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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Numerical simulations can model the physical processes that governcardiovascular device deployment. When such simulations incorporate digitaltwins; computational models of patient-specific anatomy, they can expedite andde-risk the device design process. Nonetheless, the exclusive use ofpatient-specific data constrains the anatomic variability which can beprecisely or fully explored. In this study, we investigate the capacity ofLatent Diffusion Models (LDMs) to edit digital twins to create anatomicvariants, which we term digital siblings. Digital twins and their correspondingsiblings can serve as the basis for comparative simulations, enabling the studyof how subtle anatomic variations impact the simulated deployment ofcardiovascular devices, as well as the augmentation of virtual cohorts fordevice assessment. However, while diffusion models have been characterized intheir ability to edit natural images, their capacity to anatomically editdigital twins has yet to be studied. Using a case example centered on 3Ddigital twins of cardiac anatomy, we implement various methods for generatingdigital siblings and characterize them through morphological and topologicalanalyses. We specifically edit digital twins to introduce anatomic variation atdifferent spatial scales and within localized regions, demonstrating theexistence of bias towards common anatomic features. We further show that suchanatomic bias can be leveraged for virtual cohort augmentation throughselective editing, partially alleviating issues related to dataset imbalanceand lack of diversity. Our experimental framework thus delineates the limitsand capabilities of using latent diffusion models in synthesizing anatomicvariation for in silico trials.

Probing the Limits and Capabilities of Diffusion Models for the Anatomic Editing of Digital Twins