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

This paper introduces a deep neural network based method, i.e., DeepOrganNet,to generate and visualize high-fidelity 3D / 4D organ geometric models fromsingle-view medical image in real time. Traditional 3D / 4D medical imagereconstruction requires near hundreds of projections, which cost insufferablecomputational time and deliver undesirable high imaging / radiation dose tohuman subjects. Moreover, it always needs further notorious processes toextract the accurate 3D organ models subsequently. To our knowledge, there isno method directly and explicitly reconstructing multiple 3D organ meshes froma single 2D medical grayscale image on the fly. Given single-view 2D medicalimages, e.g., 3D / 4D-CT projections or X-ray images, our end-to-endDeepOrganNet framework can efficiently and effectively reconstruct 3D / 4D lungmodels with a variety of geometric shapes by learning the smooth deformationfields from multiple templates based on a trivariate tensor-product deformationtechnique, leveraging an informative latent descriptor extracted from input 2Dimages. The proposed method can guarantee to generate high-quality andhigh-fidelity manifold meshes for 3D / 4D lung models. The major contributionsof this work are to accurately reconstruct the 3D organ shapes from 2Dsingle-view projection, significantly improve the procedure time to allowon-the-fly visualization, and dramatically reduce the imaging dose for humansubjects. Experimental results are evaluated and compared with the traditionalreconstruction method and the state-of-the-art in deep learning, by usingextensive 3D and 4D examples from synthetic phantom and real patient datasets.The proposed method only needs several milliseconds to generate organ mesheswith 10K vertices, which has a great potential to be used in real-time imageguided radiation therapy (IGRT).

DeepOrganNet: On-the-Fly Reconstruction and Visualization of 3D / 4D Lung Models from Single-View Projections by Deep Deformation Network