# Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis

arXiv: https://arxiv.org/abs/2502.11724 · HTML: https://mlsanity.com/paper/2502.11724/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2025.

## Built on by (most cited first, 6 of 6)

- [Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation](https://mlsanity.com/paper/2503.05319/) (2025)
- [DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities](https://mlsanity.com/paper/2511.05968/) (2025)
- [Robust Incomplete-Modality Alignment for Ophthalmic Disease Grading and Diagnosis via Labeled Optimal Transport](https://mlsanity.com/paper/2507.04999/) (2025)
- [Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding](https://mlsanity.com/paper/2606.03604/) (2026)
- [RED-Sphere: Hyperspherical Residual Edge Debiasing for Cross-Population Fundus Disease Domain Generalization](https://mlsanity.com/paper/2607.10777/) (2026)
- [GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification](https://mlsanity.com/paper/2608.05608/) (2026)

## Abstract (arXiv)

Ophthalmologists typically require multimodal data sources to improve diagnostic accuracy in clinical decisions. However, due to medical device shortages, low-quality data and data privacy concerns, missing data modalities are common in real-world scenarios. Existing deep learning methods tend to address it by learning an implicit latent subspace representation for different modality combinations. We identify two significant limitations of these methods: (1) implicit representation constraints that hinder the model's ability to capture modality-specific information and (2) modality heterogeneity, causing distribution gaps and redundancy in feature representations. To address these, we propose an Incomplete Modality Disentangled Representation (IMDR) strategy, which disentangles features into explicit independent modal-common and modal-specific features by guidance of mutual information, distilling informative knowledge and enabling it to reconstruct valuable missing semantics and produce robust multimodal representations. Furthermore, we introduce a joint proxy learning module that assists IMDR in eliminating intra-modality redundancy by exploiting the extracted proxies from each class. Experiments on four ophthalmology multimodal datasets demonstrate that the proposed IMDR outperforms the state-of-the-art methods significantly.