A Study on Transformers and CNNs in Medical Image Segmentation
Seungri Yoo The Graduate school of Advanced Imaging Science, Multimedia & film.
Seungri Yoo
| The Graduate school of Advanced Imaging Science, Multimedia & film.
Research on artificial intelligence (AI) has continued to develop considerably in recent years. In particular, the emergence of ChatGPT in the field of natural language processing (NLP) is having a greater influence on human life than the appearance of AlphaGo several years ago. Attention-based Transformers, which are playing a significant role in the field of deep learning, are gradually spreading not only to natural images but also to the field of medical image analysis. In the recent field of medical image segmentation, models that implement a similar appearance to U-Net through the merger of Transformers and CNN have emerged, and these models show significantly better results compared to the existing U-Net. In this paper, we will talk about how Transformers and CNN-based networks have been applied to the field of medical image segmentation.