A hybrid Kolmogorov-Arnold network for medical image segmentation

2026-02-07

AI Summary

This work addresses the limited capacity of existing methods to model fine-grained anatomical structures in medical image segmentation due to their inadequate representation of nonlinear relationships. To overcome this, we propose U-KABS, a novel framework that integrates Kolmogorov–Arnold Networks (KANs) into the U-Net architecture for the first time. U-KABS employs learnable activation functions based on Bernstein polynomials and B-splines, which enhance local detail representation while preserving global smoothness. Furthermore, it incorporates Squeeze-and-Excitation modules within skip connections to collaboratively refine feature representations. Extensive experiments demonstrate that U-KABS significantly outperforms strong baseline models across multiple medical image segmentation benchmarks, with particularly notable gains in tasks involving complex anatomical structures.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Deep Neural Architectures and Foundation Models
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Medical image segmentation plays a vital role in diagnosis and treatment planning, but remains challenging due to the inherent complexity and variability of medical images, especially in capturing non-linear relationships within the data. We propose U-KABS, a novel hybrid framework that integrates the expressive power of Kolmogorov-Arnold Networks (KANs) with a U-shaped encoder-decoder architecture to enhance segmentation performance. The U-KABS model combines the convolutional and squeeze-and-excitation stage, which enhances channel-wise feature representations, and the KAN Bernstein Spline (KABS) stage, which employs learnable activation functions based on Bernstein polynomials and B-splines. This hybrid design leverages the global smoothness of Bernstein polynomials and the local adaptability of B-splines, enabling the model to effectively capture both broad contextual trends and fine-grained patterns critical for delineating complex structures in medical images. Skip connections between encoder and decoder layers support effective multi-scale feature fusion and preserve spatial details. Evaluated across diverse medical imaging benchmark datasets, U-KABS demonstrates superior performance compared to strong baselines, particularly in segmenting complex anatomical structures.

Problem

• medical image segmentation
• non-linear relationships
• complexity
• variability
• anatomical structures

Innovation

• Kolmogorov-Arnold Network
• Bernstein polynomial
• B-spline
• medical image segmentation
• hybrid architecture