Diagnosis of lung and colon cancer based on clinical pathology images using convolutional neural network and CLAHE framework

Cancer is a non-contagious disease that the leading cause of death globally. The most common types cancer with high mortality are lung and colon cancer. One efforts to reduce cases early diagnosis followed by medical therapy. Tissue sampling clinical pathological examination gold standard in diagnosis. However, some cases, tissue cell level requires accuracy, depending on contrast image, experience clinician. Therefore, we need an image processing approach combined artificial intelligence for automatic classification. In this study, method proposed classification based deep learning approach. object classified histopathological normal tissue, benign cancer, malignant Convolutional neural network (CNN) VGG16 architecture Contrast Limited Adaptive Histogram Equalization (CLAHE) were employed demonstration 25000 images. simulation results show able classify maximum accuracy 98.96%. system performance using CLAHE shows higher detection than without consistent all epoch scenarios. comparative study outperforms previous studies. With method, it hoped can help clinicians diagnosing automatically, low cost, fast large datasets.