Search

Shape-based markers have entered the field of morphometric neuroimaging analysis as a second mainstay alongside conventional volumetric approaches. We aimed to assess the added value of shape description for the analysis of lesional and autoimmune temporal lobe epilepsy (TLE) focusing on hippocampus and amygdala. We retrospectively investigated MRI and clinical data from 65 patients with lesional TLE (hippocampal sclerosis (HS) and astrogliosis) and from 62 patients with limbic encephalitis (LE) with serologically proven autoantibodies. Surface reconstruction and volumetric segmentation were performed with FreeSurfer. For the shape analysis, we used BrainPrint, a tool that utilizes eigenvalues of the Laplace-Beltrami operator on triangular meshes to calculate intra-subject asymmetry. Psychometric tests of memory performance were ascertained, to evaluate clinical relevance of the shape descriptor. The potential benefit of shape in addition to volumetric information for classification was assessed by five-fold repeated cross validation and logistic regression. For the LE group, the best performing classification model consisted of a combination of volume and shape asymmetry (mean AUC = 0.728), the logistic regression model was significantly improved considering both modalities instead of just volume asymmetry. For lesional TLE, the best model only considered volumetric information (mean AUC = 0.867). Shape asymmetry of the hippocampus was largely associated with verbal memory performance only in LE patients (OR = 1.07, p = 0.02). For lesional TLE, shape description is robust, but redundant when compared to volumetric approaches. For LE, in contrast, shape asymmetry as a complementary modality significantly improves the detection of subtle morphometric changes and is further associated with memory performance, which underscores the clinical relevance of shape asymmetry as a novel imaging biomarker.