In Clinical cancer research : an official journal of the American Association for Cancer Research
BACKGROUND : Patients with 1p/19q co-deleted low grade glioma (LGG) have longer overall survival and better treatment response than patients with 1p/19q intact tumors. Therefore, it is relevant to know the 1p/19q status. To investigate whether the 1p/19q status can be assessed prior to tumor resection, we developed a machine learning algorithm to predict the 1p/19q status of presumed LGG based on preoperative magnetic resonance imaging (MRI).
METHODS : Preoperative brain MRI scans from 284 patients who had undergone biopsy or resection of presumed LGG were used to train a support vector machine algorithm. The algorithm was trained based on features extracted from T1-weighted and T2-weighted MRI scans, and on patient age and sex. The performance of the algorithm compared to tissue diagnosis was assessed on an external validation dataset of MRI scans from 129 LGG patients from The Cancer Imaging Archive (TCIA). Four clinical experts also predicted the 1p/19q status of the TCIA MRI scans.
RESULTS : The algorithm achieved an area under the curve (AUC) of 0.72 in the external validation dataset. The algorithm had a higher predictive performance than the average of the neurosurgeons (AUC 0.52), but lower than that of the neuroradiologists (AUC 0.81). There was a wide variability between clinical experts (AUC 0.45-0.83).
CONCLUSION : Our results suggest that our algorithm can non-invasively predict the 1p/19q status of presumed LGG with a performance that on average outperformed the oncological neurosurgeons . Evaluation on an independent dataset indicates that our algorithm is robust and generalizable.
van der Voort Sebastian R, Incekara Fatih, Wijnenga Maarten Mj, Kapsas Georgios, Gardeniers Mayke, Schouten Joost W, Starmans Martijn Pa, Nandoe Tewarie Rishie, Lycklama Geert J, French Pim J, Dubbink Hendrikus J, van den Bent Martin J, Vincent Arnaud Jpe, Niessen Wiro J, Klein Stefan, Smits Marion