Leukemia detection system using convolutional neural networks by means of microscopic pictures

All over the world, there are a significant number of patients suffering every year from blood cancer. Most of the people are unaware of the risk involved in such a disease. A majority of these diseases are dangerous and may cause death. The patient who have been diagnosed with such a disease, feels very afraid. The patient may feel that the disease is very uncontrolled. Such diseases are very uncommon, and the patient may get very less assistance and information available about this disease. This symptom is called as acute lymphocytic leukemia (ALL) in medical science. In such a kind of cancer, white blood cells are mostly affected. In case of children, this disease is mainly detected i.e. children are more prone to this disease. If the disease is diagnosed in the early stage, the chances of recovery are maximum. Hence, there should be an accurate and guaranteed mechanism available to detect such type of blood cancers in the patients. This work proposes a system to distinguish the three different types of ALL using a convolutional neural network (CNN) by means of microscopic pictures of peripheral blood smears (PBS) and obtain accuracy levels that surpass those of practicing physicians