Peripheral prototypical contrastive loss for supervised medical image segmentation
Abstract
Robust segmentation of biomedical images remains challenging primarily due to ill-defined object boundaries. Although several loss functions have recently been proposed to enhance object boundary recognition, concerns remain about the susceptibility to unstable annotations resulting from boundary ambiguities. Here, we introduce the Peripheral Prototypical Contrastive (PPC) loss, which leverages prototypical contrastive learning to improve boundary recognition and enable stable training even under noisy annotation conditions. The PPC loss utilizes prototype features obtained from local regions near object boundaries, focusing specifically on ambiguous areas that have been challenging for existing approaches. Extensive experiments across multiple datasets demonstrated that the PPC loss consistently improve segmentation performance even under conditions with noisy labels. A newly proposed strategy, which adaptively determines the local region for prototype calculation, enhanced robustness and outperformed existing methods. Our findings indicate the potential of the PPC loss in facilitating scalable and reliable medical image segmentation, including the development of foundation models with imperfect annotations.
Versions
Related
- Lyman Break Galaxy selection and redshift measurement with supervised contrastive learning
- Sam-Correction: Fully Adaptive Label Noise Reduction for Medical Image Segmentation
- Extreme anharmonicity determines the superionic transition in the prototypical antifluorite Li2O
- Unsupervised and probabilistic learning with Contrastive Local Learning Networks: The Restricted Kirchhoff Machine
- SelfTICA: contrastive learning of dynamical representations for rare-event sampling and characterization
BibTeX
@misc{shimaya2026peripheral,
title = {{Peripheral prototypical contrastive loss for supervised medical image segmentation}},
author = {Takuro Shimaya and Ryosaku Shino and Masahiro Saiko},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.02305},
eprint = {2611.02305},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.02305},
}
RIS
TY - UNPB
TI - Peripheral prototypical contrastive loss for supervised medical image segmentation
AU - Takuro Shimaya
AU - Ryosaku Shino
AU - Masahiro Saiko
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.02305
UR - https://arxiv.org/abs/2611.02305
AB - Robust segmentation of biomedical images remains challenging primarily due to ill-defined object boundaries. Although several loss functions have recently been proposed to enhance object boundary recognition, concerns remain about the susceptibility to unstable annotations resulting from boundary ambiguities. Here, we introduce the Peripheral Prototypical Contrastive (PPC) loss, which leverages prototypical contrastive learning to improve boundary recognition and enable stable training even under noisy annotation conditions. The PPC loss utilizes prototype features obtained from local regions near object boundaries, focusing specifically on ambiguous areas that have been challenging for existing approaches. Extensive experiments across multiple datasets demonstrated that the PPC loss consistently improve segmentation performance even under conditions with noisy labels. A newly proposed strategy, which adaptively determines the local region for prototype calculation, enhanced robustness and outperformed existing methods. Our findings indicate the potential of the PPC loss in facilitating scalable and reliable medical image segmentation, including the development of foundation models with imperfect annotations.
ER -