الملخص
Accurately isolating disease-related features from confounding covariates (e.g., age, gender, site) and individual variations remains a fundamental challenge in medical image classification. Traditional regression-based approaches may ignore non-linear relations between image features and true covariates. To overcome this issue, we present a generalized Medical Imaging Disentanglement Learning (MedIDL) framework. MedIDL maps image features into three mutually orthogonal latent spaces through specialized disentanglement heads: a disease classification head guided by a supervised loss, a covariate-alignment head constrained by cross-subject similarity matching, and a Gaussian head absorbing individual variations. We evaluated our framework across 7 datasets encompassing diverse imaging modalities. MedIDL outperforms state-of-the-art supervised and self-supervised classification methods in accuracy across all datasets. Association analyses demonstrate that MedIDL successfully isolates target-specific latent representations. Gradient-based interpretability mappings localize pathognomonic patterns aligning with established clinical literature.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhang, S., Zhang, J., Jiang, Z., Yu, Z., Zhang, Y., Zhang, Q., Chen, X., Yang, H., Gao, F., Cui, L., Zhou, Y., Zhang, X. Y., & Initiative, A. D. N. (2026). Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification. https://omanscience.com/ar/articles/decoupling-disease-covariates-and-individual-variability-a-unified-disentanglement-framework-for-medical-image-classification
MLA 9
Zhang, Shengjie, et al. "Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification." https://omanscience.com/ar/articles/decoupling-disease-covariates-and-individual-variability-a-unified-disentanglement-framework-for-medical-image-classification.
شيكاغو (المؤلف–التاريخ)
Zhang, Shengjie, Jinglin Zhang, Zhuangzhuang Jiang, Ziqi Yu, Yipin Zhang, Qi Zhang, Xiang Chen, Haibo Yang, Fei Gao, Longbiao Cui, Yuan Zhou, Xiao-Yong Zhang, and Alzheimer's Disease Neuroimaging Initiative. 2026. "Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification." https://omanscience.com/ar/articles/decoupling-disease-covariates-and-individual-variability-a-unified-disentanglement-framework-for-medical-image-classification.
هارفارد
Zhang, S., Zhang, J., Jiang, Z., Yu, Z., Zhang, Y., Zhang, Q., Chen, X., Yang, H., Gao, F., Cui, L., Zhou, Y., Zhang, X. Y. and Initiative, A. D. N. (2026) 'Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification', Available at: https://omanscience.com/ar/articles/decoupling-disease-covariates-and-individual-variability-a-unified-disentanglement-framework-for-medical-image-classification.
فانكوفر
Zhang S, Zhang J, Jiang Z, Yu Z, Zhang Y, Zhang Q, et al. Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification. https://omanscience.com/ar/articles/decoupling-disease-covariates-and-individual-variability-a-unified-disentanglement-framework-for-medical-image-classification
IEEE
S. Zhang, J. Zhang, Z. Jiang, Z. Yu, Y. Zhang, Q. Zhang, X. Chen, H. Yang, F. Gao, L. Cui, Y. Zhou, X. Y. Zhang, and A. D. N. Initiative, "Decoupling Disease, Covariates, and Individual Variability: A Unified Disentanglement Framework for Medical Image Classification," https://omanscience.com/ar/articles/decoupling-disease-covariates-and-individual-variability-a-unified-disentanglement-framework-for-medical-image-classification.