Automated grade prediction of glioma patients based on magnetic resonance imaging and a random forests approach
- Author
- Stijn Bonte, Ingeborg Goethals (UGent) and Roel Van Holen (UGent)
- Organization
- Abstract
- An automated brain tumour classification method is presented which is able to distinguish between low-grade and high-grade glioma on conventional MRI scans. Per patient, 208 quantitative features are extracted from a manually annotated brain tumour database of 274 patients. These features were then used to train a Random Forests classification algorithm. We achieved a high-grade prediction sensitivity of 85.5% and specificity of 83.3%, with a global accuracy of 85.0%.
- Keywords
- Neuro-oncology, Machine Learning, Radiomics, Glioma, Random Forests, MRI
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8117504
- MLA
- Bonte, Stijn, et al. “Automated Grade Prediction of Glioma Patients Based on Magnetic Resonance Imaging and a Random Forests Approach.” Neuro-Oncology, vol. 18, no. Supplement 4, Society for Neuro-Oncology, 2016, pp. iv38–iv38.
- APA
- Bonte, S., Goethals, I., & Van Holen, R. (2016). Automated grade prediction of glioma patients based on magnetic resonance imaging and a random forests approach. Neuro-Oncology, 18(Supplement 4), iv38–iv38. Society for Neuro-Oncology.
- Chicago author-date
- Bonte, Stijn, Ingeborg Goethals, and Roel Van Holen. 2016. “Automated Grade Prediction of Glioma Patients Based on Magnetic Resonance Imaging and a Random Forests Approach.” In Neuro-Oncology, 18:iv38–iv38. Society for Neuro-Oncology.
- Chicago author-date (all authors)
- Bonte, Stijn, Ingeborg Goethals, and Roel Van Holen. 2016. “Automated Grade Prediction of Glioma Patients Based on Magnetic Resonance Imaging and a Random Forests Approach.” In Neuro-Oncology, 18:iv38–iv38. Society for Neuro-Oncology.
- Vancouver
- 1.Bonte S, Goethals I, Van Holen R. Automated grade prediction of glioma patients based on magnetic resonance imaging and a random forests approach. In: Neuro-Oncology. Society for Neuro-Oncology; 2016. p. iv38–iv38.
- IEEE
- [1]S. Bonte, I. Goethals, and R. Van Holen, “Automated grade prediction of glioma patients based on magnetic resonance imaging and a random forests approach,” in Neuro-Oncology, Mannheim/Heidelberg, 2016, vol. 18, no. Supplement 4, pp. iv38–iv38.
@inproceedings{8117504, abstract = {{An automated brain tumour classification method is presented which is able to distinguish between low-grade and high-grade glioma on conventional MRI scans. Per patient, 208 quantitative features are extracted from a manually annotated brain tumour database of 274 patients. These features were then used to train a Random Forests classification algorithm. We achieved a high-grade prediction sensitivity of 85.5% and specificity of 83.3%, with a global accuracy of 85.0%.}}, author = {{Bonte, Stijn and Goethals, Ingeborg and Van Holen, Roel}}, booktitle = {{Neuro-Oncology}}, issn = {{1522-8517}}, keywords = {{Neuro-oncology,Machine Learning,Radiomics,Glioma,Random Forests,MRI}}, language = {{eng}}, location = {{Mannheim/Heidelberg}}, number = {{Supplement 4}}, pages = {{iv38--iv38}}, publisher = {{Society for Neuro-Oncology}}, title = {{Automated grade prediction of glioma patients based on magnetic resonance imaging and a random forests approach}}, volume = {{18}}, year = {{2016}}, }