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

The real-time segmentation of surgical instruments plays a crucial role inrobot-assisted surgery. However, it is still a challenging task to implementdeep learning models to do real-time segmentation for surgical instruments dueto their high computational costs and slow inference speed. In this paper, wepropose an attention-guided lightweight network (LWANet), which can segmentsurgical instruments in real-time. LWANet adopts encoder-decoder architecture,where the encoder is the lightweight network MobileNetV2, and the decoderconsists of depthwise separable convolution, attention fusion block, andtransposed convolution. Depthwise separable convolution is used as the basicunit to construct the decoder, which can reduce the model size andcomputational costs. Attention fusion block captures global contexts andencodes semantic dependencies between channels to emphasize target regions,contributing to locating the surgical instrument. Transposed convolution isperformed to upsample feature maps for acquiring refined edges. LWANet cansegment surgical instruments in real-time while takes little computationalcosts. Based on 960*544 inputs, its inference speed can reach 39 fps with only3.39 GFLOPs. Also, it has a small model size and the number of parameters isonly 2.06 M. The proposed network is evaluated on two datasets. It achievesstate-of-the-art performance 94.10% mean IOU on Cata7 and obtains a new recordon EndoVis 2017 with a 4.10% increase on mean IOU.

Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments