Deep Learning-based Super-resolution for High-definition Endoscopic Imaging: A Comparative Study
Journal: Journal of Clinical Medicine Research DOI: 10.32629/jcmr.v5i4.3321
Abstract
With the advancement of medical imaging technology, low-resolution and noisy endoscopic images often hinder accurate lesion identification. This study explores deep learning-based super-resolution for endoscopic images and compares it with traditional interpolation methods. The results show that deep learning significantly improves image resolution and restores fine details, particularly in complex textures and small lesions. Both quantitative and qualitative analyses reveal that deep learning outperforms traditional methods in image quality, detail recovery, and visual effects, enhancing the clinical application of endoscopic images and improving diagnostic accuracy.
Keywords
endoscopic image, super-resolution, deep learning, image quality, lesion detection
Full Text
PDF - Viewed/Downloaded: 0 TimesReferences
[1] Chen Jian, Zhang Zihao, Wang Ganhong, et al. Establishment of an Artificial Intelligence-Assisted System for Colonoscopy Quality Control Based on Different Deep Learning Architectures [J]. Chinese Journal of Medical Physics, 2024, 41(11): 1443-1452.
[2] Zhou Jielu, Lin Jiaxi, Zhu Jinzhou. Application of Artificial Intelligence in Endoscopic Diagnosis of Colorectal Tumors [J]. Chinese Medical Equipment, 2024, 39(09): 136-143.
[3] Wu Yahui, Zhu Shiqi, Wu Yudong, et al. Colonoscopy Image Classification System for Submucosal Colorectal Tumors and Polyps Based on Few-Shot Learning Algorithms [J]. Chinese Journal of Medical Physics, 2024, 41(07): 897-904.
[4] Chen Jian, Wang Jennie, Xia Kaijian, et al. Comparison of Deep Learning-Based Methods for Colonoscopy Image Segmentation and Classification of Colorectal Polyps [J]. Journal of Shanghai Jiao Tong University (Medical Science), 2024, 44(06): 762-772.
[5] Zhang Qiusheng, Lin Qi, Li Guanghua, et al. Research Progress on the Application of Deep Learning-Based Artificial Intelligence Technology in Gastric Cancer [J]. Digestive Tumor Journal (Electronic Edition), 2024, 16(02): 223-230.
[6] Yao Hanmin. Preprocessing and Assisted Diagnosis of Esophageal Lesion Images Based on Deep Learning [D]. Southwest University of Science and Technology, 2024. DOI: 10.27415/d.cnki.gxngc.2024.001235.
[7] Cheng Zhuo, Liang Hui, Xing Lumin. Research Progress and Prospects of Deep Learning Technology in Laryngopharyngeal Endoscopy Applications [J/OL]. Journal of Otolaryngology, Ophthalmology and Otorhinolaryngology, Shandong University, 1-9 [2024-12-14]. http://kns.cnki.net/kcms/detail/37.1437.R.20240522.1300.003.html.
[2] Zhou Jielu, Lin Jiaxi, Zhu Jinzhou. Application of Artificial Intelligence in Endoscopic Diagnosis of Colorectal Tumors [J]. Chinese Medical Equipment, 2024, 39(09): 136-143.
[3] Wu Yahui, Zhu Shiqi, Wu Yudong, et al. Colonoscopy Image Classification System for Submucosal Colorectal Tumors and Polyps Based on Few-Shot Learning Algorithms [J]. Chinese Journal of Medical Physics, 2024, 41(07): 897-904.
[4] Chen Jian, Wang Jennie, Xia Kaijian, et al. Comparison of Deep Learning-Based Methods for Colonoscopy Image Segmentation and Classification of Colorectal Polyps [J]. Journal of Shanghai Jiao Tong University (Medical Science), 2024, 44(06): 762-772.
[5] Zhang Qiusheng, Lin Qi, Li Guanghua, et al. Research Progress on the Application of Deep Learning-Based Artificial Intelligence Technology in Gastric Cancer [J]. Digestive Tumor Journal (Electronic Edition), 2024, 16(02): 223-230.
[6] Yao Hanmin. Preprocessing and Assisted Diagnosis of Esophageal Lesion Images Based on Deep Learning [D]. Southwest University of Science and Technology, 2024. DOI: 10.27415/d.cnki.gxngc.2024.001235.
[7] Cheng Zhuo, Liang Hui, Xing Lumin. Research Progress and Prospects of Deep Learning Technology in Laryngopharyngeal Endoscopy Applications [J/OL]. Journal of Otolaryngology, Ophthalmology and Otorhinolaryngology, Shandong University, 1-9 [2024-12-14]. http://kns.cnki.net/kcms/detail/37.1437.R.20240522.1300.003.html.
Copyright © 2025 Junjun Huang, Weiting Wu, Dongdong Hu, Xufeng Sun
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
