# MEGAN: Mixture of Experts for Robust Uncertainty Estimation in Endoscopy Videos

arXiv: https://arxiv.org/abs/2509.12772 · HTML: https://mlsanity.com/paper/2509.12772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts.
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Placed in

- Mixture-of-experts / [Medical and biomedical MoE](https://mlsanity.com/moe/medical-and-biomedical-moe/)

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train](https://mlsanity.com/paper/2306.16741/) (2023)
- [TBraTS: Trusted Brain Tumor Segmentation](https://mlsanity.com/paper/2206.09309/) (2022)
- [Quantifying and Leveraging Predictive Uncertainty for Medical Image Assessment](https://mlsanity.com/paper/2007.04258/) (2020)
- [Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment](https://mlsanity.com/paper/1906.07775/) (2019)
- [Self-Supervised Learning for Endoscopic Video Analysis](https://mlsanity.com/paper/2308.12394/) (2023)
- [Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection](https://mlsanity.com/paper/2203.12121/) (2022)
- [Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation](https://mlsanity.com/paper/2202.05167/) (2022)
- [EndoDINO: A Foundation Model for GI Endoscopy](https://mlsanity.com/paper/2501.05488/) (2025)
- [Evidential segmentation of 3D PET/CT images](https://mlsanity.com/paper/2104.13293/) (2021)
- [Automatic Estimation of Ulcerative Colitis Severity from Endoscopy Videos using Ordinal Multi-Instance Learning](https://mlsanity.com/paper/2109.14685/) (2021)
- [Arges: Spatio-Temporal Transformer for Ulcerative Colitis Severity Assessment in Endoscopy Videos](https://mlsanity.com/paper/2410.00536/) (2024)

## Abstract (arXiv)

Reliable uncertainty quantification (UQ) is essential in medical AI. Evidential Deep Learning (EDL) offers a computationally efficient way to quantify model uncertainty alongside predictions, unlike traditional methods such as Monte Carlo (MC) Dropout and Deep Ensembles (DE). However, all these methods often rely on a single expert's annotations as ground truth for model training, overlooking the inter-rater variability in healthcare. To address this issue, we propose MEGAN, a Multi-Expert Gating Network that aggregates uncertainty estimates and predictions from multiple AI experts via EDL models trained with diverse ground truths and modeling strategies. MEGAN's gating network optimally combines predictions and uncertainties from each EDL model, enhancing overall prediction confidence and calibration. We extensively benchmark MEGAN on endoscopy videos for Ulcerative colitis (UC) disease severity estimation, assessed by visual labeling of Mayo Endoscopic Subscore (MES), where inter-rater variability is prevalent. In large-scale prospective UC clinical trial, MEGAN achieved a 3.5% improvement in F1-score and a 30.5% reduction in Expected Calibration Error (ECE) compared to existing methods. Furthermore, MEGAN facilitated uncertainty-guided sample stratification, reducing the annotation burden and potentially increasing efficiency and consistency in UC trials.