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

Image segmentation is an important task in medical imaging. It constitutesthe backbone of a wide variety of clinical diagnostic methods, treatments, andcomputer-aided surgeries. In this paper, we propose a multi-kernel imagesegmentation net (MKIS-Net), which uses multiple kernels to create an efficientreceptive field and enhance segmentation performance. As a result of itsmulti-kernel design, MKIS-Net is a light-weight architecture with a smallnumber of trainable parameters. Moreover, these multi-kernel receptive fieldsalso contribute to better segmentation results. We demonstrate the efficacy ofMKIS-Net on several tasks including segmentation of retinal vessels, skinlesion segmentation, and chest X-ray segmentation. The performance of theproposed network is quite competitive, and often superior, in comparison tostate-of-the-art methods. Moreover, in some cases MKIS-Net has more than anorder of magnitude fewer trainable parameters than existing medical imagesegmentation alternatives and is at least four times smaller than otherlight-weight architectures.

MKIS-Net: A Light-Weight Multi-Kernel Network for Medical Image Segmentation