An Unsupervised Learning Approach Based on Hopfield-like Network for Assessing Posterior Capsule Opacification

Posterior Capsule Opacification (PCO) is the commonest complication of cataract surgery occurring in up to 50% of patients by 2 to 3 years after the operation [1]. This paper proposes a new approach for the assessment of PCO digital images. The approach deploys an unsupervised learning technique for clustering image pixels into different regions based on chromatic attributes. The innovation aspect of this paper, is proposing the number of regions in a clustered image as measurement tool for assessing the PCO. The approach exhibits robustness and stability that would contribute in providing a systematic and objective assessment.