An automatic diagnosis system of nuclear cataract using slit-lamp images

An automatic diagnosis system of nuclear cataract is presented in this paper. Nuclear cataract is graded according to the severity of opacity using slit-lamp lens images. Anatomical structure in the lens image is detected using a modified active shape model (ASM). Based on the anatomical landmark, local features are extracted according to clinical grading protocol. Support vector machine (SVM) regression is employed to train a grading model for grade prediction. The system is tested using clinical images and clinical ground truth. More than five thousands slit-lamp images were tested. The success rate of feature extraction is 95% and the mean grading difference is 0.36. The automatic diagnosis system can help to improve the grading objectivity and save the workload of ophthalmologists.

[1]  Nicola J. Ferrier,et al.  Automated Identification of the Anatomical Features in Slit Lamp Photographs of the Lens , 2002 .

[2]  M. C. Leske,et al.  The Lens Opacities Classification System III , 1993 .

[3]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[4]  Tien Yin Wong,et al.  Towards Automatic Grading of Nuclear Cataract , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  Joo-Hwee Lim,et al.  Image based grading of nuclear cataract by SVM regression , 2008, SPIE Medical Imaging.

[6]  D D Duncan,et al.  New objective classification system for nuclear opacification. , 1997, Journal of the Optical Society of America. A, Optics, image science, and vision.

[7]  D Machin,et al.  Risk factors for nuclear, cortical and posterior subcapsular cataracts in the Chinese population of Singapore: the Tanjong Pagar Survey , 2003, The British journal of ophthalmology.

[8]  T. Wong,et al.  Rationale and Methodology for a Population-Based Study of Eye Diseases in Malay People: The Singapore Malay Eye Study (SiMES) , 2007, Ophthalmic epidemiology.

[9]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[10]  P. Asbell,et al.  Age-related cataract , 2005, The Lancet.

[11]  Gj Johnson.  Cataract: A worldwide perspective , 2001 .

[12]  Huiqi Li,et al.  Boundary detection of optic disk by a modified ASM method , 2003, Pattern Recognit..

[13]  K L Linton,et al.  Assessment of cataracts from photographs in the Beaver Dam Eye Study. , 1990, Ophthalmology.

[14]  Charles R. Dyer,et al.  An Automatic System for Classification of Nuclear Sclerosis from Slit-Lamp Photographs , 2003, MICCAI.