Article Details

Abstract

To address engineering problems in the integration of Deep Learning models and traditional Web information systems, this paper designs and implements a loosely coupled and highly available medical image segmentation information management system. The system adopts B/S architecture. It develops the user interface and business logic based on the ASP.NET framework at the front-end, and calls the independently deployed Mask R-CNN model service through RESTful API at the back-end to complete image segmentation tasks. It adopts SQL Server database for data management and designs an asynchronous task processing mechanism. It successfully builds a management system integrating user management, patient information management, image upload, and asynchronous segmentation task scheduling. Tests verify the effectiveness of the system architecture in function, performance, and heterogeneous service communication. This study provides a feasible scheme for solving engineering integration problems of Deep Learning models in medical information systems. The proposed loosely coupled architecture has good practicality and scalability.

Keywords

information management system; system integration; ASP.NET; Mask R-CNN; B/S architecture

References

1. [1] Yan Chao, Sun Zhanquan, Tian Engang, etc Research progress on medical image segmentation technology based on deep learning [J]. Electronic Science and Technology, 2021, 34 (2): 7-11
2. [2] Shi Haoran, Sun Jingyu Edge aware melanoma segmentation method based on hybrid deep learning network [J]. Computer Engineering and Design, 2025, 46 (6): 1796-1802
3. [3] Tu Yaofeng Research on Key Technologies of Database Storage and Query for New Hardware [D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2022
4. [4] Zhu Yuchao Research on Service Chain Deployment Mechanism Based on Deep Reinforcement Learning [D]. Beijing: Beijing University of Posts and Telecommunications, 2022
5. [5] Su Jiaxing, Zhao Yi, Leo, etc A loosely coupled cross domain collaborative learning platform that balances efficiency and security [J]. Journal of Cyberspace Security Science, 2024, 2 (6): 74-85
6. [6] Zhao Jingpeng Research on Hierarchical Web Service Classification Method Based on Deep Learning [D]. Beijing: North China Electric Power University (Beijing), 2021
7. [7] Tang Yi, Lu Mei Design of Enterprise Job Recruitment Voting and Comprehensive Evaluation System Based on ASP.NET Core [J]. Modern Information Technology, 2025, 9 (14): 113-117
8. [8] Deng Jie, Tong Bing, Han Junfeng, etc Design and Implementation of RH Secondary Client in Refining Furnace Based on ASP.NET MVC Architecture [J]. Industrial Control Computer, 2024, 37 (6): 30-32, 35
9. [9] Li Jing, Zhang Yue, Qiao Yaxin, etc Cervical cell segmentation based on improved Mask R-CNN model [J]. Journal of Changchun University of Science and Technology: Natural Science Edition, 2024, 47 (2): 107-113
10. [10] Li Qingzhong Design and Implementation of Logistics Scheduling Management System Based on ASP.NET Technology and Quantum Genetic Algorithm [J]. Information Technology and Informatization, 2024 (8): 65-68

About the authors

Chen Shaojie (1998-), female, Han ethnicity, from Chaozhou, Guangdong, teaching assistant, master's degree, research direction: computer technology and artificial intelligence; Chen Rongzheng (1979-), male, Han nationality, from Linyi, Shandong, associate professor, master's degree, research direction: software technology and artificial intelligence.