# DiffSight-Former: Modeling Structural Differences and Temporal Dynamics for Glaucoma Progression Prediction

arXiv: https://arxiv.org/abs/2606.09140 · HTML: https://mlsanity.com/paper/2606.09140/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 55 references that are in the map.
- First posted on arXiv 8 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Transformers in Medical Imaging: A Survey](https://mlsanity.com/paper/2201.09873/) (2022)
- [UniFormer: Unifying Convolution and Self-attention for Visual Recognition](https://mlsanity.com/paper/2201.09450/) (2022)
- [METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens](https://mlsanity.com/paper/2304.02211/) (2023)
- [Time Series as Images: Vision Transformer for Irregularly Sampled Time Series](https://mlsanity.com/paper/2303.12799/) (2023)
- [Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation](https://mlsanity.com/paper/1801.00926/) (2018)
- [RetainVis: Visual Analytics with Interpretable and Interactive Recurrent Neural Networks on Electronic Medical Records](https://mlsanity.com/paper/1805.10724/) (2018)
- [ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer](https://mlsanity.com/paper/2201.09376/) (2022)
- [CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading](https://mlsanity.com/paper/1911.01376/) (2019)
- [Learning Spatio-Temporal Model of Disease Progression with NeuralODEs from Longitudinal Volumetric Data](https://mlsanity.com/paper/2211.04234/) (2022)
- [Longformer: Longitudinal Transformer for Alzheimer's Disease Classification with Structural MRIs](https://mlsanity.com/paper/2302.00901/) (2023)
- [Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification](https://mlsanity.com/paper/2304.02836/) (2023)
- [XTSFormer: Cross-Temporal-Scale Transformer for Irregular-Time Event Prediction in Clinical Applications](https://mlsanity.com/paper/2402.02258/) (2024)
- [LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression](https://mlsanity.com/paper/2404.07091/) (2024)
- [Multi-scale Spatio-temporal Transformer-based Imbalanced Longitudinal Learning for Glaucoma Forecasting from Irregular Time Series Images](https://mlsanity.com/paper/2402.13475/) (2024)
- [Spatiotemporal Representation Learning for Short and Long Medical Image Time Series](https://mlsanity.com/paper/2403.07513/) (2024)
- [Risk Estimation of Knee Osteoarthritis Progression via Predictive Multi-task Modelling from Efficient Diffusion Model using X-ray Images](https://mlsanity.com/paper/2506.14560/) (2025)

## Abstract (arXiv)

Glaucoma is a leading cause of irreversible blindness worldwide, and early detection from fundus images is critical for effective disease management. While deep learning has achieved promising performance in fundus image analysis, most existing methods rely on single time-point images and fail to capture longitudinal structural and vascular changes associated with disease progression. Sequential fundus images acquired during clinical follow-up provide valuable temporal information; however, current sequential models often struggle to detect subtle early progression signals and commonly depend on fixed-length inputs or diagnostic cues from already glaucomatous images, limiting their clinical utility for early prediction. To address these limitations, we propose DiffSight-Former, a framework for glaucoma progression prediction from sequential fundus images. It incorporates a time-variant feature extraction module based on a fundus-specific foundation model to obtain robust anatomical representations. A multi-structure difference modeling module is introduced to quantify progression-related changes in the optic disc/cup region and retinal vasculature. These representations are integrated with temporal interval embeddings and processed by a time-aware Transformer to model disease progression and estimate the probability of future glaucoma onset. Experiments were conducted on two longitudinal datasets, SIGF (405 sequences) and GRAPE (263 sequences). On SIGF, DiffSight-Former achieved an AUC of 91.54% and a sensitivity of 92.16% for progression prediction. On GRAPE, it achieved an average accuracy of 87.48% across three clinical visual-field progression criteria. Compared with existing approaches, DiffSight-Former demonstrates strong performance and robustness across different temporal settings, highlighting its potential for longitudinal glaucoma monitoring and early risk prediction.