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

Current treatment planning of patients diagnosed with a brain tumor, such asglioma, could significantly benefit by accessing the spatial distribution oftumor cell concentration. Existing diagnostic modalities, e.g. magneticresonance imaging (MRI), contrast sufficiently well areas of high cell density.In gliomas, however, they do not portray areas of low cell concentration, whichcan often serve as a source for the secondary appearance of the tumor aftertreatment. To estimate tumor cell densities beyond the visible boundaries ofthe lesion, numerical simulations of tumor growth could complement imaginginformation by providing estimates of full spatial distributions of tumorcells. Over recent years a corpus of literature on medical image-based tumormodeling was published. It includes different mathematical formalismsdescribing the forward tumor growth model. Alongside, various parametricinference schemes were developed to perform an efficient tumor modelpersonalization, i.e. solving the inverse problem. However, the unifyingdrawback of all existing approaches is the time complexity of the modelpersonalization which prohibits a potential integration of the modeling intoclinical settings. In this work, we introduce a deep learning based methodologyfor inferring the patient-specific spatial distribution of brain tumors fromT1Gd and FLAIR MRI medical scans. Coined as Learn-Morph-Infer the methodachieves real-time performance in the order of minutes on widely availablehardware and the compute time is stable across tumor models of differentcomplexity, such as reaction-diffusion and reaction-advection-diffusion models.We believe the proposed inverse solution approach not only bridges the way forclinical translation of brain tumor personalization but can also be adopted toother scientific and engineering domains.

Learn-Morph-Infer: a new way of solving the inverse problem for brain tumor modeling