Cancer Blood Disorder Detection Using Deep Convolutional Neural Networks: A Comprehensive Revi

One of the main health issues affecting people of all ages is cancer blood disorder. This paper's primary goal is to predict Cancer blood disorder in the early stage. This paved a way to propose a comparative study with previous studies based on Deep Convolutional Neural Networks. Furthermore, pre-processing techniques are used to predict these types of issues. In contrast to current DCNN models, several sophisticated models have recently been proposed that offer state-of-the-art performance for various computer vision and biomedical image analysis problems. In this work, we used these Advanced DCNN algorithms to solve issues related to cancer blood disorder that are assessed using several publically accessible microscopic blood image datasets. The outcomes show better performance for tasks, including classification, segmentation, and prediction, when compared to current machine learning and DCNN-based methods. Machine learning methods including Support Vector Machine, Naïve Bayes, Logistic Regression, K Mean Clustering Algorithm, and Decision Tree techniques are compared with the suggested methodology.