Clinical evaluation of automated deep-learning based meningioma segmentation in multiparametric MRI

We trained an established deep-learning-model architecture (3D-Deep-Convolutional-Neural-Network, DeepMedic) on manual segmentations from 70 meningiomas independently segmented by two radiologists. The trained deep-learning model was then validated in a group of 55 meningiomas. Ground truth segmentations were established by two further radiologists in a consensus reading. In the validation-group the comparison of the automated deep-learning-model and manual segmentations revealed average dice-coefficients of 0.91±0.08 for contrast-enhancing-tumor volume and 0.82±0.12 for total-lesion-volume. In the training-group, interreader-variabilities of the two manual readers were 0.92±0.07 for contrast-enhancing-tumor and 0.88±0.05 for total-lesion-volume. Deep-learning based automated segmentation yielded high segmentation accuracy, comparable to manual interreader-variability.