Unravelling the effect of data augmentation transformations in polyp segmentation
ConclusionDespite being infrequently used, pixel-based transformations show a great potential to improve polyp segmentation in CVC-EndoSceneStill. On the other hand, image-based transformations are more suitable for Kvasir-SEG. Problem-based transformations behave similarly in both datasets. Polyp area, brightness and contrast of the dataset have an influence on these differences.
Source: International Journal of Computer Assisted Radiology and Surgery - Category: Intensive Care Source Type: research
More News: Computers | Databases & Libraries | Intensive Care | Learning | Polyps | Radiology | Statistics | Universities & Medical Training