Individualized Cerebellar Damage Predicts the Behavioral Disorders in Children with Brainstem Tumors

Background and PurposeBrainstem tumors are rare but cause enduring behavioral issues, challenging patients and surgeons. Research on cerebellar changes in these patients limited, despite symptoms similar to cerebellar injuries. This study aims to investigate cerebellar damage pattern resulting from brainstem tumors and its association with behavioral disorders. MethodsIn this study, a U-Net-based segmentation algorithm was used to divide the cerebellum into 26 lobules, which were then used to build a normative model for assessing individual structural deviations. Furthermore, a behavior prediction model was developed using the total outlier count (tOC) index and brain volume as predictive features. ResultsMost patients were found to have negative deviations in cerebellar regions, particularly in anterior lobules like Left V. Higher tOC was significantly associated with severe social problems (r = 0.31, p = 0.001) and withdrawal behavior (r = 0.28, p = 0.001). Smaller size of cerebellar regions strongly correlated with more pronounced social problems (r = 0.27, p = 0.007) and withdrawal behavior (r = 0.25, p = 0.015). Notably, lobules Right X, V, IV, VIIB, Left IX, VIII, and X influenced social problems, while Left V, Right IV, Vermis VI, and VIII impacted withdrawal behavior. ConclusionsOur study revealed cerebellar damage patterns in patients with brainstem tumors, emphasizing the role of both anterior and posterior cerebellar lobes in social problems and withdrawal behavior. This research sheds light on the brain mechanisms underlying complex behavioral disorders in brainstem tumor patients.