Evaluation of Uncertainty-Aware Multi-Software Ensembles for Hippocampal Segmentation

Gabriel Oliveira-Stahl, Anna Schroder, James Moggridge, Hamza A. Salhab, Caroline Micallef, Josephine Barnes, M. Jorge Cardoso, Carole H. Sudre, Matthew Grech-Sollars

Keywords: Uncertainty estimation · Ensemble · Hippocampal segmentation · Carbon footprint.

Abstract:

Accurate hippocampal segmentation can be a useful tool for
diagnosing and monitoring neurological conditions such as Alzheimer’s
disease and epilepsy. While numerous automated segmentation methods
exist, their clinical adoption remains limited. Reliable uncertainty assessment
can enhance trust and facilitate clinical translation. This study
evaluates five heterogeneous hippocampal segmentation methods — InnerEye,
ASHS, FastSurfer, HippoSeg, and FreeSurfer — across two dementia
datasets and one epilepsy dataset. The sub-ensemble containing
InnerEye, FastSurfer, and HippoSeg emerged as both accurate and efficient,
highlighting the feasibility of balancing computational cost and
performance. Additionally, ensemble-derived uncertainty quantification
with sample variance, mutual information, and predictive entropy is
shown to reduce inaccurate segmentations by flagging low-confidence
cases, potentially providing a mechanism for automatically escalating
ambiguous cases for expert assessment.

Submission Number: 5