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

Deep learning has made a remarkable impact in the field of natural imageprocessing over the past decade. Consequently, there is a great deal ofinterest in replicating this success across unsolved tasks in related domains,such as medical image analysis. Core to medical image analysis is the task ofsemantic segmentation which enables various clinical workflows. Due to thechallenges inherent in manual segmentation, many decades of research have beendevoted to discovering extensible, automated, expert-level segmentationtechniques. Given the groundbreaking performance demonstrated by recent neuralnetwork-based techniques, deep learning seems poised to achieve what classicmethods have historically been unable. This paper will briefly overview some ofthe state-of-the-art (SoTA) neural network-based segmentation algorithms with aparticular emphasis on the most recent architectures, comparing and contrastingthe contributions and characteristics of each network topology. Usingultrasonography as a motivating example, it will also demonstrate importantclinical implications of effective deep learning-based solutions, articulatechallenges unique to the modality, and discuss novel approaches developed inresponse to those challenges, concluding with the proposal of future directionsin the field. Given the generally observed ephemerality of the best deeplearning approaches (i.e. the extremely quick succession of the SoTA), the maincontributions of the paper are its contextualization of modern deep learningarchitectures with historical background and the elucidation of the currenttrajectory of volumetric medical image segmentation research.

Catalyzing Clinical Diagnostic Pipelines Through Volumetric Medical Image Segmentation Using Deep Neural Networks: Past, Present, & Future