Purpose: Navigated panretinal photocoagulation is a standard care for proliferative diabetic retinopathy. Slit-lamp-based systems used for this treatment provide a narrow view of the retina. Retinal mosaics are used for view expansion and treatment planning. Mosaicing slit-lamp images is a hard task due to the absence of a physical model of the imaging process, large textureless regions and imaging artifacts, mostly reflections.
Methods: We present a comparative study of various geometric transformation models applied to retinal image mosaicing in computer-assisted slit-lamp imaging. We propose an efficient point correspondence-based framework for transformation model evaluation in a typical closed-loop motion scenario. We compare the performance of multiple linear and nonlinear models of different complexities and assess the effect of the number of points used for parameter estimation. We use a local fitting error (LFE) metric to estimate the models' performance in pairwise registration. Because LFE alone is not conclusive regarding the problem of accumulated drift, we propose a loop closure error (LCE) metric to quantify the effect of accumulated local registration errors. We also provide a new normalization procedure for the quadratic transformation model, widely used in retinal image registration.
Results: In total, seven transformation models were evaluated on three datasets of long image sequences. LFE decreases with increasing complexity of the model, while LCE, in contrast, shows superior performance of simple models. Varying the number of point correspondences did not reveal a common trend for the LCE metric, showing an increase in the error for simple models and an unstable behavior of the complex models.
Conclusion: Our results show that simple models are less sensitive to drift and preferable for sequential mosaicing in slit-lamp imaging, while more complex models are the best choice for short-term registration.
Keywords: Drift; Image registration; Model; Mosaicing; Retina; Transformation.