Prior studies show differences in empathy and affect-recognition ability between those with autism spectrum disorder (ASD) and typically developing (TD) individuals. Autistic individuals also exhibit increased behavioral, gastrointestinal, and sleep issues. In the current study, we explored the differences in empathy and affect recognition between the ASD and TD groups; and we investigated their associations with conditions co-occurring in ASD. A total of 54 TD and 56 ASD children (8–17 years) were included. As compared to the TD group, the ASD group showed lower scores for affect recognition and perspective taking (PT) and higher scores for personal distress (PD). Interestingly, results from hierarchical linear regressions suggested that disparities in the PD and PT between the groups were primarily attributable to attenuated levels of alexithymia, rather than being mediated by the presence of an autism diagnosis. Differences in affect-recognition ability, however, were mediated by both an autism diagnosis and alexithymia. We also found significant correlations between empathy and affect recognition and measures of related conditions common in ASD. Alexithymia, hence, contributes to difficulties in empathy while both alexithymia and autism are associated with affect-recognition ability in ASD. Additionally, the association between affect recognition and empathic ability with co-occurring conditions in ASD needs to be considered during assessments and interventions.

Accurate stroke lesion segmentation is essential for large-scale neuroimaging studies, yet manual delineation remains labor-intensive, and existing automated methods often struggle to generalize across imaging protocols and stages of recovery. We developed MAESTRO, a deep learning framework for automated lesion segmentation across the stroke recovery continuum using T1-weighted (T1) MRI alone. We hypothesized that combining a transformer-based architecture with an image augmentation strategy would improve segmentation accuracy and robustness under heterogeneous imaging conditions. T1 MRI scans and expert-traced lesion masks from 955 stroke participants across 33 international cohorts were used to train and evaluate MAESTRO within the open-source nnU-Net framework. Performance was evaluated on a held-out test set using spatial and volumetric agreement metrics. An exploratory human-in-the-loop (HITL) evaluation compared correction of MAESTRO-generated segmentations with manual tracing from scratch. MAESTRO achieved the strongest performance across several evaluated model configurations, providing the most accurate lesion localization and lesion volume estimates (median Dice = 0.686; Pearson r = 0.861; ICC = 0.792). Segmentation performance was sensitive to lesion size and stroke chronicity but remained robust across diverse imaging conditions. Additionally, using a HITL workflow to correct MAESTRO segmentations reduced annotation time by 47.4% compared to manual tracing while improving accuracy relative to both automated and manual workflows. MAESTRO is publicly available to enable robust, automated stroke lesion segmentation from T1 MRI. When combined with human review and correction, MAESTRO offers a practical approach for generating standardized, high-quality lesion annotations, helping reduce a major barrier to large-scale stroke imaging studies.