EndoSight AI: Deep Learning-Driven Real-Time Gastrointestinal Polyp Detection and Segmentation for Enhanced Endoscopic Diagnostics

TL;DR

EndoSight AI is a deep learning system that enables real-time detection and segmentation of gastrointestinal polyps during endoscopy, improving early diagnosis and clinical decision-making.

Contribution

The paper introduces a novel deep learning architecture with a thermal-aware training procedure for accurate, real-time polyp detection and segmentation in endoscopic images.

Findings

Achieves 88.3% mAP for detection

Up to 69% Dice coefficient for segmentation

Operates at over 35 fps on GPU hardware

Abstract

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.