Abstract
Extent Of Resection (EOR) after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. The current standard method for estimating EOR is subject to high inter- and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of EOR. In this study we trained neural networks for segmentation of residual tumor tissue in early post-operative MRI. We introduce a new dataset for this task, consisting of data from 645 patients from 13 hospitals in Europe and the US. The segmentation performance of the best model is similar to that of human expert raters, and the results be used to classify cases of gross total resection and residual tumor with high recall and precision.
