MedKamba: A Novel Approach Integrating State-Space Models and Fractional Kolmogorov–Arnold Networks for Medical Image Segmentation.

Amit Shakya, Akanksha Yadav, Rupesh Kumar, Lalit Sharma

Keywords: Medical Image Segmentation, State Space Models, Fractional KANs.

Abstract: Medical image segmentation plays a crucial role in healthcare, serving as a key step in diseases diagnosis and treatment planning. Convolutional neural networks (CNNs) are limited by their restricted receptive fields, whereas Transformer-based models suffer from quadratic computational cost. Recent advances such as Mamba, a selective state-space model with linear complexity, and its vision-oriented variant, the Visual State Space (VSS) models, have shown strong ability to capture long-range dependencies efficiently. How- ever, they still exhibits shortcomings in segmentation tasks, including loss of pixel-level structural information and inefficient channel utilization. To address this, we introduce VSSM based Local Aware Channel Enhancement (LACE) block, which incorporates local enhancement and channel attention to better preserve spatial detail. To this end we pro- posed MedKamba, a novel U-shaped segmentation approach that employs a hybrid enoder with CNNs–LACE block to effectively capture both local and global contextual informa- tion. While the U-Net backbone remains highly efficient, its traditional skip connections rely on simple scale-matched fusion, limiting cross-scale interaction. To overcome this, we redesign the skip connections using Fractional Kolmogorov–Arnold Networks (f -KANs) to generate channel-wise attention weights from features aggregated across multiple stages. Experiments on two benchmark datasets demonstrate that MedKamba consistently out- performs competing approaches and produces more visually accurate segmentation results.

Primary Subject Area: Segmentation

Secondary Subject Area: Detection and Diagnosis

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 142