Evidential DualUNet: Single-Pass Uncertainty for Cell Instance Segmentation

David Anglada-Rotger, Ferran Marques, Montse Pardàs

Keywords: Cell Instance Segmentation, Evidential Deep Learning, Uncertainty Estimation, Multitask Learning, Nuclei Segmentation

Abstract: Accurate and trustworthy cell instance segmentation requires models that not only detect and classify nuclei but also communicate how much evidence supports each prediction. DualU-Net is a fast and effective two-head multi-task architecture for this problem, but—like most deterministic models—it provides no principled uncertainty estimates. We introduce \emph{Evidential DualU-Net}, the first evidential framework for multi-task cell instance segmentation. Its segmentation head predicts Dirichlet concentration parameters, enabling single-pass, closed-form aleatoric, epistemic, and vacuity uncertainties at both pixel and instance level, while its centroid decoder is complemented with two lightweight geometric uncertainty cues that quantify localisation reliability without auxiliary models or sampling. Together, these evidential and geometric measures expose complementary failure modes and allow principled filtering of low-confidence nuclei. Across multi-tissue and multi-stain datasets, Evidential DualU-Net matches or surpasses deep ensembles in error separation at a fraction of the cost, maintains or improves calibration over deterministic baselines, and generalises across datasets without retuning. This work provides an interpretable and computationally practical uncertainty formulation for digital pathology. Code and weights are available at: https://github.com/davidanglada/Evidential-DualU-Net.

Primary Subject Area: Uncertainty Estimation

Secondary Subject Area: Segmentation

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 285