A Dual-Generalization Low-Light Enhancement Framework for Capsule Endoscopy Image Restoration and Segmentation
- 25 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (5) , 1747-1762
Abstract
In recent years, deep learning technology has automated the diagnosis of gastrointestinal (GI) tract disease, enabling doctor-machine collaborative diagnosis. However, the images captured by wireless capsule endoscopy (WCE) easily suffer from varying brightness levels of low-light degradation due to the complex structure of GI tract and the limitations of the light source, which impacts both human and machine diagnostic accuracy. Moreover, images may contain varying degrees of structural and semantic details even under a similar brightness level, which still can compromise segmentation accuracy. To address these issues, we propose a dual-generalization framework for low-light WCE images. Our framework includes an Image Guidance and Laplacian Fusion Module (IGLFM), a Brightness Level Generalization Module (BLGM) and a Wavelet Segmentation Generalization Module (WSGM). IGLFM and BLGM can restore low-light images across different brightness levels and WSGM can enhance segmentation accuracy by generalizing the varying degrees of details across images. With BLGM and WSGM, our framework enables two aspects of generalization: generalization to input images with different brightness levels and generalization to images with varying detail levels. Extensive experiments demonstrate that our method achieves significant performance under varying brightness levels and improvements in segmentation accuracy, surpassing the existing state-of-the-art (SOTA) method with gains of 4.70 dB / 0.022 (PSNR/SSIM) on Kvasir-Capsule dataset and 1.61 dB / 0.018 on RLE dataset. WSGM consistently improves segmentation accuracy across six popular networks, achieving up to +4.7% mIoU and +5.3% Dice improvements on RLE dataset. Our code will be available at https://github.com/superwsc/Dual-Gen-Frame.Keywords
Funding Information
- China NSF (62427801)
- China NSF (62031009)
- National Key Research and Development Program of China (2023YFB4502802)
- Fudan-Zhongxing Telecom Equipment (ZTE) Joint Laboratory
- Guangxi Key Research and Development Program
This publication has 67 references indexed in Scilit:
- RetiDiff: Diffusion-Based Synthesis of Retinal OCT Images for Enhanced Segmentation2025
- LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion2023
- Colorectal endoscopic image enhancement via unsupervised deep learningMultimedia Tools and Applications, 2023
- Learning to Adapt to LightInternational Journal of Computer Vision, 2023
- Learning Enriched Features for Real Image Restoration and Enhancement2020
- An automatic framework for endoscopic image restoration and enhancementApplied Intelligence, 2020
- Adaptive Context Selection for Polyp Segmentation2020
- A Deep Learning Approach for Red Lesions Detection in Video Capsule Endoscopies2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observationsColor Research & Application, 2004