Uncertainty-driven Sanity Check: Application to Postoperative Brain Tumor Cavity Segmentation
This work addresses safety-critical medical applications like neurosurgical interventions by providing a method to validate segmentation performance, though it is incremental as it builds on existing uncertainty estimation techniques.
The paper tackled the problem of improving reliability in postoperative brain tumor cavity segmentation by proposing an uncertainty-driven sanity check to identify results needing expert review, achieving Dice coefficients of 0.792 ± 0.154 and detecting the worst segmentation and three out of four outliers.
Uncertainty estimates of modern neuronal networks provide additional information next to the computed predictions and are thus expected to improve the understanding of the underlying model. Reliable uncertainties are particularly interesting for safety-critical computer-assisted applications in medicine, e.g., neurosurgical interventions and radiotherapy planning. We propose an uncertainty-driven sanity check for the identification of segmentation results that need particular expert review. Our method uses a fully-convolutional neural network and computes uncertainty estimates by the principle of Monte Carlo dropout. We evaluate the performance of the proposed method on a clinical dataset with 30 postoperative brain tumor images. The method can segment the highly inhomogeneous resection cavities accurately (Dice coefficients 0.792 $\pm$ 0.154). Furthermore, the proposed sanity check is able to detect the worst segmentation and three out of the four outliers. The results highlight the potential of using the additional information from the model's parameter uncertainty to validate the segmentation performance of a deep learning model.