Visual field (VF) test is a widely used, noninvasive technique for evaluating pathology or dysfunction in the visual pathways. The VF test, in conjunction with other diagnostics, is used for detection of laucoma and for following its progression. Early detection is critical as blindness from glaucoma is preventable in nearly all cases, provided treatment is administered early in the progression. There is a need for an automated decision aid tool that will facilitate and standardize the interpretation task. Following a successful Phase I feasibility demonstration, Phase II will apply novel machine learning approaches to the problem of glaucoma diagnosis via an automated analysis of visual field and ancillary data. IAC will develop an integrated, user friendly software program that will provide a reliable detailed classification of glaucomatous and non-glaucomatous defects with the main emphasis on glaucomatous defects and early detection.
The aim i s to achieve classification accuracy close to that of a highly skilled human expert. The diagnosis suggested by the software will be supported by a set of comprehensive rules extracted from the classification algorithm. Optionally, the program will provide measures of visual field and glaucoma progression.
Wroblewski, Dariusz; Francis, Brian A; Chopra, Vikas et al. (2009) Glaucoma detection and evaluation through pattern recognition in standard automated perimetry data. Graefes Arch Clin Exp Ophthalmol 247:1517-30 |