BiSe-Unet: A Lightweight Dual-path U-Net with Attention-refined Context for Real-time Medical Image Segmentation

TL;DR

BiSe-UNet is a lightweight, dual-path U-Net model with attention mechanisms designed for real-time medical image segmentation on resource-constrained devices, achieving high accuracy and speed in endoscopic polyp detection.

Contribution

This paper introduces BiSe-UNet, a novel lightweight dual-path U-Net architecture with attention refinement, optimized for real-time deployment in resource-limited medical imaging scenarios.

Findings

Achieves over 30 FPS on Raspberry Pi 5.

Maintains competitive Dice and IoU scores.

Demonstrates effective real-time segmentation in endoscopy.

Abstract

During image-guided procedures, real-time image segmentation is often required. This demands lightweight AI models that can operate on resource-constrained devices. One important use case is endoscopy-guided colonoscopy, where polyps must be detected in real time. The Kvasir-Seg dataset, a publicly available benchmark for this task, contains 1,000 high-resolution endoscopic images of polyps with corresponding pixel-level segmentation masks. Achieving real-time inference speed for clinical deployment in constrained environments requires highly efficient and lightweight network architectures. However, many existing models remain too computationally intensive for embedded deployment. Lightweight architectures, although faster, often suffer from reduced spatial precision and weaker contextual understanding, leading to degraded boundary quality and reduced diagnostic reliability. To address these challenges, we introduce BiSe-UNet, a lightweight dual-path U-Net that integrates an attention-refined context path with a shallow spatial path for detailed feature preservation, followed by a depthwise separable decoder for efficient reconstruction. Evaluated on the Kvasir-Seg dataset, BiSe-UNet achieves competitive Dice and IoU scores while sustaining real-time throughput exceeding 30 FPS on Raspberry Pi 5, demonstrating its effectiveness for accurate, lightweight, and deployable medical image segmentation on edge hardware.