A deep learning algorithm for fully automated volumetric measurement of meningioma burden

Background We sought to develop a deep learning (DL) model to enable fully automated 3D segmentation and volumetric assessment of meningioma burden with a specific emphasis on generalizing to high-grade and post-treatment meningiomas to improve interobserver variability and decrease reader time investment in tumor response assessment. Methods 450 post-contrast T1-weighted brain MRIs from 104 patients with meningiomas were obtained from Massachusetts General Hospital and Dana-Farber Cancer Institute. The cohort was unique among prior DL segmentation models in that it encompassed meningiomas of all grades, post-operative, and post-radiated meningiomas. Preprocessed MRIs and manually generated tumor segmentations were used to train a U-Net with a joint Dice-cross entropy loss function. Results When tested on internal data, our model achieved a median Dice of 0.741 and a median 95th percentile Hausdorff Distance (HD95) of 26 mm on a high-grade test set and a median Dice of 0.848 and median HD95 of 1.41 mm on a test set with low-grade tumors. Lesion-wise metrics were equivalent to global metrics for low-grade tumors, which contained only single lesions, but were substantially lower for high-grade tumors, with a median lesion-wise Dice of 0.45 and median lesion-wise HD95 of 130 mm, reflecting greater difficulty delineating individual high-grade lesions. Our model also generalized well to 1000 studies from 944 patients selected from the public BraTS dataset, achieving a median Dice of 0.923 and median HD95 of 2.24 mm. Conclusions The study produced a model that addresses an unmet need for automated volumetric measurements of meningiomas and created a reliable metric for quantifying meningioma burden. In comparison to prior DL approaches, our model achieved competitive performance on external data and improved Dice scores on high-grade and post-treatment meningiomas. The trained model, volumetric evaluation code, and accompanying documentation are available online at https://github.com/mccle/tumor_segmentation.1