Overcoming challenges in research and development of rare eye diseases

Sharma, Mohita

doi:10.4103/ijo.ijo_1083_22

Cited by 2 publications

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

EyeDiff: text-to-image diffusion model improves rare eye disease diagnosis

Chen,

Zhang,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

The rising prevalence of vision-threatening retinal diseases poses a significant burden on the global healthcare systems. Deep learning (DL) offers a promising solution for automatic disease screening but demands substantial data. Collecting and labeling large volumes of ophthalmic images across various modalities encounters several real-world challenges, especially for rare diseases. Here, we introduce EyeDiff, a text-to-image model designed to generate multimodal ophthalmic images from natural language prompts and evaluate its applicability in diagnosing common and rare diseases. EyeDiff is trained on eight large-scale datasets using the advanced latent diffusion model, covering 14 ophthalmic image modalities and over 80 ocular diseases, and is adapted to ten multi-country external datasets. The generated images accurately capture essential lesional characteristics, achieving high alignment with text prompts as evaluated by objective metrics and human experts. Furthermore, integrating generated images significantly enhances the accuracy of detecting minority classes and rare eye diseases, surpassing traditional oversampling methods in addressing data imbalance. EyeDiff effectively tackles the issue of data imbalance and insufficiency typically encountered in rare diseases and addresses the challenges of collecting large-scale annotated images, offering a transformative solution to enhance the development of expert-level diseases diagnosis models in ophthalmic field.

show abstract

EyeDiff: text-to-image diffusion model improves rare eye disease diagnosis

Chen,

Zhang,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Improving visual outcomes in patients with rare paediatric eye diseases

Ng,

Tan,

Sundar

2023

Ann Acad Med Singap

View full text Add to dashboard Cite

Introduction: Rare paediatric eye diseases (RPEDs) threaten both vision and life. Recently, rare diseases were recognised as a global public health agenda, with children specified as a priority in the World Health Organization’s VISION 2020 against avoidable visual loss. Method: We conducted a review through a query of online databases (PubMed, Embase and Cochrane Library). Articles related to RPEDs were selected based on relevance by 2 authors, with any disagreements adjudicated by the third author. Results: We synthesise the current state of knowledge regarding RPEDs, barriers to their care, and recommendations for the future. RPEDs often result in significant visual loss, profoundly impacting the way children comprehend and participate in the world. These diseases may also reduce life expectancy and even be life-threatening. Barriers to the care of RPEDs include an unclear definition of “rare diseases”, missed or delayed diagnosis, inadequate knowledge and expertise in management, and challenging research environments. Conclusion: Our findings provide an update on the diagnosis and management of RPEDs, which is of relevance to ophthalmologists, paediatricians, healthcare policymakers and social workers. We propose supportive policies and adequate resource allocation to these diseases, comprehensive and patient-centred care, alongside improved education and training, enhanced research capabilities and continued collaboration across institutions.

show abstract

Overcoming challenges in research and development of rare eye diseases

Cited by 2 publications

References 5 publications

EyeDiff: text-to-image diffusion model improves rare eye disease diagnosis

EyeDiff: text-to-image diffusion model improves rare eye disease diagnosis

Improving visual outcomes in patients with rare paediatric eye diseases

Contact Info

Product

Resources

About