Semantic Segmentation of Histopathological Images with Fully and Dilated Convolutional Networks

Nowadays, the segmentation of different components in medical images is a major subject of study, and parallel to this, numerous image segmentation methods are still being developed. This study aimed to assess image segmentation methodologies utilizing deep learning models, due to the success of deep learning models in image processing applications. Firstly, starting from the introduction, a literature review on semantic segmentation and medical image segmentation is introduced in this study. In addition, pre-processing steps and techniques, models used, evaluation criteria, and the reasons for their preference are also explained. In the methods section, SegNet, U-Net, and DeepLabV3+ model architectures are introduced, and the architectures of these models are visualized at a basic level. The application results section includes all evaluation results with the metrics used in measuring accuracy. The comparison of the evaluation results and the evaluations on these results are included in the results and discussion section. In addition to these, visualized prediction results are also presented under the application results section.