Statistically Evaluating Detection Capabilities of Sub Retinal Fluid Detection Methodology in Optical Coherence Tomographic Images.

Significance of therapeutic imaging in medical image based diagnostics and treatment, and there in practice implementation in image investigation is undebatable. The cyst (fluid accumulation) development just above the Retinal Pigment Epithelium (RPE) Layer is known as Sub-Retinal Fluid (SRF). This distinct anatomical localization of SRF, differs it from normal cysts. Progressive increase of SRF, adversely affects the visual acuity. Improvement in visual acuity by reduction in SRF is a desired outcome of currently available treatments. In this paper, we assess and evaluate the detection capabilities of the Sub Retinal Fluid (SRF) detection technique through the statistical analytical methodologies. Receiver Operating Characteristic (ROC) curve analysis, projects the system's ability to discriminate between the images with and without pathology (in this research pathology is SRF). Overall Sensitivity and Specificity of the SRF detection technique is 96.2% and 92.9% respectively.