Real-Time Feature Extraction of Fine Mucosal Structures in Endoscopic Images Using Morphological Watershed Segmentation for Early Gastric Cancer Detection

Siyue HAN; Zhizhao YU; Jiahui YU; Simon James Fong; Yongze GUO; Hongwei ZHANG; Saicong LU; Xian WANG; Feng TIAN

Siyue HAN Faculty of Science and Technology University of Macau, Macau SAR. China
Zhizhao YU Faculty of Science and Technology University of Macau, Macau SAR. China
Jiahui YU Faculty of Science and Technology University of Macau, Macau SAR. China
Simon James Fong Faculty of Science and Technology University of Macau, Macau SAR. China
Yongze GUO Department of Gastroenterology Affiliated Hospital of Hebei University of Engineering Handan, Hebei Province. China
Hongwei ZHANG Department of Gastroenterology Affiliated Hospital of Hebei University of Engineering Handan, Hebei Province. China
Saicong LU Department of Gastroenterology Affiliated Hospital of Hebei University of Engineering Handan, Hebei Province. China
Xian WANG Department of Gastroenterology Affiliated Hospital of Hebei University of Engineering Handan, Hebei Province. China
Feng TIAN Institute of Biomedical Informatics, School of Medicine Hebei University of Engineering, Handan Hebei Province. China

Abstract

Gastric cancer is among the leading causes of cancer related mortality worldwide, and its early detection remains challenging due to subtle endoscopic manifestations. Artificial intelligence (AI) assisted analysis of endoscopic images offers a promising pathway for improving diagnostic accuracy in real time. This paper presents a real time feature extraction framework for fine mucosal structures (FMS) in gastroscopy images using a structure enhanced morphological watershed segmentation algorithm. The method performs image preprocessing through directional filtering and morphological operations to highlight FMS patterns, followed by marker controlled watershed segmentation to deline ate structural boundaries. Geometric features including area, circularity, convexity, and Feret diameter are quantified and evaluated using multiple machine learning classifiers. Experimental results on endoscopic datasets demonstrate that filtering segmentation outliers significantly improves classification performance, with neural networks achieving an AUC of 0.813. The results indicate that max Feret diameter is the most discriminative feature for distinguishing early gastric cancer from non cancerous tissues. This study contributes to real time intelligent healthcare systems by providing an interpretable and computationally efficient feature extraction pipeline that can support AI-driven clinical decision making in endoscopic screening

References

[1] Li, J., Zhu, Y., Dong, Z., et al. (2022). Development and validation of a feature extraction based logical anthropomorphic diagnostic system for early gastric cancer: A case-control study. eClinicalMedicine 53, 101716. [2] Liu, X., Zhang, Y., Zhang, Y., et al. (2022). Deep learningbased computer aided diagnosis for early gastric cancer using magnifying endoscopy images. Diagnostics 12 (8), 1996. [3] Li, J., Zhu, Y., Dong, Z., et al. (2022). Development and validation of a feature extraction based logical anthropomorphic diagnostic system for early gastric cancer: A case-control study. eClinicalMedicine 53, 101716. [4] Shi, Y., Fan, H., Li, L., et al. (2024). The value of machine learning approaches in the diagnosis of early gastric cancer: A systematic review and meta analysis. World J. Surg. Oncol. 22, 40 [5] Klang, E., Soroush, A., Nadkarni, G. N., et al. (2023). Deep learning and gastric cancer: Systematic review of AIassisted endoscopy. Diagnostics 13 (24), 3613. [6] Uedo, N., Ishihara, H., Iishi, T., Tatsuta, M. (2006). Diagnosis of early gastric cancer by magnifying endoscopy with narrow-band imaging: correlation of vascular patterns with histopathology. Endoscopy 38 (10), 1030–1034 [7] Manasseh, M., Mithany, R. (2024). Gastric cancer: a comprehensive literature review. Br. J. Surg. 111 (Suppl. 9), znae271.170. [8] Doi, K., Mahon, Mac., H., Giger, M. L. (1998). Computer-aided diagnosis in medical imaging. IEEE Trans. Inf. Technol. Biomed. 2 (3), 161–174. [9] Doi, K. (2007). Current status and future potential of computer-aided diagnosis in medical imaging. Comput. Med. Imaging Graph. 31 (4–5), 198–211. [10] Zhang, Y., Wang, Y., Liu, Y., et al. (2023). A novel deep learning framework for gastric cancer detection using endoscopic images. Multimed. Tools Appl.