Trustworthy Endoscopic Super-Resolution

2026-04-20

AI Summary

Endoscopic super-resolution reconstruction is prone to generating hallucinated structures and amplifying noise, posing significant risks to clinical safety. To address this challenge, this work proposes a lightweight, model-agnostic error prediction network that estimates pixel-level reconstruction errors in real time from intermediate features. The method introduces a Conformal Failure Mask (CFM) to identify unreliable regions and, for the first time, achieves theoretically provable conformal risk control. By simultaneously providing guaranteed error bounds and coverage failure detection, the approach delivers dual reliability assurances while maintaining low latency. This makes it particularly suitable for safety-critical applications such as robot-assisted surgery, where high-confidence super-resolution is essential.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Safety and Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Large-scale security measurements

Abstract

Super-resolution (SR) models are attracting growing interest for enhancing minimally invasive surgery and diagnostic videos under hardware constraints. However, valid concerns remain regarding the introduction of hallucinated structures and amplified noise, limiting their reliability in safety-critical settings. We propose a direct and practical framework to make SR systems more trustworthy by identifying where reconstructions are likely to fail. Our approach integrates a lightweight error-prediction network that operates on intermediate representations to estimate pixel-wise reconstruction error. The module is computationally efficient and low-latency, making it suitable for real-time deployment. We convert these predictions into operational failure decisions by constructing Conformal Failure Masks (CFM), which localize regions where the SR output should not be trusted. Built on conformal risk control principles, our method provides theoretical guarantees for controlling both the tolerated error limit and the miscoverage in detected failures. We evaluate our approach on image and video SR, demonstrating its effectiveness in detecting unreliable reconstructions in endoscopic and robotic surgery settings. To our knowledge, this is the first study to provide a model-agnostic, theoretically grounded approach to improving the safety of real-time endoscopic image SR.

Problem

• super-resolution
• endoscopic imaging
• hallucination
• trustworthiness
• safety-critical

Innovation

• Conformal Failure Masks
• error prediction
• super-resolution
• trustworthy AI
• endoscopic imaging