PALM: PAthoLogic Myopia Challenge

PALM: PAthoLogic Myopia Challenge

Citation Author(s):
Huazhu
Fu
Inception Institute of Artificial Intelligence
Fei
Li
Zhongshan Ophthalmic Center, Sun Yat-sen University, China.
José Ignacio
Orlando
Medical University of Vienna, Austria
Hrvoje
Bogunović
Medical University of Vienna, Austria
Xu
Sun
Baidu Inc., China
Jingan
Liao
South China University of Technology, China
Yanwu
Xu
Baidu Inc., China
Shaochong
Zhang
Zhongshan Ophthalmic Center, Sun Yat-sen University, China
Xiulan
Zhang
Zhongshan Ophthalmic Center, Sun Yat-sen University, China
Submitted by:
Huazhu Fu
Last updated:
Thu, 07/18/2019 - 23:43
DOI:
10.21227/55pk-8z03
Links:
License:
Dataset Views:
65
Share / Embed Cite
Abstract: 

Pathologic Myopia Challenge (PALM), as a part of the serial challenge iChallenge, is organized as a half day Challenge, a Satellite Event of the ISBI 2019 conference in Venice, Italy. The PALM challenge focuses on the investigation and development of algorithms associated with the diagnosis of Pathological Myopia (PM) and segmentation of lesions in fundus photos from PM patients. The goal of the challenge is to evaluate and compare automated algorithms for the detection of pathological myopia on a common dataset of retinal fundus images. In PALM challenge, we provide 1200 images with annotations as 400 training images, 400 validation images, and 400 test images. Challenge Homepage: https://palm.grand-challenge.org

Instructions: 

Challenge Homepage: https://palm.grand-challenge.org

 

Tasks

 

Task 1: Classification of PM and non-PM (including HM: high myopia and normal) fundus images.

 

Description: The reference standard for PM presence obtained from the health records, which is not based on fundus image ONLY, but also take OCT, Visual Test, and other facts into consideration. For training data, PM, HM and normal labels (a.k.a. the reference standard) are reflected in the image file names.

 

The classification results should be provided in a single CSV file, named “classification_results.csv”, with the first column corresponding to the filename of the test fundus image (including the extension “.jpg”) and the second column containing the estimated classification probability/risk of the image belonging to a patient diagnosed with PM (value from 0.0 to 1.0).

 

Task 2: Detection and segmentation of disc.

 

Description: Manual pixel-wise annotations of the optic disc were obtained by SEVEN independent OPHTHALMOLOGISTS from Zhongshan Ophthalmic Center, Sun Yat-sen University, China. The reference standard for the segmentation task was created from the seven annotations, which were merged into single annotation by another SENIOR SPECIALIST. It is stored as a BMP image with the same size as the corresponding fundus image with the following labels: 0-Optic Disc (Black color) and 255-Others (White color)

 

The segmentation results should be provided in a “disc segmentation” folder, as one image per test image, with the segmented pixels labeled in the same way as in the reference standard (8bit bmp files with 0: optic disc, 255: elsewhere). Please, make sure that your submitted segmentation files are named according to the original image names and with the same extension.

 

Task 3: Localization of fovea.

 

Description: Manual annotations of the fovea were obtained by SEVEN independent OPHTHALMOLOGISTS from Zhongshan Ophthalmic Center, Sun Yat-sen University, China.

 

The localization results should be provided in a single CSV file, named “fovea_location_results.csv”, with the first column corresponding to the filename of the test fundus image (including the extension “.jpg”), the second column containing the X-coordinate and the third column containing the Y-coordinate. Please, make sure that your submitted segmentation files are named according to the original image names and with the same extension.

 

 

Task 4: Detection & Segmentation of retinal lesions ( atrophy and detachment) from fundus images.

 

Description: Two typical kinds of lesions related to PM are annotated on each image.

Dataset Files

No Data files have been uploaded.

Embed this dataset on another website

Copy and paste the HTML code below to embed your dataset:

Share via email or social media

Click the buttons below:

facebooktwittermailshare
[1] Huazhu Fu, Fei Li, José Ignacio Orlando, Hrvoje Bogunović, Xu Sun, Jingan Liao, Yanwu Xu, Shaochong Zhang, Xiulan Zhang, "PALM: PAthoLogic Myopia Challenge", IEEE Dataport, 2019. [Online]. Available: http://dx.doi.org/10.21227/55pk-8z03. Accessed: Aug. 20, 2019.
@data{55pk-8z03-19,
doi = {10.21227/55pk-8z03},
url = {http://dx.doi.org/10.21227/55pk-8z03},
author = {Huazhu Fu; Fei Li; José Ignacio Orlando; Hrvoje Bogunović; Xu Sun; Jingan Liao; Yanwu Xu; Shaochong Zhang; Xiulan Zhang },
publisher = {IEEE Dataport},
title = {PALM: PAthoLogic Myopia Challenge},
year = {2019} }
TY - DATA
T1 - PALM: PAthoLogic Myopia Challenge
AU - Huazhu Fu; Fei Li; José Ignacio Orlando; Hrvoje Bogunović; Xu Sun; Jingan Liao; Yanwu Xu; Shaochong Zhang; Xiulan Zhang
PY - 2019
PB - IEEE Dataport
UR - 10.21227/55pk-8z03
ER -
Huazhu Fu, Fei Li, José Ignacio Orlando, Hrvoje Bogunović, Xu Sun, Jingan Liao, Yanwu Xu, Shaochong Zhang, Xiulan Zhang. (2019). PALM: PAthoLogic Myopia Challenge. IEEE Dataport. http://dx.doi.org/10.21227/55pk-8z03
Huazhu Fu, Fei Li, José Ignacio Orlando, Hrvoje Bogunović, Xu Sun, Jingan Liao, Yanwu Xu, Shaochong Zhang, Xiulan Zhang, 2019. PALM: PAthoLogic Myopia Challenge. Available at: http://dx.doi.org/10.21227/55pk-8z03.
Huazhu Fu, Fei Li, José Ignacio Orlando, Hrvoje Bogunović, Xu Sun, Jingan Liao, Yanwu Xu, Shaochong Zhang, Xiulan Zhang. (2019). "PALM: PAthoLogic Myopia Challenge." Web.
1. Huazhu Fu, Fei Li, José Ignacio Orlando, Hrvoje Bogunović, Xu Sun, Jingan Liao, Yanwu Xu, Shaochong Zhang, Xiulan Zhang. PALM: PAthoLogic Myopia Challenge [Internet]. IEEE Dataport; 2019. Available from : http://dx.doi.org/10.21227/55pk-8z03
Huazhu Fu, Fei Li, José Ignacio Orlando, Hrvoje Bogunović, Xu Sun, Jingan Liao, Yanwu Xu, Shaochong Zhang, Xiulan Zhang. "PALM: PAthoLogic Myopia Challenge." doi: 10.21227/55pk-8z03