AUTOMATIC RETINA EXUDATES SEGMENTATION WITHOUT A MANUALLY LABELLED TRAINING SET

Conference · Sat Jan 01 04:00:00 EST 2011

OSTI ID:1003765

Giancardo, Luca ^[1]; Meriaudeau, Fabrice ^[1]; Karnowski, Thomas Paul ^[1]; Li, Yaquin ^[2]; Tobin, Jr, Kenneth William ^[1]; Chaum, Edward ^[2]

---

1. ORNL
2. University of Tennessee, Knoxville (UTK)

Diabetic macular edema (DME) is a common vision threatening complication of diabetic retinopathy which can be assessed by detecting exudates (a type of bright lesion) in fundus images. In this work, two new methods for the detection of exudates are presented which do not use a supervised learning step and therefore do not require ground-truthed lesion training sets which are time consuming to create, difficult to obtain, and prone to human error. We introduce a new dataset of fundus images from various ethnic groups and levels of DME which we have made publicly available. We evaluate our algorithm with this dataset and compare our results with two recent exudate segmentation algorithms. In all of our tests, our algorithms perform better or comparable with an order of magnitude reduction in computational time.

• Research Organization: Oak Ridge National Laboratory (ORNL)
• Sponsoring Organization: ME USDOE - Office of Management, Budget, and Evaluation; ORNL work for others
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1003765
• Country of Publication: United States
• Language: English

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
99 GENERAL AND MISCELLANEOUS
ALGORITHMS
DETECTION
EDEMA
LEARNING
MINORITY GROUPS
RETINA
TRAINING
VISION