ECSNN: Spiking Neural Networks for Efficient Exposure Correction in Endoscopy Imaging

Abstract

The quality of endoscopic images is critical to the success of polyp segmentation, highlighting the need for accurate exposure correction in endoscopy. While traditional deep learning methods are effective, they demand substantial computational resources during inference. To address this, we propose the Endoscopic Exposure Correction Spiking Neural Network (ECSNN), an efficient framework designed for resource-limited devices. Our approach features a Positive Incentive Learning Module that reduces noise in input images. These enhanced features are then processed by U-Shape Networks (USNet), which leverages spiking neural networks to learn deep representations for exposure correction. Additionally, we introduce a Brightness Prompt Module consisting of two components: the Brightness Spike Encoding Module (BSEM), which encodes brightness information into spike signals, and the Brightness-Aware Prompt Block (BAPB), which adjusts exposure by guiding the network through brightness-aware attention. We evaluate ECSNN on the Endo4IE and ECSEG datasets, where it outperforms six state-of-the-art methods and demonstrates its practical utility in clinical diagnosis.