Lung and colon cancer detection with InceptionResNetV2: a transfer learning approach

Lung and colon cancers are among the most common and lethal types of cancer. It is possible for individuals to develop both cancers simultaneously, as risk factors such as smoking, which is a leading cause of lung cancer, can also contribute to poor dietary habits, thereby increasing the risk of colon cancer. Traditionally, the diagnosis of these cancers relies on biopsies and subsequent laboratory analysis. This study proposes an Inception-ResNetV2-based model for accurately classifying lung and colon cancer using histopathological images. The dataset analyzed consists of 25,000 images categorized into five cancer types: Colon Adenocarcinoma, Colon Benign Tissue, Lung Adenocarcinoma, Lung Benign Tissue, and Lung Squamous Cell Carcinoma. The developed approach achieved an accuracy of 99.15%. The model's performance is further enhanced through the use of Local Binary Patterns (LBP), improving both accuracy and computational efficiency. Additionally, the explainable AI method SHAP is employed to demonstrate the contribution of each feature to the predictive analysis