Enhancing Cancer Diagnosis: CNN-Based Classification of Lung and Colon Histopathological Images

Lung and colon cancers rank among the most common and lethal malignancies globally, rendering precise and prompt detection essential for enhancing patient prognoses. This study introduces a convolutional neural network (CNN) methodology for the classification of lung and colon cancer utilising histopathology pictures. The model is engineered to differentiate among five distinct tissue categories: colon cancer, colon benign tissue, lung adenocarcinoma, lung benign tissue, and lung squamous cell carcinoma. The dataset underwent preprocessing through resizing, normalisation, and data augmentation methods to improve model generalisation. The CNN model was trained and assessed, with an overall accuracy of 97%, indicating its viability as a dependable instrument for aiding pathologists in cancer diagnosis. The model’s efficacy is evaluated against current methodologies, emphasising its superiority in precision and recall across several cancer types. This research advances the development of AI-driven diagnostic instruments, which can markedly improve the efficiency and precision of cancer detection in clinical environments.