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 accurate segmentation of breast tumors is an important prerequisite forlesion detection, which has significant clinical value for breast tumorresearch. The mainstream deep learning-based methods have achieved abreakthrough. However, these high-performance segmentation methods areformidable to implement in clinical scenarios since they always embrace highcomputation complexity, massive parameters, slow inference speed, and hugememory consumption. To tackle this problem, we propose LightBTSeg, a dual-pathjoint knowledge distillation framework, for lightweight breast tumorsegmentation. Concretely, we design a double-teacher model to represent thefine-grained feature of breast ultrasound according to different semanticfeature realignments of benign and malignant breast tumors. Specifically, weleverage the bottleneck architecture to reconstruct the original AttentionU-Net. It is regarded as a lightweight student model named Simplified U-Net.Then, the prior knowledge of benign and malignant categories is utilized todesign the teacher network combined dual-path joint knowledge distillation,which distills the knowledge from cumbersome benign and malignant teachers to alightweight student model. Extensive experiments conducted on breast ultrasoundimages (Dataset BUSI) and Breast Ultrasound Dataset B (Dataset B) datasetsdemonstrate that LightBTSeg outperforms various counterparts.

LightBTSeg: A lightweight breast tumor segmentation model using ultrasound images via dual-path joint knowledge distillation