Dr. ADITYA ANAND

Abstract

PURPOSE: To automatically detect and measure pathologic features in images of the eye by use of Simple automated detectors,Basic machine learning, Advanced machine learning, Deep learning with convolutional neural networks, Disease feature based versus image based learning.

METHOD: By use of IDx-DR device,Ladas IOL formula, fundus camera, OCT images and corneal topography scans.

RESULT: For ARMD, the algorithm predictions is based on the SRF volume in the central 3 mm during the first 2 months after therapy initiation,and it has an accuracy of 70%.IDx-DR is not intended to evaluate rapidly PDR.Google Brain taught itself to accurately detect DR&DME in fundus photographs. The IDx-DR was able to detect mtmDR at a sensitivity of 87.4% and a specificity of 89.5%.

CONCLUSION: It is a valuable research tool.There is definitely a huge role in research, for hypothesis generation and discovery.Augmentation,not replacement,of specialists. Final decisions and management will depend on specialists.