ENCODER-DECODER ATTENTION NETWORK (EDANET) FOR POLYP SEGMENTATION IN COLONOSCOPY IMAGES
Colorectal cancer (CRC) is one of the most common malignancies that can develop from high-risk colon polyps. Colonoscopy is a standard for examination and detection of colorectal polyps.[1] Segmentation and distinction of polyps can play a vital role in treatment (e.g., surgical planning) and predictive decision making. This paper proposes a neural network architecture called EDANet, using attention gates to effectively combine multi-level features to yield accurate polyp segmentation. The Encoder is a fully connected Convolution Neural Network (CNN) and the decoder part is a Cascaded Partial Decoder. Encoder and Decoder sub-networks are connected through a series of nested, dense skip pathways. The skip pathways aim at reducing the semantic gap between the feature maps of the Encoder and Decoder sub-networks. The proposed system trains the model on several epochs and it unies the previous epoch mask with the feature map of the current training epoch. The previous epoch mask is then used to provide a hard attention to the learnt feature maps at different convolutional layers. Experimental results demonstrate that the model trained and tested on the Kvasir-SEG dataset achieves a dice coefcient of 0.7874, mean Intersection over Union (mIoU) of 0.7010, recall of 0.7987, and a precision of 0.8577.