Multi-Rater Calibrated Segmentation Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Riera-Marín, Meritxell, López, Javier García, Rodríguez-Comas, Júlia, Ballester, Miguel A. González, Galdran, Adrian
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914527724961792
author Riera-Marín, Meritxell
López, Javier García
Rodríguez-Comas, Júlia
Ballester, Miguel A. González
Galdran, Adrian
author_facet Riera-Marín, Meritxell
López, Javier García
Rodríguez-Comas, Júlia
Ballester, Miguel A. González
Galdran, Adrian
contents Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a problem exacerbated when multiple expert annotations exhibit substantial disagreement. While inter-rater variability is typically treated as noise, it provides valuable information about intrinsic annotation ambiguity that must be reflected in model confidence. Methods: We improve the probabilistic calibration of medical image segmentation models by reformulating multi-rater supervision as an ordinal learning problem. Voxel-wise annotator agreement is treated as an ordered target, linking predictive confidence to the empirical variability in training data. This formulation allows the use of ordinal-aware scoring rules, such as the Ranked Probability Score ordinal loss, combined with a standard binary objective to preserve discriminative performance. Results: We evaluated the proposed approach across four public segmentation benchmarks spanning ophthalmology, histopathology, and thoracic imaging. Calibration was assessed using a multi-rater extension of expected calibration error. Results consistently show that ordinal-aware training yields substantially improved calibration with respect to inter-rater agreement without degrading segmentation accuracy. Conclusions: Treating multi-rater annotations as ordered information provides a principled and architecture-agnostic route to more reliable probabilistic segmentation models.
format Preprint
id arxiv_https___arxiv_org_abs_2605_02437
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Rater Calibrated Segmentation Models
Riera-Marín, Meritxell
López, Javier García
Rodríguez-Comas, Júlia
Ballester, Miguel A. González
Galdran, Adrian
Computer Vision and Pattern Recognition
Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a problem exacerbated when multiple expert annotations exhibit substantial disagreement. While inter-rater variability is typically treated as noise, it provides valuable information about intrinsic annotation ambiguity that must be reflected in model confidence. Methods: We improve the probabilistic calibration of medical image segmentation models by reformulating multi-rater supervision as an ordinal learning problem. Voxel-wise annotator agreement is treated as an ordered target, linking predictive confidence to the empirical variability in training data. This formulation allows the use of ordinal-aware scoring rules, such as the Ranked Probability Score ordinal loss, combined with a standard binary objective to preserve discriminative performance. Results: We evaluated the proposed approach across four public segmentation benchmarks spanning ophthalmology, histopathology, and thoracic imaging. Calibration was assessed using a multi-rater extension of expected calibration error. Results consistently show that ordinal-aware training yields substantially improved calibration with respect to inter-rater agreement without degrading segmentation accuracy. Conclusions: Treating multi-rater annotations as ordered information provides a principled and architecture-agnostic route to more reliable probabilistic segmentation models.
title Multi-Rater Calibrated Segmentation Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.02437