An Efficient WBC Cancer Cells Prediction Using Dense Net Algorithm

The critical factor causing cancer disease is aberrant cells that prevent normal blood cells from growing. There are many types of cancer diseases. This study proposes automating the diagnosis of this condition. This study suggests the use of tiny blood pictures. There were 62 preparations and 38 tests. Segmentation and clustering were performed using YCbCr, Gaussian Distribution, Otsu Adaptive, and K-Means. Convolutional Neural Networks were used to classify GLCM features. This splits these disorders into two groups based on similar symptoms, making diagnosis challenging. The doctor had a choice between two possibilities. Each technique calculates the characteristics of one of the two sickness groups. The Random Forest classifier was used to conclude. The proposed method intends to increase system learning, reduce misdiagnosis, and detect white blood cell malignancy early. This study suggests using tiny white blood cell pictures to detect leukemia in patients. The cell shape classifier was investigated using MATLAB and LabVIEW in this study. The proposed method intends to increase system learning, reduce misdiagnosis, and detect white blood cell malignancy early. This study suggests using tiny white blood cell pictures to detect leukemia in patients. This research’s primary application is using machine learning prediction systems in hospitals.