Emulating Hyperspectral and Narrow-Band Imaging for Deep-Learning-Driven Gastrointestinal Disorder Detection in Wireless Capsule Endoscopy
Bioengineering · 04.09.2025 · 12 (9) · 953
DOI: 10.3390/bioengineering12090953 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 04.09.2025. Verfasst von Chu-Kuang Chou und 9 weiteren Autor:innen. Beteiligte Einrichtung: Division of Gastroenterology and Hepatology, Department of Internal Medicine, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chia-Yi 60002,…. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science and Technology Council, Southern Taiwan Science Park, Ditmanson Medical Foundation Chia-Yi Christian Hospital.
Abstract (Originalsprache)
Diagnosing gastrointestinal disorders (GIDs) remains a significant challenge, particularly when relying on wireless capsule endoscopy (WCE), which lacks advanced imaging enhancements like Narrow Band Imaging (NBI). To address this, we propose a novel framework, the Spectrum-Aided Vision Enhancer (SAVE), especially designed to transform standard white light (WLI) endoscopic images into spectrally enriched representations that emulate both hyperspectral imaging (HSI) and NBI formats. By leveraging color calibration through the Macbeth Color Checker, gamma correction, CIE 1931 XYZ transformation, and principal component analysis (PCA), SAVE reconstructs detailed spectral information from conventional RGB inputs. Performance was evaluated using the Kvasir-v2 dataset, which includes 6490 annotated images spanning eight GI-related categories. Deep learning models like Inception-Net V3, MobileNetV2, MobileNetV3, and AlexNet were trained on both original WLI- and SAVE-enhanced images. Among these, MobileNetV2 achieved an F1-score of 96% for polyp classification using SAVE, and AlexNet saw a notable increase in average accuracy to 84% when applied to enhanced images. Image quality assessment showed high structural similarity (SSIM scores of 93.99% for Olympus endoscopy and 90.68% for WCE), confirming the fidelity of the spectral transformations. Overall, the SAVE framework offers a practical, software-based enhancement strategy that significantly improves diagnostic accuracy in GI imaging, with strong implications for low-cost, non-invasive diagnostics using capsule endoscopy systems.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chia-Yi 60002, Taiwan.
- Obesity Center, Ditmanson Medical Foundation Chia-Yi Christian Hospital, Chia-Yi 60002, Taiwan.
- Department of Trauma, Changhua Christian Hospital, No. 135, Nanxiao St., Changhua City 50006, Taiwan.
- Department of Mechanical Engineering, National Chung Cheng University, No. 168, University Rd., Min Hsiung, Chia-Yi 62102, Taiwan.
- Department of Biomedical Imaging, Chennai Institute of Technology, Sarathy Nagar, Chennai 600069, Tamil Nadu, India.
- Information Technology Department, Sanjivani College of Engineering, Kopargaon 423603, Maharashtra, India.
ORCID-Profile: Chu-Kuang Chou, Kun-Hua Lee, Arvind Mukundan, Devansh Gupta, Tsung-Hsien Chen, Hsiang-Chen Wang
Förderung
- National Science and Technology Council
- Southern Taiwan Science Park
- Ditmanson Medical Foundation Chia-Yi Christian Hospital
- Kaohsiung Armed Forces General Hospital
- National Science and Technology Council, the Republic of China
- Dalin Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation-National Chung Cheng University Joint Research Program
Zitieren
APA
Chou, C. K., Lee, K. H., Karmakar, R., Mukundan, A., Gade, P. C., Gupta, D., Su, C. C., Chen, T. H., Ko, C. Y., & Wang, H. C. (2025). Emulating Hyperspectral and Narrow-Band Imaging for Deep-Learning-Driven Gastrointestinal Disorder Detection in Wireless Capsule Endoscopy. Bioengineering, 12(9), 953. https://doi.org/10.3390/bioengineering12090953
Vancouver
Chou CK, Lee KH, Karmakar R, Mukundan A, Gade PC, Gupta D, et al. Emulating Hyperspectral and Narrow-Band Imaging for Deep-Learning-Driven Gastrointestinal Disorder Detection in Wireless Capsule Endoscopy. Bioengineering. 2025;12(9):953. doi:10.3390/bioengineering12090953
BibTeX
@article{Chou2025,
author = {Chou, Chu-Kuang and Lee, Kun-Hua and Karmakar, Riya and Mukundan, Arvind and Gade, Pratham Chandraskhar and Gupta, Devansh and Su, Chang-Chao and Chen, Tsung-Hsien and Ko, Chou-Yuan and Wang, Hsiang-Chen},
title = {Emulating Hyperspectral and Narrow-Band Imaging for Deep-Learning-Driven Gastrointestinal Disorder Detection in Wireless Capsule Endoscopy},
journal = {Bioengineering},
year = {2025},
volume = {12},
number = {9},
pages = {953},
doi = {10.3390/bioengineering12090953}
}
EUVIMED