Akshi IMAGE - A Retinal Fundus Image Database for Glaucoma Detection

Citation Author(s):
Harish Kumar
J R
Department of Electrical and Electronics Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal - 576104, Karnataka, India
Chandra Sekhar
Seelamantula
Department of Electrical Engineering, Indian Institute of Science, Bangalore 560012, India
Gagan
J H
Department of Electrical and Electronics Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal - 576104, Karnataka, India
Yogish
S Kamath
Department of Ophthalmology , Kasturba Medical College, Manipal Academy of Higher Education, Manipal - 576104, Karnataka, India
Neetha
I R Kuzhuppilly
Department of Ophthalmology , Kasturba Medical College, Manipal Academy of Higher Education, Manipal - 576104, Karnataka, India
Vivekanand
U
Department of Ophthalmology, ASRAM, Eluru−534005, India
Preeti
Gupta
Department of Ophthalmology, Dr. Ram Manohar Lohia Institute of Medical Sciences, Lucknow−226010, India
Shilpa
Patil
Aastha Superspeciality Eye Hospital, Banashankari, Bangalore - 560085, India
Submitted by:
HARISH KUMAR JA...
Last updated:
DOI:
10.21227/ktzx-a222
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

Akshi IMAGE, a new Indian ethnicity retinal fundus image database, has been established for the evaluation of computer-assisted glaucoma prescreening methods. ‘Akshi’ is a Sanskrit word for the ‘Eye’ and ‘IMAGE’ is an acronym for IISc-MAHE Glaucoma Evaluation database. This database is a result of an interdisciplinary collaboration between Indian Institute of Science (IISc) and Manipal Academy of Higher Education (MAHE). The database consists of retinal color fundus images acquired using three different devices. Five expert ophthalmologists provided the optic disc (OD) and optic cup (OC) ground-truth for the evaluation of segmentation performance and a binary decision (normal/glaucomatous). The uncompressed and compressed versions of the size of the database are about 230 GB and 12 GB, respectively.

Akshi IMAGE consists of 1345 retinal fundus images stored in JPEG/PNG format, with 8 bits per color channel, acquired using three devices: Remidio non-mydriatic Fundus-on-Phone camera with a resolution of 2448×3264 pixels (1074 images), Forus 3Nethra Classic non-mydriatic fundus camera with a resolution of 2048×1536 pixels (126 images), and a Bosch handheld fundus camera with a resolution of 1920×1440 pixels (145 images). This is by far the largest Indian ethnicity-specific fundus image database. Most of the images acquired by these devices are OD-centered and particular to the assessment of OD and glaucoma. The patient’s personal information was anonymized. Five expert ophthalmologists provided manual OD and OC annotations and a decision on whether the subject is glaucoma suspect or not. Their experience ranges from 5 to 15 years. 

 The entire database of 1345 fundus images is divided into training and test subsets comprising 1050 images and 295 images, respectively. The train and test subsets are approximately in the ratio of 3:1 for fundus images. The database provides information about OD and OC height/width/area, and neuroretinal rim area leading to the computation of clinically relevant glaucoma parameters such as vertical cup-to-disc ratio (VCDR), horizontal cup-to-disc ratio (HCDR), and area cup-to-disc ratio (ACDR) from the experts’ annotations.  

Instructions: 

File Structure

 1.0_Original_Fundus_Images  (contains original fundus images)

-Bosch 

-Forus

-Remedio  

 2.0_Doctors_Annotations (contains expert annotations of optic disc and optic cup)   

-Expert 1         

-Expert 2         

-Expert 3         

-Expert 4         

-Expert 5  

 3.0_Doctors_Annotations_Binary_OD_OC  (contains binary segmentation of optic disc and optic cup)

-Expert 1         

-Expert 2 

-Expert 3         

-Expert 4         

-Expert 5  

 4.0_OD_OC_Fusion_Images (contains binary images of optic disc and optic cup fused into one)

-Expert 1         

-Expert 2         

-Expert 3

-Expert 4         

-Expert 5  

 5.0_OD_OC_Mean_Majority_Median     

-Bosch  

-Forus

-Remedio 

This folder contains the overlay, mean, majority, and median binary images obtained from the binary images of doctors' annotations.  

 6.0_Glaucoma_Decision           

-Expert 1         

-Expert 2         

-Expert 3

-Expert 4         

-Expert 5         

-Glaucoma_decision_comparision  This folder contains the glaucoma decision of several experts and a comparison of the decisions.

Terms of usage

The database can be downloaded and used for research purposes only. Users of the database are not allowed to redistribute or modify it. Due acknowledgment and citation are expected from the users of this database.

 

Funding Agency: 
1. IMPRINT- India (Project id: 6013), 2. Science and Engineering Research Board (SERB) – Teachers Associateship for Research Excellence (TARE) fellowship (Project id: TAR/2019/000037)

Comments

The authors would like to thank IEEE DataPort for hosting the 'Akshi IMAGE' database.
The authors would like to thank Manipal Academy of Higher Education (MAHE) for giving permission to acquire retinal fundus images at its constituent institutions. Thanks to all the subjects for consenting and taking part in the fundus examination.
The authors would like to thank Remidio Innovative Solutions Pvt. Ltd., Forus Health Pvt. Ltd., and Bosch Eye Care Solutions, Bengaluru, Karnataka, India, for the support provided during fundus image acquisition using their fundus imaging devices.
The authors would like to thank Subramanya Jois, Harsha Sridhar, Harshit Shirsat, and Aniketh Manjunath for insightful technical discussions and also for being part of the data acquisition and curating activity.

Submitted by HARISH KUMAR JA... on Wed, 06/08/2022 - 08:21

-

Submitted by HARISH KUMAR JA... on Wed, 06/08/2022 - 08:22

-

Submitted by HARISH KUMAR JA... on Thu, 06/16/2022 - 01:52

Dataset Files

  • (0 bytes)
  • (0 bytes)
LOGIN TO ACCESS DATASET FILES

Documentation

AttachmentSize
File bytes