Customized CycleGAN with balanced skip-networked residual layer (CCGAN-BSNRL) to enhance colonoscopy image by narrow-band imaging translation
Open Access
- 12 August 2026
- journal article
- Published by The Royal Society in Royal Society Open Science
- Vol. 13 (8)
Abstract
Colonoscopy can achieve significantly enhanced polyp detection by employing narrowband imaging (NBI) along with conventional white light (WL) imaging. However, problems associated with switching between two modalities during colonoscopy hinder its widespread clinical application. This study proposes a novel skip-connected residual layer-based customized CycleGAN model, which we refer to as customized CycleGAN with balanced skip-networked residual layer (CCGAN-BSNRL), for achieving an effective translation of WL colonoscopy images into NBI-like images. We chose the residual layer for customization as it is crucial for capturing the core spatial features of the input and translating them into the target domain. To evaluate, we have chosen a set of existing metrics to compare images generated by our model with images generated by other related models. We additionally propose those metrics for the comprehensive evaluation of other generative models’ generated images. Finally, a simple segmentation model is used to inspect the improvement in polyp detection. Considering the overall results, with a significantly enhanced detection of polyps achieved through the translated NBI (Dice score greater than 6%, Jaccard score greater than 8%, on average) from the proposed model, it is expected that the CCGAN-BSNRL model should positively impact the diagnosis accuracy of colorectal cancer in clinical applications.Keywords
Funding Information
- New Frontiers in Research Fund
This publication has 37 references indexed in Scilit:
- NBIGAN: Automatic nasopharyngeal white light and narrow band imaging transformation based on feature aggregation and perceptual generative adversarial networksExpert Systems with Applications, 2025
- DC-cycleGAN: Bidirectional CT-to-MR synthesis from unpaired dataComputerized Medical Imaging and Graphics, 2023
- Anatomical evaluation of deep-learning synthetic computed tomography images generated from male pelvis cone-beam computed tomographyPhysics and Imaging in Radiation Oncology, 2023
- PISDGAN: Perceive image structure and details for laryngeal image enhancementBiomedical Signal Processing and Control, 2022
- Image translation for medical image generation: Ischemic stroke lesion segmentationBiomedical Signal Processing and Control, 2022
- Narrow band imaging versus white light for detecting sessile serrated lesion: A prospective randomized multicenter studyDEN Open, 2021
- SoftSeg: Advantages of soft versus binary training for image segmentationMedical Image Analysis, 2021
- TSIT: A Simple and Versatile Framework for Image-to-Image Translation2020
- Computer-aided diagnosis of laryngeal cancer via deep learning based on laryngoscopic imagesEBioMedicine, 2019
- The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observationsColor Research & Application, 2004