Imaging and Predictive Modelling of Proliferative Vitreoretinopathy.

Identification of Imaging Biomarkers and Predictive Modelling of Proliferative Vitreoretinopathy Using Deep Learning.

Patients with retinal detachment are at risk of recurrence and failure of surgery requiring multiple surgeries due to a condition called proliferative vitreoretinopathy (PVR).

Study aims to help tailor patients' treatments and improve outcomes by:

[i] studying imaging biomarkers of PVR, and [ii] develop AI models for PVR detection.

Inclusion:

• Patients with 'complicated' retinal detachment with PVR recruited to a phase 1 dose-finding trial called MORPH-1.
• Patients with 'simple' retinal detachment without PVR recruited to a PhD study.

Non -invasive multimodal imaging and anonymized imaging will be used to study imaging biomarkers of PVR and develop deep learning models to predict PVR in collaboration with an artificial intelligence (AI) expert team at UCL Institute of Ophthalmology.

Inclusion Criteria:

• MORPH-1 and Cohort-NHS study imaging

Exclusion Criteria:

• Participants from above studies who have not consented for image analysis and AI related analysis.