|
مقاله
|
Abstract
|
|
|
Title:
|
Plus Disease detection with a novel automated algorithm
|
Author(s):
|
Elyas Khalili Pour M.D Hamid Reza Pour Reza Ph.D Amir Hossein Gharib M.D Mahla Shadravan M.D Arash Mir Mohammad Sadeghi M.D Reza Karkhaneh M.D Ramak Rouhi Pour M.D Mohammad Riazi Esfahani M.D
|
Presentation Type:
|
Poster
|
Subject:
|
Posterior Segment and Uveitis
|
Others:
|
|
Presenting Author:
|
|
Name:
|
Elyas Khalili pour
|
Affiliation :(optional)
|
Farabi Eye Hospital - Tehran University of Medical Sciences
|
E mail:
|
ekhalilipour@gmail.com
|
Phone:
|
|
Mobile:
|
09113727471
|
|
|
Purpose:
|
to design a software with a novel algorithm which analyzes the tortuosity and vascular dilatation in fundus images of ROP patients with an acceptable accuracy for detecting plus disease.
|
Methods:
|
87 well focused fundus images taken with Retcam were classified to three groups of plus, non-plus and pre-plus by agreement between 3 ROP experts. Automated algorithms in this study designed based on two methods: the curvature measure and distance transform for assessment of tortuosity and vascular dilatation, respectively as two major parameters of Plus disease detection.
|
Results:
|
38 plus, 37 pre-plus and 12 non-plus images that have been classified by 3 experts tested by automated algorithm and evaluation of software in correct grouping of images in comparison to experts votes with three different classifiers, k-Nearest Neighbor, Support Vector Machine (SVM) and Multilayer Perceptron Network, showed 72.3 , 83.7 and 84.4 % accuracy, respectively.
|
Conclusion:
|
New Automated Algorithm used in this pilot scheme for diagnosis and screening of patients with Plus ROP, has acceptable Accuracy and in the future with more improvements it can be used especially in centers without a skilled person in the ROP field.
|
Attachment:
|
5965.pptx
|
|