A Contemporary CNN Based Classifier Approach for Intelligent Diagnostic Systems

Intelligent diagnostic systems significantly enhance the effectiveness and efficiency of cancer detection and management, ultimately leading to better patient outcomes. According to statistics, cancer is the second prime cause of death in males. It's a sluggish-growing ailment that doesn't show symptoms until it's quite evolved. Various investigations on AI (Artificial Intelligence) algorithms analysis have been done in the previous few years over varied medical imaging modalities which includes Computed Tomography, Magnetic Resonance Imaging, and Ultrasound. The use of artificial intelligence to monitor prostate cancer would have a tremendous impact on healthcare. Cancer scientists would have a superior understanding of the ailment and it would be helpful in developing a more precise mechanism for cancer detection as it is the need of the hour, as it has been predicted that there will be over 1.3 million additional cases diagnosed annually around the world. Here an attempt has been made to provide an analysis of the progress being made in the sector of medical image processing. Also, based on the rising interest in CNN (Convolutional Neural Networks) in recent years, we have examined the use of CNN in numerous automatic processing tasks for prostate cancer identification and diagnosis. In this study, a novel deep learning convolutional neural network (CNN) model was employed and its performance was compared against three established CNN models: AlexNet, GoogleNet, and ResNet. It has been found that the use of CNN has increased dramatically, with excellent outputs gained using either new models or pre-conditioned networks for transfer learning. Deep learning-based research surpasses traditional patient prognostic methods with regard to accuracy, according to the survey's findings.