Medical Image Segmentation via Cascaded Attention Decoding

By Md Mostafijur Rahman, Radu Marculescu. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2023

333 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c27dcfd2e6bbe0954eeb06c9b72f4937778ec4bb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mustafa Munir
  2. Radu Marculescu
  3. Md Mostafijur Rahman

In Computer Vision and Pattern Recognition

  1. Mustafa Munir
  2. Md Mostafijur Rahman
  3. Radu Marculescu

Citations in the corpus