Blood Cells Classification for Identification of Acute Lymphoblastic Leukemia on Microscopic Images Using Image Processing

Author(s):  
Shelly Oktia Heriawati ◽  
Tri Harsono ◽  
Mochamad Mobed Bachtiar ◽  
Yetti Hernaningsih
Author(s):  
Ika Candradewi ◽  
Reno Ghaffur Bagasjvara

One of the diagnosis procedures for acute lymphoblastic leukemia is screening for blood cells by expert operator using microscope. This process is relatively long and will slow healing process of this disease which need fast treatment. Another way to screen this disease is by using digital image processing technique in microscopic image of blood smears to detect lymphoblast cells and types of white blood cells. One of essential step in digital image processing is segmentation because this process influences the subsequent process of detecting and classifying Acute Lymphoblastic Leukemia disease. This research performed segmentation of white blood cells using moving k-means algorithm. Some process are done to remove noise such as red blood cells and reduce detection errors such as white blood cells and/or lymphoblastic cell  that’s appear overlap. Postprocessing are performed to improve segmentation quality and to separate connected white blood cell. The dataset in this study has been validated with expert clinical pathologists from Sardjito Regional General Hospital, Yogyakarta, Indonesia. This research produces systems performance with results in sensitivity of 85.6%, precision 82.3%, Fscore of 83,9% and accuracy of 72.3%. Based on the results of the testing process with a much larger number of datasets on the side of the variations level of cell segmentation difficulties both in terms of illumination and overlapping cell, the method proposed in this study was able to detect or segment overlapping white blood cells better.


2017 ◽  
Vol 2017 ◽  
pp. 1-3 ◽  
Author(s):  
Khalid Mahmood ◽  
Muhammad Ubaid ◽  
Syeda Taliya Rizvi

Acute lymphoblastic leukemia is characterized by unchecked proliferation of malignant lymphoblasts which replaces the normal bone marrow culminating in anemia due to red blood cells inadequacy as well as in easy bruising/bleeding secondary to insufficient platelets production. Even the white blood cells which are produced excessively are immature and abnormal. ALL is the most common hematological malignancy in children. Most commonly, patients present with lymphadenopathy, recurrent infections, bleeding, fatigue, and bone pains. Bone pains, often particularly involving long bones, occur in about 21–38% of cases and are due to overcrowding of bone marrow with malignant cells. Vast majority of children with ALL have thrombocytopenia and/or anemia with a normal or mildly elevated white blood cells count with the presence of lymphoblasts on peripheral smear. About 50% of children present with bleeding while about 75% of patients have platelet count 100,000/microL. Visceromegaly is not uncommon but osteolytic lesions and hypercalcemia are rather uncommon. We present a 22-year-old gentleman with generalized fatigue and bone pains without visceromegaly. There was severe hypercalcemia with normal parathyroid levels but multiple osteolytic lesions. Peripheral smear showed anemia without blasts, whereas a bone marrow biopsy revealed > 30% blasts with interspersed CD 10 positive cells.


Sign in / Sign up

Export Citation Format

Share Document