Adaptive unsupervised learning with enhanced feature representation for intra-tumor partitioning and survival prediction for glioblastoma

TL;DR

This paper introduces an adaptive unsupervised learning method using a feature-enhanced auto-encoder and Bayesian optimization to improve intra-tumor partitioning and survival prediction in glioblastoma MRI analysis.

Contribution

It presents a novel feature-enhanced auto-encoder and an adaptive hyper-parameter optimization framework for more stable and accurate glioblastoma sub-region segmentation and survival prediction.

Findings

Produced robust MRI sub-regions relevant to clinical outcomes

Achieved statistically significant survival prediction results

Enhanced clustering stability with the proposed auto-encoder

Abstract

Glioblastoma is profoundly heterogeneous in regional microstructure and vasculature. Characterizing the spatial heterogeneity of glioblastoma could lead to more precise treatment. With unsupervised learning techniques, glioblastoma MRI-derived radiomic features have been widely utilized for tumor sub-region segmentation and survival prediction. However, the reliability of algorithm outcomes is often challenged by both ambiguous intermediate process and instability introduced by the randomness of clustering algorithms, especially for data from heterogeneous patients. In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction. A novel and problem-specific Feature-enhanced Auto-Encoder (FAE) is developed to enhance the representation of pairwise clinical modalities and therefore improve clustering stability of unsupervised learning algorithms such as K-means. Moreover, the entire process is modelled by the Bayesian optimization (BO) technique with a custom loss function that the hyper-parameters can be adaptively optimized in a reasonably few steps. The results demonstrate that the proposed approach can produce robust and clinically relevant MRI sub-regions and statistically significant survival predictions.