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

Over the last ten years, Patient-Derived Organoids (PDOs) emerged as the mostreliable technology to generate ex-vivo tumor avatars. PDOs retain the maincharacteristics of their original tumor, making them a system of choice forpre-clinical and clinical studies. In particular, PDOs are attracting interestin the field of Functional Precision Medicine (FPM), which is based upon anex-vivo drug test in which living tumor cells (such as PDOs) from a specificpatient are exposed to a panel of anti-cancer drugs. Currently, the AdenosineTriphosphate (ATP) based cell viability assay is the gold standard test toassess the sensitivity of PDOs to drugs. The readout is measured at the end ofthe assay from a global PDO population and therefore does not capture singlePDO responses and does not provide time resolution of drug effect. To this end,in this study, we explore for the first time the use of powerful largefoundation models for the automatic processing of PDO data. In particular, wepropose a novel imaging-based high-throughput screening method to assessreal-time drug efficacy from a time-lapse microscopy video of PDOs. Therecently proposed SAM algorithm for segmentation and DINOv2 model are adaptedin a comprehensive pipeline for processing PDO microscopy frames. Moreover, anattention mechanism is proposed for fusing temporal and spatial features in amultiple instance learning setting to predict ATP. We report better resultsthan other non-time-resolved methods, indicating that the temporality of datais an important factor for the prediction of ATP. Extensive ablations shedlight on optimizing the experimental setting and automating the prediction bothin real-time and for forecasting.

Spatio-Temporal Analysis of Patient-Derived Organoid Videos Using Deep Learning for the Prediction of Drug Efficacy