Controlling for Biasing Signals in Images for Prognostic Models: Survival Predictions for Lung Cancer with Deep Learning

by   Wouter A. C. van Amsterdam, et al.
UMC Utrecht

Deep learning has shown remarkable results for image analysis and is expected to aid individual treatment decisions in health care. To achieve this, deep learning methods need to be promoted from the level of mere associations to being able to answer causal questions. We present a scenario with real-world medical images (CT-scans of lung cancers) and simulated outcome data. Through the sampling scheme, the images contain two distinct factors of variation that represent a collider and a prognostic factor. We show that when this collider can be quantified, unbiased individual prognosis predictions are attainable with deep learning. This is achieved by (1) setting a dual task for the network to predict both the outcome and the collider and (2) enforcing independence of the activation distributions of the last layer with ordinary least squares. Our method provides an example of combining deep learning and structural causal models for unbiased individual prognosis predictions.


page 1

page 2

page 3

page 4


DeepMMSA: A Novel Multimodal Deep Learning Method for Non-small Cell Lung Cancer Survival Analysis

Lung cancer is the leading cause of cancer death worldwide. The critical...

Deep Learning for Automated Medical Image Analysis

Medical imaging is an essential tool in many areas of medical applicatio...

A Normalized Fully Convolutional Approach to Head and Neck Cancer Outcome Prediction

In medical imaging, radiological scans of different modalities serve to ...

Deep Learning for the Classification of Lung Nodules

Deep learning, as a promising new area of machine learning, has attracte...

Cats or CAT scans: transfer learning from natural or medical image source datasets?

Transfer learning is a widely used strategy in medical image analysis. I...

Airway Tree Modeling Using Dual-channel 3D UNet 3+ with Vesselness Prior

The lung airway tree modeling is essential to work for the diagnosis of ...

Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology

A model's ability to express its own predictive uncertainty is an essent...