Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma
This work addresses the need for a non-invasive, cost-effective alternative to invasive tissue sampling for glioma patients, though it appears incremental as it builds on existing radiogenomics approaches.
The authors tackled the problem of non-invasive prediction of isocitrate dehydrogenase (IDH) mutation status in glioma patients by developing a collaborative learning framework that integrates tumor images and geometrics using CNNs and GNNs, resulting in a model that outperforms baseline methods and identifies key regions of interest.
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.