A combined neural network mechanism for categorizing the normal and cancer cells

Abstract

The dangerous form of acute lymphocytic leukemia damages the bone marrow tissue and white blood cells. Unformed white blood cells multiply and exchange healthy cells in the bone marrow. Everything spreads fast and, if not noticed, can be dangerous in some months. As a result, computer assisted diagnosis of acute lymphocytic leukemia has the possible to protect several lives, but it needs a high-precision categorization of malignant cells, that is difficult due to the graphical similarity of malignant and normal cells. Though deep convolutional neural networks and the classic machine learning algorithms have exposed excellent results in classifying blood cell images, they have not been able to make effective use of the long-term correlation between some important image attributes and image labeling. This study introduced Long short-term memory (LSTM) to solve this difficulty. This study actually combines VGG16 neural networks and LSTM, which provide the VGG16-LSTM framework, which improves the recognizing of image content and learns the structural features of images, as well as initiate big data training in clinical image processing. The transfer learning approach was used to transfer pre-trained weight parameters to the VGG16 area in the ImageNet database, and the custom loss function was used to train and integrate the network quickly and accurately with the weight parameters. Experimental findings reveal that the suggested network approach is more relevant and effective in categorizing cancer cell images than other existing methods.