EndoSight AI：深度学习驱动的实时胃肠道息肉检测与分割以增强内镜诊断
EndoSight AI: Deep Learning-Driven Real-Time Gastrointestinal Polyp Detection and Segmentation for Enhanced Endoscopic Diagnostics
- Department of Computer Science, Faculty of Sciences, Central University of Venezuela (UCV), Caracas, Venezuela（委内瑞拉中央大学计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对内镜操作中胃肠道息肉精准实时检测的需求，提出独立开发的深度学习架构EndoSight AI，基于Hyper-Kvasir数据集实现88.3%的检测mAP、最高69%的分割Dice系数及每秒超35帧的GPU实时推理，提升诊断准确性与临床决策水平。
AI中文摘要：
内镜操作中胃肠道息肉的精准实时检测对结直肠癌的早期诊断和预防至关重要。本研究提出EndoSight AI，一种独立开发和评估的深度学习架构，可实现准确的息肉定位和详细的边界描绘。利用公开可用的Hyper-Kvasir数据集，该系统在息肉检测任务上达到88.3%的平均精度均值（mAP），分割任务的Dice系数最高达69%，同时在GPU硬件上的实时推理速度超过每秒35帧。训练过程整合了临床相关的性能指标和一种新颖的热感知流程，以确保模型的鲁棒性和效率。这种集成AI解决方案旨在无缝部署于内镜工作流程，有望提升胃肠道医疗中的诊断准确性和临床决策水平。
英文摘要：
Precise and real-time detection of gastrointestinal polyps during endoscopic procedures is crucial for early diagnosis and prevention of colorectal cancer. This work presents EndoSight AI, a deep learning architecture developed and evaluated independently to enable accurate polyp localization and detailed boundary delineation. Leveraging the publicly available Hyper-Kvasir dataset, the system achieves a mean Average Precision (mAP) of 88.3% for polyp detection and a Dice coefficient of up to 69% for segmentation, alongside real-time inference speeds exceeding 35 frames per second on GPU hardware. The training incorporates clinically relevant performance metrics and a novel thermal-aware procedure to ensure model robustness and efficiency. This integrated AI solution is designed for seamless deployment in endoscopy workflows, promising to advance diagnostic accuracy and clinical decision-making in gastrointestinal healthcare.
