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/

Zendy Plus

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

Zendy Tools

Zendy Open

The rapidly emerging field of deep learning-based computational pathology hasdemonstrated promise in developing objective prognostic models from histologywhole slide images. However, most prognostic models are either based onhistology or genomics alone and do not address how histology and genomics canbe integrated to develop joint image-omic prognostic models. Additionallyidentifying explainable morphological and molecular descriptors from thesemodels that govern such prognosis is of interest. We used multimodal deeplearning to integrate gigapixel whole slide pathology images, RNA-seqabundance, copy number variation, and mutation data from 5,720 patients across14 major cancer types. Our interpretable, weakly-supervised, multimodal deeplearning algorithm is able to fuse these heterogeneous modalities forpredicting outcomes and discover prognostic features from these modalities thatcorroborate with poor and favorable outcomes via multimodal interpretability.We compared our model with unimodal deep learning models trained on histologyslides and molecular profiles alone, and demonstrate performance increase inrisk stratification on 9 out of 14 cancers. In addition, we analyze morphologicand molecular markers responsible for prognostic predictions across all cancertypes. All analyzed data, including morphological and molecular correlates ofpatient prognosis across the 14 cancer types at a disease and patient level arepresented in an interactive open-access database(http://pancancer.mahmoodlab.org) to allow for further exploration andprognostic biomarker discovery. To validate that these model explanations areprognostic, we further analyzed high attention morphological regions in WSIs,which indicates that tumor-infiltrating lymphocyte presence corroborates withfavorable cancer prognosis on 9 out of 14 cancer types studied.

Pan-Cancer Integrative Histology-Genomic Analysis via Interpretable Multimodal Deep Learning