A Real-time Endoscopic Image Denoising System

2025-06-18

AI Summary

To address severe mixed noise—arising from small photosensitive area (<1 mm × 1 mm), limited dynamic range, and analog circuit noise—in ultra-miniaturized, single-use endoscopic imaging sensors, this paper establishes, for the first time, a unified physical noise model tailored to medical analog image sensors, encompassing fixed-pattern noise, periodic banding noise, and Poisson–Gaussian mixed noise. We propose a lightweight hybrid denoising architecture synergizing classical signal processing and deep learning: integrating physics-driven noise modeling, adaptive frequency-domain filtering, and a compact CNN. Deployed on an FPGA for edge-side real-time inference (≥30 fps), the method achieves a PSNR improvement of 11.89 dB (from 21.16 to 33.05) on the test set. It effectively suppresses mixed noise while preserving fine texture details and color fidelity, fulfilling clinical requirements for real-time endoscopic video stream processing.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Medical and Biological Imaging

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Browser and end-point security

Abstract

Endoscopes featuring a miniaturized design have significantly enhanced operational flexibility, portability, and diagnostic capability while substantially reducing the invasiveness of medical procedures. Recently, single-use endoscopes equipped with an ultra-compact analogue image sensor measuring less than 1mm x 1mm bring revolutionary advancements to medical diagnosis. They reduce the structural redundancy and large capital expenditures associated with reusable devices, eliminate the risk of patient infections caused by inadequate disinfection, and alleviate patient suffering. However, the limited photosensitive area results in reduced photon capture per pixel, requiring higher photon sensitivity settings to maintain adequate brightness. In high-contrast medical imaging scenarios, the small-sized sensor exhibits a constrained dynamic range, making it difficult to simultaneously capture details in both highlights and shadows, and additional localized digital gain is required to compensate. Moreover, the simplified circuit design and analog signal transmission introduce additional noise sources. These factors collectively contribute to significant noise issues in processed endoscopic images. In this work, we developed a comprehensive noise model for analog image sensors in medical endoscopes, addressing three primary noise types: fixed-pattern noise, periodic banding noise, and mixed Poisson-Gaussian noise. Building on this analysis, we propose a hybrid denoising system that synergistically combines traditional image processing algorithms with advanced learning-based techniques for captured raw frames from sensors. Experiments demonstrate that our approach effectively reduces image noise without fine detail loss or color distortion, while achieving real-time performance on FPGA platforms and an average PSNR improvement from 21.16 to 33.05 on our test dataset.

Problem

• Reduces noise in endoscopic images from small sensors
• Addresses fixed-pattern, banding, and Poisson-Gaussian noise types
• Ensures real-time denoising without detail or color loss

Innovation

• Developed comprehensive noise model for endoscopes
• Proposed hybrid denoising system combining algorithms
• Achieved real-time performance on FPGA platforms