English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

One of the common and promising deep learning approaches used for medicalimage segmentation is transformers, as they can capture long-range dependenciesamong the pixels by utilizing self-attention. Despite being successful inmedical image segmentation, transformers face limitations in capturing localcontexts of pixels in multimodal dimensions. We propose a Medical ImageSegmentation Transformer (MIST) incorporating a novel Convolutional AttentionMixing (CAM) decoder to address this issue. MIST has two parts: a pre-trainedmulti-axis vision transformer (MaxViT) is used as an encoder, and the encodedfeature representation is passed through the CAM decoder for segmenting theimages. In the CAM decoder, an attention-mixer combining multi-headself-attention, spatial attention, and squeeze and excitation attention modulesis introduced to capture long-range dependencies in all spatial dimensions.Moreover, to enhance spatial information gain, deep and shallow convolutionsare used for feature extraction and receptive field expansion, respectively.The integration of low-level and high-level features from different networkstages is enabled by skip connections, allowing MIST to suppress unnecessaryinformation. The experiments show that our MIST transformer with CAM decoderoutperforms the state-of-the-art models specifically designed for medical imagesegmentation on the ACDC and Synapse datasets. Our results also demonstratethat adding the CAM decoder with a hierarchical transformer improvessegmentation performance significantly. Our model with data and code ispublicly available on GitHub.

MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder