Detecting Cancer through Analysis of Histopathological Images

Prostate cancer stands out as one of the most prevalent cancers, ranking second in cancer-related male fatalities on a global scale. Early diagnosis and effective treatment are pivotal in halting the proliferation and dissemination of cancer cells within the body. The gold standard for prostate cancer detection remains histopathological image diagnosis, distinguished by its unique visual attributes. Nonetheless, the interpretation of these images necessitates a high level of expertise and is often time-consuming. One promising field to expedite this diagnostic process lies in the utilization of Artificial Intelligence (AI), particularly through the utilization of Computer-Aided Diagnosis (CAD) systems. This study is dedicated to the categorization of histopathological images into “normal” and “prostate cancer-affected” categories, utilizing the extensive PANDAS dataset. In this study, Convolutional Neural Networks (CNN) are employed to extract relevant features, and three distinct machine learning (ML) models-Support Vector Machine (SVM), k-Nearest Neighbors (KNN), and Naïve Bayes (NB)-are applied. The experimental findings of this study highlight the superior performance of the SVM model, which achieves an impressive accuracy rate of 98%, while also exhibiting minimal false negative and positive rates of 1.98% and 2.01%, respectively. This research underscores the potential of AI technology in prostate cancer identification.