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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Image post-processing is used in clinical-grade ultrasound scanners toimprove image quality (e.g., reduce speckle noise and enhance contrast). Thesepost-processing techniques vary across manufacturers and are generally keptproprietary, which presents a challenge for researchers looking to matchcurrent clinical-grade workflows. We introduce a deep learning framework,MimickNet, that transforms raw conventional delay-and-summed (DAS) beams intothe approximate post-processed images found on clinical-grade scanners.Training MimickNet only requires post-processed image samples from a scanner ofinterest without the need for explicit pairing to raw DAS data. Thisflexibility allows it to hypothetically approximate any manufacturer'spost-processing without access to the pre-processed data. MimickNet generatesimages with an average similarity index measurement (SSIM) of 0.930$\pm$0.0892on a 300 cineloop test set, and it generalizes to cardiac cineloops outside ofour train-test distribution achieving an SSIM of 0.967$\pm$0.002. We alsoexplore the theoretical SSIM achievable by evaluating MimickNet performancewhen trained under gray-box constraints (i.e., when both pre-processed andpost-processed images are available). To our knowledge, this is the first workto establish deep learning models that closely approximate currentclinical-grade ultrasound post-processing under realistic black-box constraintswhere before and after post-processing data is unavailable. MimickNet serves asa clinical post-processing baseline for future works in ultrasound imageformation to compare against. To this end, we have made the MimickNet softwareopen source.

MimickNet, Mimicking Clinical Image Post- Processing Under Black-Box Constraints