Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Van Nguyen, Phi, Trinh, Ngoc Huynh, Nguyen, Duy Minh Lam, Nguyen, Phu Loc, Tran, Quoc Long
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914449696227328
author Van Nguyen, Phi
Trinh, Ngoc Huynh
Nguyen, Duy Minh Lam
Nguyen, Phu Loc
Tran, Quoc Long
author_facet Van Nguyen, Phi
Trinh, Ngoc Huynh
Nguyen, Duy Minh Lam
Nguyen, Phu Loc
Tran, Quoc Long
contents Quantifying aleatoric uncertainty in medical image segmentation is critical since it is a reflection of the natural variability observed among expert annotators. A conventional approach is to model the segmentation distribution using the generative model, but current methods limit the expression ability of generative models. While current diffusion-based approaches have demonstrated impressive performance in approximating the data distribution, their inherent stochastic sampling process and inability to model exact densities limit their effectiveness in accurately capturing uncertainty. In contrast, our proposed method leverages conditional flow matching, a simulation-free flow-based generative model that learns an exact density, to produce highly accurate segmentation results. By guiding the flow model on the input image and sampling multiple data points, our approach synthesizes segmentation samples whose pixel-wise variance reliably reflects the underlying data distribution. This sampling strategy captures uncertainties in regions with ambiguous boundaries, offering robust quantification that mirrors inter-annotator differences. Experimental results demonstrate that our method not only achieves competitive segmentation accuracy but also generates uncertainty maps that provide deeper insights into the reliability of the segmentation outcomes. The code for this paper is freely available at https://github.com/huynhspm/Data-Uncertainty
format Preprint
id arxiv_https___arxiv_org_abs_2507_22418
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching
Van Nguyen, Phi
Trinh, Ngoc Huynh
Nguyen, Duy Minh Lam
Nguyen, Phu Loc
Tran, Quoc Long
Computer Vision and Pattern Recognition
Artificial Intelligence
Quantifying aleatoric uncertainty in medical image segmentation is critical since it is a reflection of the natural variability observed among expert annotators. A conventional approach is to model the segmentation distribution using the generative model, but current methods limit the expression ability of generative models. While current diffusion-based approaches have demonstrated impressive performance in approximating the data distribution, their inherent stochastic sampling process and inability to model exact densities limit their effectiveness in accurately capturing uncertainty. In contrast, our proposed method leverages conditional flow matching, a simulation-free flow-based generative model that learns an exact density, to produce highly accurate segmentation results. By guiding the flow model on the input image and sampling multiple data points, our approach synthesizes segmentation samples whose pixel-wise variance reliably reflects the underlying data distribution. This sampling strategy captures uncertainties in regions with ambiguous boundaries, offering robust quantification that mirrors inter-annotator differences. Experimental results demonstrate that our method not only achieves competitive segmentation accuracy but also generates uncertainty maps that provide deeper insights into the reliability of the segmentation outcomes. The code for this paper is freely available at https://github.com/huynhspm/Data-Uncertainty
title Aleatoric Uncertainty Medical Image Segmentation Estimation via Flow Matching
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2507.22418