Parameterized Diffusion Optimization enabled Autoregressive Ordinal Regression for Diabetic Retinopathy Grading

2025-07-07

AI Summary

Diabetic retinopathy (DR) grading faces two key challenges: long-tailed class distributions leading to severe scarcity of minority-stage samples, and clinically ambiguous diagnostic boundaries causing inter-observer annotation inconsistency. To address these, we propose the Autoregressive Ordinal Diffusion model (AORD), the first framework integrating diffusion mechanisms into autoregressive ordinal regression. AORD models disease progression continuity via multi-stage ordered prediction, leveraging pretrained large-model global features for conditional probability estimation—thereby avoiding redundant local context learning and substantially enhancing discriminative robustness under long-tailed distributions and cross-center consistency. Evaluated on four public fundus image datasets, AORD consistently outperforms six state-of-the-art methods, achieving new best-in-class DR grading performance. The implementation is publicly available.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

As a long-term complication of diabetes, diabetic retinopathy (DR) progresses slowly, potentially taking years to threaten vision. An accurate and robust evaluation of its severity is vital to ensure prompt management and care. Ordinal regression leverages the underlying inherent order between categories to achieve superior performance beyond traditional classification. However, there exist challenges leading to lower DR classification performance: 1) The uneven distribution of DR severity levels, characterized by a long-tailed pattern, adds complexity to the grading process. 2)The ambiguity in defining category boundaries introduces additional challenges, making the classification process more complex and prone to inconsistencies. This work proposes a novel autoregressive ordinal regression method called AOR-DR to address the above challenges by leveraging the clinical knowledge of inherent ordinal information in DR grading dataset settings. Specifically, we decompose the DR grading task into a series of ordered steps by fusing the prediction of the previous steps with extracted image features as conditions for the current prediction step. Additionally, we exploit the diffusion process to facilitate conditional probability modeling, enabling the direct use of continuous global image features for autoregression without relearning contextual information from patch-level features. This ensures the effectiveness of the autoregressive process and leverages the capabilities of pre-trained large-scale foundation models. Extensive experiments were conducted on four large-scale publicly available color fundus datasets, demonstrating our model's effectiveness and superior performance over six recent state-of-the-art ordinal regression methods. The implementation code is available at https://github.com/Qinkaiyu/AOR-DR.

Problem

• Address uneven distribution of DR severity levels
• Resolve ambiguity in defining category boundaries
• Improve DR grading via autoregressive ordinal regression

Innovation

• Autoregressive ordinal regression for DR grading
• Diffusion process for conditional probability modeling
• Leverages pre-trained large-scale foundation models