Generative Adversarial Networks for Automatic Polyp Segmentation
This work addresses the problem of automatic polyp segmentation, which is important for medical diagnosis, but the reported scores are low, suggesting an incremental contribution.
This paper explores the use of conditional generative adversarial networks for automatic polyp segmentation, framing it as an image-to-image translation task. The model achieved a Jaccard index of 0.4382 and an F2 score of 0.611.
This paper aims to contribute in bench-marking the automatic polyp segmentation problem using generative adversarial networks framework. Perceiving the problem as an image-to-image translation task, conditional generative adversarial networks are utilized to generate masks conditioned by the images as inputs. Both generator and discriminator are convolution neural networks based. The model achieved 0.4382 on Jaccard index and 0.611 as F2 score.