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

Magnetic resonance imaging (MRI) is highly sensitive for lesion detection inthe breasts. Sequences obtained with different settings can capture thespecific characteristics of lesions. Such multi-parameter MRI information hasbeen shown to improve radiologist performance in lesion classification, as wellas improving the performance of artificial intelligence models in varioustasks. However, obtaining multi-parameter MRI makes the examination costly inboth financial and time perspectives, and there may be safety concerns forspecial populations, thus making acquisition of the full spectrum of MRIsequences less durable. In this study, different than naive input fusion orfeature concatenation from existing MRI parameters, a novel$\textbf{I}$ntegrated MRI $\textbf{M}$ulti-$\textbf{P}$arameterreinf$\textbf{O}$rcement fusion generato$\textbf{R}$ wi$\textbf{T}$h$\textbf{A}$tte$\textbf{NT}$ion Network (IMPORTANT-Net) is developed togenerate missing parameters. First, the parameter reconstruction module is usedto encode and restore the existing MRI parameters to obtain the correspondinglatent representation information at any scale level. Then the multi-parameterfusion with attention module enables the interaction of the encoded informationfrom different parameters through a set of algorithmic strategies, and appliesdifferent weights to the information through the attention mechanism afterinformation fusion to obtain refined representation information. Finally, areinforcement fusion scheme embedded in a $V^{-}$-shape generation module isused to combine the hierarchical representations to generate the missing MRIparameter. Results showed that our IMPORTANT-Net is capable of generatingmissing MRI parameters and outperforms comparable state-of-the-art networks.Our code is available athttps://github.com/Netherlands-Cancer-Institute/MRI_IMPORTANT_NET.

IMPORTANT-Net: Integrated MRI Multi-Parameter Reinforcement Fusion Generator with Attention Network for Synthesizing Absent Data