FunKAN: Functional Kolmogorov-Arnold Network for Medical Image Enhancement and Segmentation

• URL: http://arxiv.org/abs/2509.13508v1
• Date: Tue, 16 Sep 2025 20:13:48 GMT
• Title: FunKAN: Functional Kolmogorov-Arnold Network for Medical Image Enhancement and Segmentation
• Authors: Maksim Penkin, Andrey Krylov,
• Abstract summary: Functional Kolmogorov-Arnold Network (FunKAN) is a novel interpretable neural framework for image processing.<n>FunKAN generalizes the Kolmogorov-Arnold representation theorem onto functional spaces and learns inner functions.<n>Our work bridges the gap between theoretical function approximation and medical image analysis, offering a robust, interpretable solution for clinical applications.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical image enhancement and segmentation are critical yet challenging tasks in modern clinical practice, constrained by artifacts and complex anatomical variations. Traditional deep learning approaches often rely on complex architectures with limited interpretability. While Kolmogorov-Arnold networks offer interpretable solutions, their reliance on flattened feature representations fundamentally disrupts the intrinsic spatial structure of imaging data. To address this issue we propose a Functional Kolmogorov-Arnold Network (FunKAN) -- a novel interpretable neural framework, designed specifically for image processing, that formally generalizes the Kolmogorov-Arnold representation theorem onto functional spaces and learns inner functions using Fourier decomposition over the basis Hermite functions. We explore FunKAN on several medical image processing tasks, including Gibbs ringing suppression in magnetic resonance images, benchmarking on IXI dataset. We also propose U-FunKAN as state-of-the-art binary medical segmentation model with benchmarks on three medical datasets: BUSI (ultrasound images), GlaS (histological structures) and CVC-ClinicDB (colonoscopy videos), detecting breast cancer, glands and polyps, respectively. Experiments on those diverse datasets demonstrate that our approach outperforms other KAN-based backbones in both medical image enhancement (PSNR, TV) and segmentation (IoU, F1). Our work bridges the gap between theoretical function approximation and medical image analysis, offering a robust, interpretable solution for clinical applications.

Related papers

• A hybrid Kolmogorov-Arnold network for medical image segmentation [6.69087470775851]
  We propose U-KABS, a novel framework that integrates the expressive power of Kolmogorov-shaped Networks (KANs) with a U-grained encoder-decoder architecture to enhance segmentation performance.
  arXiv  Detail & Related papers  (2026-02-07T21:00:38Z)
• Large Language Model Evaluated Stand-alone Attention-Assisted Graph Neural Network with Spatial and Structural Information Interaction for Precise Endoscopic Image Segmentation [16.773882069530426]
  We propose FOCUS-Med, which stands for Fusion of spatial and structural graph with attentional context-aware polyp segmentation.<n> FOCUS-Med integrates a Dual Graph Convolutional Network (Dual-GCN) module to capture contextual spatial and topological structural dependencies.<n>Experiments on public benchmarks demonstrate that FOCUS-Med achieves state-of-the-art performance across five key metrics.
  arXiv  Detail & Related papers  (2025-08-09T15:53:19Z)
• Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation [56.52520416420957]
  We propose Multimodal Causal-Driven Representation Learning (MCDRL) to tackle domain generalization in medical image segmentation.<n>MCDRL consistently outperforms competing methods, yielding superior segmentation accuracy and exhibiting robust generalizability.
  arXiv  Detail & Related papers  (2025-08-07T03:41:41Z)
• RadIR: A Scalable Framework for Multi-Grained Medical Image Retrieval via Radiology Report Mining [64.66825253356869]
  We propose a novel methodology that leverages dense radiology reports to define image-wise similarity ordering at multiple granularities.<n>We construct two comprehensive medical imaging retrieval datasets: MIMIC-IR for Chest X-rays and CTRATE-IR for CT scans.<n>We develop two retrieval systems, RadIR-CXR and model-ChestCT, which demonstrate superior performance in traditional image-image and image-report retrieval tasks.
  arXiv  Detail & Related papers  (2025-03-06T17:43:03Z)
• MedFuncta: Modality-Agnostic Representations Based on Efficient Neural Fields [1.931185411277237]
  We introduce MedFuncta, a modality-agnostic continuous data representation based on neural fields.<n>We demonstrate how to scale neural fields from single instances to large datasets by exploiting redundancy in medical signals.<n>We release a large-scale dataset of > 550k annotated neural fields to promote research in this direction.
  arXiv  Detail & Related papers  (2025-02-20T09:38:13Z)
• FAN-Unet: Enhancing Unet with vision Fourier Analysis Block for Biomedical Image Segmentation [5.318153305245246]
  We present FAN-UNet, a novel architecture that combines the strengths of Fourier Analysis Network (FAN)-based vision backbones and the U-Net architecture.<n>The proposed Vision-FAN layer integrates the FAN layer and self-attention mechanisms, leveraging Fourier analysis to enable the model to effectively capture both long-range dependencies and periodic relationships.
  arXiv  Detail & Related papers  (2024-11-28T07:53:47Z)
• K-Space-Aware Cross-Modality Score for Synthesized Neuroimage Quality Assessment [71.27193056354741]
  The problem of how to assess cross-modality medical image synthesis has been largely unexplored. We propose a new metric K-CROSS to spur progress on this challenging problem. K-CROSS uses a pre-trained multi-modality segmentation network to predict the lesion location.
  arXiv  Detail & Related papers  (2023-07-10T01:26:48Z)
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation [0.22843885788439805]
  Generative Adversarial Networks (GANs) can generate realistic but novel samples, and thus effectively cover the real image distribution. This thesis contains four GAN projects aiming to present such novel applications' clinical relevance in collaboration with physicians.
  arXiv  Detail & Related papers  (2021-06-03T15:08:14Z)
• Spatially Dependent U-Nets: Highly Accurate Architectures for Medical Imaging Segmentation [10.77039660100327]
  We introduce a novel deep neural network architecture that exploits the inherent spatial coherence of anatomical structures. Our approach is well equipped to capture long-range spatial dependencies in the segmented pixel/voxel space. Our method performs favourably to commonly used U-Net and U-Net++ architectures.
  arXiv  Detail & Related papers  (2021-03-22T10:37:20Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation Maximization [112.2628296775395]
  Clinical decision support using deep neural networks has become a topic of steadily growing interest. clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. We propose a novel decision explanation scheme based on CycleGAN activation which generates high-quality visualizations of classifier decisions even in smaller data sets.
  arXiv  Detail & Related papers  (2020-10-09T14:39:27Z)
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation [84.7571086566595]
  We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape. The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
  arXiv  Detail & Related papers  (2020-03-31T11:50:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.