Automated 5-year Mortality Prediction using Deep Learning and Radiomics Features from Chest Computed Tomography

TL;DR

This study develops and compares deep learning and radiomics-based models for predicting 5-year mortality in elderly using chest CT scans, demonstrating promising accuracy improvements for personalized healthcare.

Contribution

It introduces a unified deep learning framework and a radiomics-based approach for mortality prediction from chest CTs, with experimental validation on a novel dataset.

Findings

Deep learning model achieved 68.5% accuracy in mortality prediction.

Radiomics approach achieved 56-66% accuracy depending on features and classifiers.

Deep learning outperformed radiomics in this prediction task.

Abstract

We propose new methods for the prediction of 5-year mortality in elderly individuals using chest computed tomography (CT). The methods consist of a classifier that performs this prediction using a set of features extracted from the CT image and segmentation maps of multiple anatomic structures. We explore two approaches: 1) a unified framework based on deep learning, where features and classifier are automatically learned in a single optimisation process; and 2) a multi-stage framework based on the design and selection/extraction of hand-crafted radiomics features, followed by the classifier learning process. Experimental results, based on a dataset of 48 annotated chest CTs, show that the deep learning model produces a mean 5-year mortality prediction accuracy of 68.5%, while radiomics produces a mean accuracy that varies between 56% to 66% (depending on the feature selection/extraction method and classifier). The successful development of the proposed models has the potential to make a profound impact in preventive and personalised healthcare.