SCKAN: Structural Consensus-based KAN Prototype Learning for Semi-Supervised Pancreas Segmentation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Yuqi, Chen, Yufei, Fu, Wei, Yue, Xiaodong, Li, Shuo
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913164115836928
author Liu, Yuqi
Chen, Yufei
Fu, Wei
Yue, Xiaodong
Li, Shuo
author_facet Liu, Yuqi
Chen, Yufei
Fu, Wei
Yue, Xiaodong
Li, Shuo
contents Accurate pancreas segmentation is critical for early cancer diagnosis, where annotation scarcity necessitates Semi-Supervised Learning (SSL). However, due to significant inter-sample morphological variability, existing SSL methods face severe generalizability limitations under sparse supervision, leading to the Supervision Bias problem. To address this, we propose Structural Consensus-based KAN Prototype Learning (SCKAN), which constructs the first cross-sample structural consensus learning with Kolmogorov-Arnold Networks (KANs), to achieve more generalizable and accurate segmentation. Specifically, SCKAN contains two key designs: Structure-constrained Prototype Consistency Learning (SPCL), which prompts unbiased structural representation by enforcing cross-sample consistency via prototype-level contrastive optimization, and Consensus-based Kolmogorov-Arnold Fusion (CKaF), which reduces morphology-specific bias by aggregating stable consensus and filtering sample-wise noise via KAN's adaptive B-spline nonlinearity. Extensive experiments on two public pancreas datasets demonstrate the effectiveness of SCKAN. Code is at https://github.com/rhodaliu17/SCKAN.
format Preprint
id arxiv_https___arxiv_org_abs_2605_27032
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SCKAN: Structural Consensus-based KAN Prototype Learning for Semi-Supervised Pancreas Segmentation
Liu, Yuqi
Chen, Yufei
Fu, Wei
Yue, Xiaodong
Li, Shuo
Computer Vision and Pattern Recognition
Accurate pancreas segmentation is critical for early cancer diagnosis, where annotation scarcity necessitates Semi-Supervised Learning (SSL). However, due to significant inter-sample morphological variability, existing SSL methods face severe generalizability limitations under sparse supervision, leading to the Supervision Bias problem. To address this, we propose Structural Consensus-based KAN Prototype Learning (SCKAN), which constructs the first cross-sample structural consensus learning with Kolmogorov-Arnold Networks (KANs), to achieve more generalizable and accurate segmentation. Specifically, SCKAN contains two key designs: Structure-constrained Prototype Consistency Learning (SPCL), which prompts unbiased structural representation by enforcing cross-sample consistency via prototype-level contrastive optimization, and Consensus-based Kolmogorov-Arnold Fusion (CKaF), which reduces morphology-specific bias by aggregating stable consensus and filtering sample-wise noise via KAN's adaptive B-spline nonlinearity. Extensive experiments on two public pancreas datasets demonstrate the effectiveness of SCKAN. Code is at https://github.com/rhodaliu17/SCKAN.
title SCKAN: Structural Consensus-based KAN Prototype Learning for Semi-Supervised Pancreas Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.27032