Search

Leukemia is a blood disease . The pace of cure be dependent upon the kind of Leukemia just as the period of unfortunate casualties. Intense lymphocytic Leukemia, Acute myeloid Leukemia and typical instances of Microscopic pictures of blood marrow spreads at first separated the core by evacuating foundation utilizing division. At that point the impacted cores' shading, GLCM and geometric highlights are separated lastly these cells are named carcinogenic or nonmalignant cell and its subtypes utilizing bolster vector machine (SVM) and KNN classifier. The precision of the classifier assessed up to 94.3%. The trial results demonstrates that proposed calculation could achieve a sufficient exhibition for the analysis of AML, ALL and their sub-types.

Social media are nowadays used by people to talk about any kind of topic, either private or not, and among others health problems. Concerning health, on social media one can find large communities discussing about chronic diseases. Here people look for advise, information, support, and so on. In this paper we take into consideration the Italian Twitter community interested in diabetes, a chronic blood disease. Our aim is to understand which are the main conversation topics in this community. Thus, we analyzed about 9K tweets written in Italian that contained the world {\em diabete} (diabetes) and performed both a hashtag analysis and a lexicon analysis, the latter by means of ad-hoc dictionaries. Results show that this is a calm community interested into several distinct topics (e.g., disease related information gathering, recipes for diabetes patients, fundraising campaigns), none of which is really predominant over the others.

Sickle cell disease (SCD) is the most popular inherited blood disease, that red blood cells change its shape form circular shape to sickle shape and loses its main job which carries oxygen throughout the body. The watershed segmentation method has become highly developed for automated analysis of overlapping red blood cell microscopic images. The aim of this work is to suppress over segmentation problem which is a major drawback of the watershed algorithm. The experimental results showed that, watershed is most effective when done on filtered image using non local means denoising method. The effectiveness of the proposed method is validated by analyzing the image segmentation quality measures. The proposed method provides higher performance in term of accuracy, sensitivity and specificity factors.

In healthcare systems, there is huge medical data collected from many medical tests which conducted in many domains. Much research has been done to generate knowledge from medical data by using data mining techniques. However, there still needs to extract hidden information in the medical data, which can help in detecting diseases in the early stage or even before happening. In this study, we apply three data mining classifiers; Decision Tree, Rule Induction, and Naive Bayes, on a test blood dataset which has been collected from Europe Gaza Hospital, Gaza Strip. The classifiers utilize the CBC characteristics to predict information about possible blood diseases in early stage, which may enhance the curing ability. Three experiments are conducted on the test blood dataset, which contains three types of blood diseases; Hematology Adult, Hematology Children and Tumor. The results show that Naive Bayes classifier has the ability to predict the Tumor of blood disease better than the other two classifiers with accuracy of 56%, Rule induction classifier gives better result in predicting Hematology (Adult, Children) with accuracy of (57%–67%) respectively, while Decision Tree has the Lowest accuracy rate for detecting the three types of diseases in our dataset.

Microscopic analysis of images in the health care at the cellular level is one of the important methods for analysis and final diagnosis. In the diagnosis of blood diseases, although high technology systems provide very important information, for a definitive diagnosis microscopic smear examinations are needed. Microscopic examination is a time-consuming task for doctors. Therefore, in this study a basic system has been developed that may speed up the eye examination. In future, further development of this system may be an alternative to visual examination. From the basic blood cells (leukocyte, erythrocyte, platelet), we only focused on the locations of white blood cells in the image. In the development process of this system real blood smear images has been used. In this study iterative algorithms are not used instead of this, logical and morphological processes have been used. This allows faster operation of the system.