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

TL;DR

This study explores using deep learning and StyleGAN embeddings of facial photos to predict cancer patient survival, demonstrating that facial features contain valuable prognostic information beyond traditional clinical data.

Contribution

First to investigate the use of StyleGAN embeddings of portrait photos for cancer survival prediction, achieving improved accuracy and interpretability.

Findings

Achieved a C-index of 0.677 using facial image embeddings.

Validated reliance on essential facial features, reducing bias.

Extracted health attributes from facial features with potential clinical value.

Abstract

Survival prediction for cancer patients is critical for optimal treatment selection and patient management. Current patient survival prediction methods typically extract survival information from patients' clinical record data or biological and imaging data. In practice, experienced clinicians can have a preliminary assessment of patients' health status based on patients' observable physical appearances, which are mainly facial features. However, such assessment is highly subjective. In this work, the efficacy of objectively capturing and using prognostic information contained in conventional portrait photographs using deep learning for survival predication purposes is investigated for the first time. A pre-trained StyleGAN2 model is fine-tuned on a custom dataset of our cancer patients' photos to empower its generator with generative ability suitable for patients' photos. The StyleGAN2 is then used to embed the photographs to its highly expressive latent space. Utilizing the state-of-the-art survival analysis models and based on StyleGAN's latent space photo embeddings, this approach achieved a C-index of 0.677, which is notably higher than chance and evidencing the prognostic value embedded in simple 2D facial images. In addition, thanks to StyleGAN's interpretable latent space, our survival prediction model can be validated for relying on essential facial features, eliminating any biases from extraneous information like clothing or background. Moreover, a health attribute is obtained from regression coefficients, which has important potential value for patient care.