Oliveira-Stahl, G;
Schroder, A;
Moggridge, J;
Salhab, HA;
Micallef, C;
Barnes, J;
Cardoso, MJ;
... Grech-Sollars, M; + view all
(2026)
Evaluation of Uncertainty-Aware Multi-software Ensembles for Hippocampal Segmentation.
In: Sudre, Carole H and Hoque, Mobarak I and Mehta, Raghav and Ouyang, Cheng and Qin, Chen and Rakic, Marianne and Wells, William M, (eds.)
Uncertainty for Safe Utilization of Machine Learning in Medical Imaging. UNSURE 2025.
(pp. 45-55).
Springer Nature Switzerland: Cham, Switzerland.
(In press).
![[thumbnail of Anonymized_MICCAI_2025 - Gabriel.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) |
Text
Anonymized_MICCAI_2025 - Gabriel.pdf - Submitted Version Access restricted to UCL open access staff until 30 September 2026. Download (2MB) |
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.
Archive Staff Only
 |
View Item |
