Brain Tumor Localization Using Yolo v2

Abstract

Brain tumors are one of the most important causes of the increase in mortality worldwide. Early detection of brain tumors can save many lives. Therefore, brain tumors need to be detected quickly and accurately. Many algorithms have been developed using conventional image processing methods for brain tumor detection. The object detectors developed in all these algorithms consist of several stages in which the success of the current step depends on the success of the previous step. On the other hand, single-stage and two-stage deep learning-based detectors developed in recent years enable faster and more accurate object detection. However, in many deep learning-based detections, it is generally studied to determine the object locations in natural images. In this study, Yolo v2 model which is a single-stage deep learning-based detector is performed for brain tumor tissue detection. Initial results obtained by running the designed detector architecture on different data sets show the effectiveness of the proposed method.