Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma

TL;DR

This paper introduces a collaborative learning framework combining CNNs and GNNs to non-invasively predict IDH mutation status in glioma from MRI images and tumor geometrics, outperforming baseline models.

Contribution

The study presents a novel collaborative learning approach integrating image and geometric data for glioma genotyping, enhancing prediction accuracy over individual models.

Findings

The collaborative model outperforms the 3D-DenseNet121 baseline.

Combining CNN and GNN improves prediction accuracy.

Model interpretation reveals key regions for IDH mutation prediction.

Abstract

The isocitrate dehydrogenase (IDH) gene mutation status is an important biomarker for glioma patients. The gold standard of IDH mutation detection requires tumour tissue obtained via invasive approaches and is usually expensive. Recent advancement in radiogenomics provides a non-invasive approach for predicting IDH mutation based on MRI. Meanwhile, tumor geometrics encompass crucial information for tumour phenotyping. Here we propose a collaborative learning framework that learns both tumor images and tumor geometrics using convolutional neural networks (CNN) and graph neural networks (GNN), respectively. Our results show that the proposed model outperforms the baseline model of 3D-DenseNet121. Further, the collaborative learning model achieves better performance than either the CNN or the GNN alone. The model interpretation shows that the CNN and GNN could identify common and unique regions of interest for IDH mutation prediction. In conclusion, collaborating image and geometric learners provides a novel approach for predicting genotype and characterising glioma.