DE-KAN: A Kolmogorov Arnold Network with Dual Encoder for accurate 2D Teeth Segmentation

TL;DR

DE-KAN introduces a dual encoder network utilizing Kolmogorov Arnold representation for precise 2D teeth segmentation, significantly outperforming existing models on benchmark dental datasets.

Contribution

The paper presents a novel dual encoder architecture with Kolmogorov Arnold-based layers, enhancing feature extraction and segmentation accuracy in dental radiographs.

Findings

Achieved 94.5% mIoU on benchmark datasets.

Improved Dice coefficient by up to 4.7%.

Outperformed state-of-the-art models in teeth segmentation.

Abstract

Accurate segmentation of individual teeth from panoramic radiographs remains a challenging task due to anatomical variations, irregular tooth shapes, and overlapping structures. These complexities often limit the performance of conventional deep learning models. To address this, we propose DE-KAN, a novel Dual Encoder Kolmogorov Arnold Network, which enhances feature representation and segmentation precision. The framework employs a ResNet-18 encoder for augmented inputs and a customized CNN encoder for original inputs, enabling the complementary extraction of global and local spatial features. These features are fused through KAN-based bottleneck layers, incorporating nonlinear learnable activation functions derived from the Kolmogorov Arnold representation theorem to improve learning capacity and interpretability. Extensive experiments on two benchmark dental X-ray datasets demonstrate that DE-KAN outperforms state-of-the-art segmentation models, achieving mIoU of 94.5%, Dice coefficient of 97.1%, accuracy of 98.91%, and recall of 97.36%, representing up to +4.7% improvement in Dice compared to existing methods.