Jeyagopal Janarththanan

Abstract— Cholangiocarcinoma affliction is the second most common primary cancer in worldwide. many Deep Learning (DL) has been suggested for classification, segmentation, and detection takes in medical imaging. The main research in this paper, we using InceptionRestNetV2 transfer learning model to classify, and ultimately acquire a practical and realistic computer-aided symptomatic model. In this investigation, we splitting the Cholangiocarcinoma images into blocks to build a new data source, then used the customize InceptionRestNetV2 model based on transfer learning to extract features frequently, and exercised softmax activation classifier to classify the Cholangiocarcinoma images. The model is evaluated dataset from Multidimensional Choledochal Database. Observations are made through 4116 colour images obtained from 880 scenes taken from 174 individuals and the classification model shows around 95% testing accuracy. Comparatively, this approach obtains high precision rate rather than other propose methods which are predicted to use small size of dataset samples.