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

Multispectral optoacoustic tomography (MSOT) is a high-resolution functionalimaging modality that can non-invasively access a broad range ofpathophysiological phenomena by quantifying the contrast of endogenouschromophores in tissue. Real-time imaging is imperative to translate MSOT intoclinical imaging, visualize dynamic pathophysiological changes associated withdisease progression, and enable in situ diagnoses. Model-based reconstructionaffords state-of-the-art optoacoustic images; however, the image qualityprovided by model-based reconstruction remains inaccessible during real-timeimaging because the algorithm is iterative and computationally demanding. Deeplearning affords faster reconstruction, but the lack of ground truth trainingdata can lead to reduced image quality for in vivo data. We introduce aframework, termed DeepMB, that achieves accurate optoacoustic imagereconstruction for arbitrary input data in 31 ms per image by expressingmodel-based reconstruction with a deep neural network. DeepMB facilitatesaccurate generalization to experimental test data through training on signalssynthesized from real-world images and ground truth images generated bymodel-based reconstruction. The framework affords in-focus images for a broadrange of anatomical locations because it supports dynamic adjustment of thereconstruction speed of sound during imaging. Furthermore, DeepMB is compatiblewith the data rates and image sizes of modern multispectral optoacoustictomography scanners. We evaluate DeepMB on a diverse dataset of in vivo imagesand demonstrate that the framework reconstructs images 1000 times faster thanthe iterative model-based reference method while affording near-identical imagequalities. Accurate and real-time image reconstructions with DeepMB can enablefull access to the high-resolution and multispectral contrast of handheldoptoacoustic tomography.

DeepMB: Deep neural network for real-time optoacoustic image reconstruction with adjustable speed of sound