Improving Lung and Colon Cancer Detection using Ensemble Method Approach

Cancer is recognised to represent an extremely high risk of mortality, despite enormous developments having been made in science and medicine. Characterized by widespread metastases, malignant cells spread rapidly and evade drugs, making it a fatal disease with little treatment success. Cancer cells have a heterogeneous nature that makes them resistant to chemotherapy and other forms of radiation. Across the globe, cancer stands to be the second most leading cause of death. Among the many types, lung and colon cancer are the most common and have the highest mortality rate. Early and accurate detection of tumor cells in lung and colon cancer patients can help the medical industry increase patient survival statistics. This study focuses on improving the current state of technology assisted lung and colon cancer detection. A large dataset of 25,000 histopathological photographs of lung and colon tissues is analyzed to build a Deep-learning model using the Ensemble Method approach for accurate and reliable cancer detection. To increase efficiency, the photos are divided into a total of five different classes. The methodology underlying the study aims to increase the detection accuracy by building a model which learns from pre-existing models in the field; thus displaying superiority in terms of predictive power. The core concept of transfer learning is used to leverage the knowledge of pre-trained models and create better and improved ensemble models. The study includes comprehensive data preprocessing, augmentation, model training, validation and testing, and model performance evaluation. With a high accuracy of 0.96, this model achieved high reliability in detecting cancer cells. This effort holds the potential to improve cancer diagnosis through efficient and accurate classification of medical images. Using pre-trained models is an efficient and effective approach to reduce the time and resources required to develop high-accuracy models.