Medical Image Segmentation via Cascaded Attention Decoding
Authors:
Top Cited Papers
- 1 January 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6211-6220
Abstract
Transformers have shown great promise in medical image segmentation due to their ability to capture long-range dependencies through self-attention. However, they lack the ability to learn the local (contextual) relations among pixels. Previous works try to overcome this problem by embedding convolutional layers either in the encoder or decoder modules of transformers thus ending up sometimes with inconsistent features. To address this issue, we propose a novel attention-based decoder, namely CASCaded Attention DEcoder (CASCADE), which leverages the multi-scale features of hierarchical vision transformers. CASCADE consists of i) an attention gate which fuses features with skip connections and ii) a convolutional attention module that enhances the long-range and local context by suppressing background information. We use a multi-stage feature and loss aggregation framework due to their faster convergence and better performance. Our experiments demonstrate that transformers with CASCADE significantly outperform state-of-the-art CNN- and transformer-based approaches, obtaining up to 5.07% and 6.16% improvements in DICE and mIoU scores, respectively. CASCADE opens new ways of designing better attention-based decoders.Keywords
This publication has 29 references indexed in Scilit:
- CE-Net: Context Encoder Network for 2D Medical Image SegmentationIEEE Transactions on Medical Imaging, 2019
- Reverse Attention for Salient Object Detection2018
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Squeeze-and-Excitation Networks2018
- SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- A Benchmark for Endoluminal Scene Segmentation of Colonoscopy ImagesJournal of Healthcare Engineering, 2017
- Automated Polyp Detection in Colonoscopy Videos Using Shape and Context InformationIEEE Transactions on Medical Imaging, 2015
- WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physiciansComputerized Medical Imaging and Graphics, 2015
- Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancerInternational Journal of Computer Assisted Radiology and Surgery, 2013