PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 8759263

Spatial classification of glaucomatous visual field loss.

D B Henson·S E Spenceley·D R Bull
View original source ↗Export metadata ↓

Abstract

AIMS: To develop and describe an objective classification system for the spatial patterns of visual field loss found in glaucoma. METHODS: The 560 Humphrey visual field analyser (program 24-2) records were used to train an artificial neural network (ANN). The type of network used, a Kohonen self organising feature map (SOM), was configured to organise the visual field defects into 25 classes of superior visual field loss and 25 classes of inferior visual field loss. Each group of 25 classes was arranged in a 5 by 5 map. RESULTS: The SOM successfully classified the defects on the basis of the patterns of loss. The maps show a continuum of change as one moves across them with early loss at one corner and advanced loss at the opposite corner. CONCLUSIONS: ANNs can classify visual field data on the basis of the pattern of loss. Once trained the ANN can be used to classify longitudinal visual field data which may prove valuable in monitoring visual field loss.

Explore related subjects

GlaucomaHumansNeural Networks, ComputerVision DisordersVisual Field TestsVisual FieldsJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

D B Henson, S E Spenceley, D R Bull. 1996. Spatial classification of glaucomatous visual field loss.. https://doi.org/10.1136/bjo.80.6.526

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2006

Do scleral flap dimensions influence reliability of intraocular pressure control in experimental trabeculectomy?

AIM: To compare the effect on intraocular pressure (IOP) of large vs small scleral flap size during trabeculectomy using adjustable sutures. METHODS: Trabeculectomy operations were performed on nine donor human eyes connected to a constant flow infusion with real-time IOP monitoring. Large scleral flaps (4 x 4 mm, 16 mm(2), n=12) or small scleral flaps (3 x 2 mm, 6 mm(2), n=9) were constructed over 0.76 mm(2) sclerostomies. For each procedure, equilibrium IOP was measured following tight closure with two four-throw adjustable 10-0 nylon sutures. RESULTS: Five scleral flaps were thin or poorly constructed; four of these were in the initial seven procedures, implying learning effect. These had a mean absolute IOP of 7.6 mmHg (range 2.7-12.4 mmHg) and mean relative IOP of 28.3% of baseline (range 10-45.8%) after closure. In the remaining 16 good quality procedures, mean IOP was 1.3 mmHg (range 0-3.4 mmHg) after sclerostomy, confirming minimal outflow resistance before closure. Following flap closure mean IOP was 20 mmHg (SD 4.4, range 15.5-29.3 mmHg) for large (n=8), and 18.7 mmHg (SD 3.6, 15.9-25.8 mmHg) for small (n=8) flaps (unpaired t-test, P=0.26). Mean IOP (% baseline) was 71.6% (SD 8.4, range 60.6-86.6%) and 66% (SD=12.7, 46.8-86.6%) for large and small flap groups, respectively (unpaired t-test, P=0.2). CONCLUSIONS: Well-constructed scleral flaps of both sizes were able to support an average IOP at least two-thirds of baseline, and both had similar absolute IOP levels. Errors in flap construction resulted in loss of IOP control. Smaller flap size does not appear to compromise control of early postoperative IOP using adjustable sutures.

Glaucoma↗