Automatic Polyp Segmentation using U-Net-ResNet50

Paper: http://ceur-ws.org/Vol-2882/paper75.pdf
Slides: https://www.slideshare.net/multimediaeval/automatic-polyp-segmentation-using-unetresnet50

Saruar Alam, Nikhil Kumar Tomar, Aarati Thakur, Debesh Jha and Ashish Rauniyar : Automatic Polyp Segmentation using U-Net-ResNet50. Proc. of MediaEval 2020, 14-15 December 2020, Online.

Polyps are the predecessors to colorectal cancer, which is one of the leading causes of cancer-related deaths worldwide. Colonoscopy is the standard procedure for the identification, localization and removal of the colorectal polyps. Due to variability in shape, size and surrounding tissue similarity, colorectal polyps are often missed by the clinicians during colonoscopy. With the use of an automatic, accurate and fast polyp segmentation method during the colonoscopy many colorectal polyps can be easily detected and removed. The Medico automatic polyp segmentation challenge provides an opportunity to study the polyp segmentation and build a build an efficient and accurate segmentation algorithm. We use the U-Net with pre-trained ResNet50 as the encoder for the polyp segmentation. The model is trained on Kvasir-SEG dataset [7] and tested on the organiser's dataset and achieves a dice coefficient of 0.8154, Jaccard of 0.7396, recall of 0.8533, precision of 0.8532, accuracy of 0.9506, and F2 score of 0.8272 demonstrating the generalization ability of our model.

Presented by: Saruar Alam