Unsupervised Clustering of Quantitative Imaging Phenotypes using Autoencoder and Gaussian Mixture Model

TL;DR

This paper introduces an unsupervised pipeline combining autoencoders and Gaussian mixture models to cluster radiomic features, effectively capturing disease heterogeneity and predicting patient survival in colorectal cancer liver metastases.

Contribution

It presents a novel unsupervised clustering method that automatically determines the optimal number of clusters and outperforms existing methods in radiomics analysis.

Findings

Automatically identifies optimal number of clusters

Clusters correlate with significantly different survival rates

Outperforms other unsupervised clustering methods

Abstract

Quantitative medical image computing (radiomics) has been widely applied to build prediction models from medical images. However, overfitting is a significant issue in conventional radiomics, where a large number of radiomic features are directly used to train and test models that predict genotypes or clinical outcomes. In order to tackle this problem, we propose an unsupervised learning pipeline composed of an autoencoder for representation learning of radiomic features and a Gaussian mixture model based on minimum message length criterion for clustering. By incorporating probabilistic modeling, disease heterogeneity has been taken into account. The performance of the proposed pipeline was evaluated on an institutional MRI cohort of 108 patients with colorectal cancer liver metastases. Our approach is capable of automatically selecting the optimal number of clusters and assigns patients into clusters (imaging subtypes) with significantly different survival rates. Our method outperforms other unsupervised clustering methods that have been used for radiomics analysis and has comparable performance to a state-of-the-art imaging biomarker.