Pattern Recognition of Acute Lymphoblastic Leukemia (ALL) Using Computational Deep Learning

Abstract

Leukemia is a cancer of blood-producing cells, including the bone marrow. Abnormal white blood cells travel through blood vessels and multiply rapidly. Healthy cells in the body become a minority, and the imbalance increases the chances of infection in the body. Leukemia or blood cancer is the most common cancer in children ages 2 - 14. Most leukemia in children is treated. Acute lymphocytic leukemia (ALL) is a type of cancer in the blood and bone marrow. It progresses rapidly when immature white blood cells are formed instead of mature ones. Treatments for acute lymphocytic leukemia include drugs and blood transfusions directly into veins, chemotherapy, and all transplantation, which involve transferring organs or tissues within the body or from one person to another. In this paper, Pattern Recognition of Acute Lymphoblastic Leukemia has been proposed using Computational Deep Learning. Pattern recognition technology uses mathematical algorithms to identify patterns in large datasets of data. Analyzing the data, the algorithms can identify patterns indicative of certain states or conditions. In the case of ALL, the algorithm would look for patterns in white blood cell count data that indicate the presence of ALL. These patterns may include changes in the number of white blood cells over time, changes in the composition of the white blood cells, or changes in the levels of certain proteins or gene expressions associated with ALL. The proposed ALLDM model achieved 81.53% (DDS) and 87.92% (SDS) of chemotherapy management, 79.16% (DDS) and 94.31% (SDS) of Stem Cell Transplantation Management, 63.77% (DDS) and 87.37% (SDS) of Radiation therapy Management and 88.92% (DDS) and 85.86% (SDS) of Targeted therapy drugs management.

Ähnliche Arbeiten