An Integrated AI-Enabled System Using One Class Twin Cross Learning (OCT-X) for Early Gastric Cancer Detection

2025-03-31

AI Summary

To address the clinical challenges of high false-negative/false-positive rates and the trade-off between real-time performance and diagnostic accuracy in early gastric cancer screening, this study proposes a software–hardware co-designed AI diagnostic system. Methodologically, we introduce the novel One-Class Twin Cross-learning (OCT-X) algorithm, integrating fast dual-threshold grid search with a patch-based fully convolutional network; hardware components include an NI CompactDAQ platform, LabVIEW-based real-time control, a high-resolution point-of-care testing (POCT) imaging sensor, and a wireless transmission module—enabling millisecond-level inference with precise lesion localization. Experimental results demonstrate a diagnostic accuracy of 99.70%, outperforming state-of-the-art models by 4.47 percentage points; multi-rate adaptability improves by 10%, significantly enhancing clinical deployability. The core contributions are the first integration of the OCT-X algorithm with an end-to-end software–hardware co-design architecture.

Technology Category

• Machine Learning: Hardware-aware ML
• Search and Optimization: Algorithm Configuration
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Algorithmic accountability and transparency on the web
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Early detection of gastric cancer, a leading cause of cancer-related mortality worldwide, remains hampered by the limitations of current diagnostic technologies, leading to high rates of misdiagnosis and missed diagnoses. To address these challenges, we propose an integrated system that synergizes advanced hardware and software technologies to balance speed-accuracy. Our study introduces the One Class Twin Cross Learning (OCT-X) algorithm. Leveraging a novel fast double-threshold grid search strategy (FDT-GS) and a patch-based deep fully convolutional network, OCT-X maximizes diagnostic accuracy through real-time data processing and seamless lesion surveillance. The hardware component includes an all-in-one point-of-care testing (POCT) device with high-resolution imaging sensors, real-time data processing, and wireless connectivity, facilitated by the NI CompactDAQ and LabVIEW software. Our integrated system achieved an unprecedented diagnostic accuracy of 99.70%, significantly outperforming existing models by up to 4.47%, and demonstrated a 10% improvement in multirate adaptability. These findings underscore the potential of OCT-X as well as the integrated system in clinical diagnostics, offering a path toward more accurate, efficient, and less invasive early gastric cancer detection. Future research will explore broader applications, further advancing oncological diagnostics. Code is available at https://github.com/liu37972/Multirate-Location-on-OCT-X-Learning.git.

Problem

• Improving early gastric cancer detection accuracy
• Reducing misdiagnosis with real-time data processing
• Integrating hardware-software for speed-accuracy balance

Innovation

• One Class Twin Cross Learning algorithm
• Fast double-threshold grid search
• All-in-one POCT device