It has been revealed that the shape of erythrocytes, leukocytes, and platelets
changes and forms aggregates. Increasing the concentration of sodium chloride causes
an increase in the rouleaux formation and aggregation of platelets. The comparison of
CBC reports of these samples with and without analytes shows that total leukocyte
count (TLC) decreases gradually towards normal ranges of leukocytes, which is
favorable in the treatment of leukemia; at the same time, decreased level of hemoglobin
HGB, mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin
concentration (MCHC) and increased level of red blood cell (RBCs) causes a reduction
in the oxygen supply, which is in favor of cancer growth and anemia.

In the second set of work, a computer-aided system was planned for automatic
classification of ultrasound kidney diseases and ultrasound liver (i.e., cirrhosis). Two
types of images were considered normal and chronic. By using the data mining
technique, the statistical features were extracted to differentiate between normal and
abnormal ultrasonic kidney images. By using feature extraction software (FES), a set of
statistical features were extracted from the region of interest of each image at different
frame rates. The data sets which were obtained using FES at different frame rates were
then classified by using Weka. These extracted feature results were classified by using
Weka and a 96.5% correct classification rate was obtained. The difference between the
values of these features was useful to identify between normal and abnormal images.


Keywords: Abnormal image, Artificial neural networks, Complete blood count, Data mining, Erythrocytes, Feature extraction, Hyperglycaemia, Hypoglycaemia, Hypotonic solutions, Liver cirrhosis, Mean corpuscular hemoglobin, Mean corpuscular hemoglobin concentration, Red blood cell, Texture analysis, Total leukocyte count, Ultrasonic kidney, Ultrasound, Ultrasound images, White blood cell, White light microscopy, Whole blood.

Related Journals

Related Books