Collaborative Learning of Images and Geometrics for Predicting Isocitrate Dehydrogenase Status of Glioma

TY - GEN

T1 - Collaborative Learning of Images and Geometrics for Predicting Isocitrate Dehydrogenase Status of Glioma

AU - Wei, Yiran

AU - Li, Chao

AU - Chen, Xi

AU - Schoinlieb, Carola Bibiane

AU - Price, Stephen J.

N1 - Publisher Copyright: © 2022 IEEE.

PY - 2022/4/26

Y1 - 2022/4/26

N2 - 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. Mean-while, 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.

AB - 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. Mean-while, 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.

KW - collaborative learning

KW - geometric deep learning

KW - glioma

KW - graph neural networks

KW - isocitrate dehydrogenase

UR - https://www.scopus.com/pages/publications/85129661066

U2 - 10.1109/ISBI52829.2022.9761407

DO - 10.1109/ISBI52829.2022.9761407

M3 - Conference contribution

AN - SCOPUS:85129661066

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - ISBI 2022 - Proceedings

PB - IEEE Computer Society

T2 - 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022

Y2 - 28 March 2022 through 31 March 2022

ER -