Pyramid-Focus-Augmentation: Medical Image Segmentation with Step-Wise Focus
This work tackles the problem of colon polyp segmentation, which is crucial for developing automatic decision support systems in gastrointestinal diagnostics, representing an incremental improvement in this domain.
This paper addresses the segmentation of colon polyps in medical images, proposing a grid-based augmentation method that uses a pyramid-like approach (large to small grids). The method achieves comparable results to other competitive methods in the Medico 2020 task.
Segmentation of findings in the gastrointestinal tract is a challenging but also an important task which is an important building stone for sufficient automatic decision support systems. In this work, we present our solution for the Medico 2020 task, which focused on the problem of colon polyp segmentation. We present our simple but efficient idea of using an augmentation method that uses grids in a pyramid-like manner (large to small) for segmentation. Our results show that the proposed methods work as indented and can also lead to comparable results when competing with other methods.