Automatic detection and segmentation of postoperative cerebellar damage based on normalization

Surgical resection is the gold standard in the treatment of pediatric posterior fossa tumors. However, surgical damage is often unavoidable and its association with postoperative complications is not well understood. A reliable localization and measure of cerebellar damage is fundamental to study the relationship between the damaged cerebellar regions and postoperative neurological outcomes. Existing cerebellum normalization methods are likely to fail on postoperative scans, therefore current approaches to measure postoperative damage rely on manual labelling. In this work, we develop a robust algorithm to automatically detect and measure cerebellum damage in postoperative 3D T1 magnetic resonance imaging (MRI).

In our approach, normal brain tissues are first segmented using a Bayesian algorithm customized for postoperative scans. Next, the cerebellum is isolated by nonlinear registration of a whole-brain template to the native space. The isolated cerebellum is then normalized into the spatially unbiased atlas (SUIT) space using anatomical information derived from the previous step. Finally, the damage is detected in the atlas space by comparing the normalized cerebellum and the SUIT template.

We evaluated our damage detection tool on postoperative scans of 153 patients with medulloblastoma based on inspection by human experts. We also designed a simulation to evaluate performance without human intervention and with an explicitly controlled and defined ground truth. Our results show that the approach performs adequately under various realistic conditions.

We develop an accurate, robust, and fully automatic localization and measurement of cerebellar damage in the atlas space using postoperative MRI.