UGPL: Uncertainty-Guided Progressive Learning for Evidence-Based Classification in Computed Tomography

2025-07-18

AI Summary

CT image classification faces challenges due to subtle lesion characteristics and heterogeneous spatial distributions, making it difficult for existing methods to simultaneously capture global contextual information and discriminative local details. To address this, we propose an uncertainty-guided global-local progressive learning framework. First, epistemic uncertainty is quantified via evidential deep learning to identify diagnostically ambiguous regions. Second, diverse critical lesion patches are adaptively extracted using a non-maximum suppression–based strategy. Finally, fine-grained modeling is achieved through progressive patch refinement, adaptive feature fusion, and joint global-local training. Evaluated on three CT datasets—renal abnormalities, lung cancer, and COVID-19—the method achieves absolute accuracy improvements of 3.29%, 2.46%, and 8.08%, respectively, consistently outperforming state-of-the-art approaches.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Reasoning under Uncertainty: Uncertainty Representations

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Accurate classification of computed tomography (CT) images is essential for diagnosis and treatment planning, but existing methods often struggle with the subtle and spatially diverse nature of pathological features. Current approaches typically process images uniformly, limiting their ability to detect localized abnormalities that require focused analysis. We introduce UGPL, an uncertainty-guided progressive learning framework that performs a global-to-local analysis by first identifying regions of diagnostic ambiguity and then conducting detailed examination of these critical areas. Our approach employs evidential deep learning to quantify predictive uncertainty, guiding the extraction of informative patches through a non-maximum suppression mechanism that maintains spatial diversity. This progressive refinement strategy, combined with an adaptive fusion mechanism, enables UGPL to integrate both contextual information and fine-grained details. Experiments across three CT datasets demonstrate that UGPL consistently outperforms state-of-the-art methods, achieving improvements of 3.29%, 2.46%, and 8.08% in accuracy for kidney abnormality, lung cancer, and COVID-19 detection, respectively. Our analysis shows that the uncertainty-guided component provides substantial benefits, with performance dramatically increasing when the full progressive learning pipeline is implemented. Our code is available at: https://github.com/shravan-18/UGPL

Problem

• Improves CT image classification accuracy for medical diagnosis
• Addresses difficulty in detecting localized pathological features
• Guides analysis using predictive uncertainty to focus on ambiguous regions

Innovation

• Uncertainty-guided global-to-local CT analysis
• Evidential deep learning quantifies predictive uncertainty
• Adaptive fusion integrates context and details