Classification of Cervical Type Image Using Capsule Networks

Cancer is one of the most lethal disease in the world. Therefore, early treatment of cancerous patient is proofed effective to decrease the lethal rate of this disease. For example, is cervical cancer, the precancerous step of cervical cancer is detected by looking at the cancerous transformation zone on the cervix. Furthermore, there are some different type of cervix regarding to its transformation zone. Therefore skills and experience is needed to be able to precisely determine which type of cervix making detection of cervical cancer is less efficient. This study is creating a deep learning model based on Capsule Networks to classify colposcopy images as a solution to make cervical cancer detection and treatment more effective and efficient. With a result of 100\% accuracy of the test set and 94.98\% accuracy of the train set. This study exceeds the result of other earlier experiments.