Cancerious Tissue Detection On Medical Images By Using Deep Learning Methods

Cancer is one of the most frequent disase and the second cause of death. The number of cancer cases is increasing in our country too. It is known that early detection of cancer is critical to increase the success of treatment. But nowadays the increase in the number of cancer cases causes examination periods to be shorter and the chance of making the right diagnosis to be decreased. Additionaly, the insufficient number of expert doctors in oncology area in our country causes inadequacy in the examinations. In addition to serious developments in medical imaging, technological developments are also utilized in the examination of these images. One of these technological developments is deep learning which is current equivalent of artificial intelligence. In this study, it was aimed to detect cancerous tissue on medical images by using deep learning methods. YOLO, one of the Artificial Neural Network architectures is used in the study. A real-time object detection tool, YOLO succeeded detection of cancer cells in medical images with the correct configuration. About 70 -75% success rate was achieved in the detection of tumor cell images in the data set used in the study.