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

Survival prediction for cancer patients is critical for optimal treatmentselection and patient management. Current patient survival prediction methodstypically extract survival information from patients' clinical record data orbiological and imaging data. In practice, experienced clinicians can have apreliminary assessment of patients' health status based on patients' observablephysical appearances, which are mainly facial features. However, suchassessment is highly subjective. In this work, the efficacy of objectivelycapturing and using prognostic information contained in conventional portraitphotographs using deep learning for survival predication purposes isinvestigated for the first time. A pre-trained StyleGAN2 model is fine-tuned ona custom dataset of our cancer patients' photos to empower its generator withgenerative ability suitable for patients' photos. The StyleGAN2 is then used toembed the photographs to its highly expressive latent space. Utilizing thestate-of-the-art survival analysis models and based on StyleGAN's latent spacephoto embeddings, this approach achieved a C-index of 0.677, which is notablyhigher than chance and evidencing the prognostic value embedded in simple 2Dfacial images. In addition, thanks to StyleGAN's interpretable latent space,our survival prediction model can be validated for relying on essential facialfeatures, eliminating any biases from extraneous information like clothing orbackground. Moreover, a health attribute is obtained from regressioncoefficients, which has important potential value for patient care.

Deep Learning for Cancer Prognosis Prediction Using Portrait Photos by StyleGAN Embedding