Parameterized Diffusion Optimization enabled Autoregressive Ordinal Regression for Diabetic Retinopathy Grading

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yu, Qinkai, Zhou, Wei, Liu, Hantao, Xu, Yanyu, Wang, Meng, Zhao, Yitian, Fu, Huazhu, Ye, Xujiong, Zheng, Yalin, Meng, Yanda
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916830174511104
author Yu, Qinkai
Zhou, Wei
Liu, Hantao
Xu, Yanyu
Wang, Meng
Zhao, Yitian
Fu, Huazhu
Ye, Xujiong
Zheng, Yalin
Meng, Yanda
author_facet Yu, Qinkai
Zhou, Wei
Liu, Hantao
Xu, Yanyu
Wang, Meng
Zhao, Yitian
Fu, Huazhu
Ye, Xujiong
Zheng, Yalin
Meng, Yanda
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04978
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Parameterized Diffusion Optimization enabled Autoregressive Ordinal Regression for Diabetic Retinopathy Grading
Yu, Qinkai
Zhou, Wei
Liu, Hantao
Xu, Yanyu
Wang, Meng
Zhao, Yitian
Fu, Huazhu
Ye, Xujiong
Zheng, Yalin
Meng, Yanda
Computer Vision and Pattern Recognition
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.
title Parameterized Diffusion Optimization enabled Autoregressive Ordinal Regression for Diabetic Retinopathy Grading
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.04978