Statistical Management of the False Discovery Rate in Medical Instance Segmentation Based on Conformal Risk Control

2025/04/06 by Dai, Mengxia, Tianyang Li, Luo, Wenqian +1
Computer Science · Medicine · #AI in cancer detection #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Cutaneous Melanoma Detection and Management #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2504.04482

openalex publication_date 2025/04/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Instance segmentation plays a pivotal role in medical image analysis by enabling precise localization and delineation of lesions, tumors, and anatomical structures. Although deep learning models such as Mask R-CNN and BlendMask have achieved remarkable progress, their application in high-risk medical scenarios remains constrained by confidence calibration issues, which may lead to misdiagnosis. To address this challenge, we propose a robust quality control framework based on conformal prediction theory. This framework innovatively constructs a risk-aware dynamic threshold mechanism that adaptively adjusts segmentation decision boundaries according to clinical requirements.Specifically, we design a calibration-aware loss function that dynamically tunes the segmentation threshold based on a user-defined risk level α. Utilizing exchangeable calibration data, this method ensures that the expected FNR or FDR on test data remains below α with high probability. The framework maintains compatibility with mainstream segmentation models (e.g., Mask R-CNN, BlendMask+ResNet-50-FPN) and datasets (PASCAL VOC format) without requiring architectural modifications. Empirical results demonstrate that we rigorously bound the FDR metric marginally over the test set via our developed calibration framework.

Citations

• SConU: Selective Conformal Uncertainty in Large Language Models
• Theoretical Foundations of Conformal Prediction
• Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models
• ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees
• Conformal Prediction for Natural Language Processing: A Survey
• Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond
• Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation
• Selection by Prediction with Conformal p-values
• Conformal Risk Control
• Sparse MLP for Image Recognition: Is Self-Attention Really Necessary?
• A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
• A Survey of Uncertainty in Deep Neural Networks
• A survey of uncertainty in deep neural networks
• BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
• Mask R-CNN
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Learning for Medical Image Segmentation

Related

• Controlling False Positives in Image Segmentation via Conformal Prediction
• Conformal Lesion Segmentation for 3D Medical Images
• Conditional Conformal Risk Adaptation
• Conformal confidence sets for biomedical image segmentation
• COMPASS: Robust Feature Conformal Prediction for Medical Segmentation Metrics