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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present W-Net, a novel Convolution Neural Network (CNN) framework thatemploys raw ultrasound waveforms from each A-scan, typically referred to asultrasound Radio Frequency (RF) data, in addition to the gray ultrasound imageto semantically segment and label tissues. Unlike prior work, we seek to labelevery pixel in the image, without the use of a background class. To the best ofour knowledge, this is also the first deep-learning or CNN approach forsegmentation that analyses ultrasound raw RF data along with the gray image.International patent(s) pending [PCT/US20/37519]. We chose subcutaneous tissue(SubQ) segmentation as our initial clinical goal since it has diverseintermixed tissues, is challenging to segment, and is an underrepresentedresearch area. SubQ potential applications include plastic surgery, adiposestem-cell harvesting, lymphatic monitoring, and possibly detection/treatment ofcertain types of tumors. A custom dataset consisting of hand-labeled images byan expert clinician and trainees are used for the experimentation, currentlylabeled into the following categories: skin, fat, fat fascia/stroma, muscle andmuscle fascia. We compared our results with U-Net and Attention U-Net. Ournovel \emph{W-Net}'s RF-Waveform input and architecture increased mIoU accuracy(averaged across all tissue classes) by 4.5\% and 4.9\% compared to regularU-Net and Attention U-Net, respectively. We present analysis as to why theMuscle fascia and Fat fascia/stroma are the most difficult tissues to label.Muscle fascia in particular, the most difficult anatomic class to recognize forboth humans and AI algorithms, saw mIoU improvements of 13\% and 16\% from ourW-Net vs U-Net and Attention U-Net respectively.

W-Net: Dense Semantic Segmentation of Subcutaneous Tissue in Ultrasound Images by Expanding U-Net to Incorporate Ultrasound RF Waveform Data