Uncertainty-driven Sanity Check: Application to Postoperative Brain Tumor Cavity Segmentation

TL;DR

This paper introduces an uncertainty-driven sanity check for brain tumor cavity segmentation that leverages Monte Carlo dropout to identify results needing expert review, enhancing safety in medical applications.

Contribution

It presents a novel method combining uncertainty estimation with a sanity check to improve validation of segmentation results in medical imaging.

Findings

Accurately segments resection cavities with Dice 0.792 ± 0.154

Detects the worst segmentation and most outliers effectively

Demonstrates potential for model validation in clinical settings

Abstract

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.