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

Booming deep learning has substantially improved the diagnosis for diverselesions in ultrasound images, but a conspicuous research gap concerningcervical lymph node lesions still remains. The objective of this work is todiagnose cervical lymph node lesions in ultrasound images by leveraging a deeplearning model. To this end, we first collected 3392 cervical ultrasound imagescontaining normal lymph nodes, benign lymph node lesions, malignant primarylymph node lesions, and malignant metastatic lymph node lesions. Given thatultrasound images are generated by the reflection and scattering of sound wavesacross varied bodily tissues, we proposed the Conv-FFT Block. It integratesconvolutional operations with the fast Fourier transform to more astutely modelthe images. Building upon this foundation, we designed a novel architecture,named SFUSNet. SFUSNet not only discerns variances in ultrasound images fromthe spatial domain but also adeptly captures micro-structural alterationsacross various lesions in the frequency domain. To ascertain the potential ofSFUSNet, we benchmarked it against 12 popular architectures through five-foldcross-validation. The results show that SFUSNet is the state-of-the-art modeland can achieve 92.89% accuracy. Moreover, its average precision, averagesensitivity and average specificity for four types of lesions achieve 90.46%,89.95% and 97.49%, respectively.

SFUSNet: A Spatial-Frequency domain-based Multi-branch Network for diagnosis of Cervical Lymph Node Lesions in Ultrasound Images