TY - JOUR
T1 - ADAM Challenge
T2 - Detecting Age-Related Macular Degeneration From Fundus Images
AU - Fang, Huihui
AU - Li, Fei
AU - Fu, Huazhu
AU - Sun, Xu
AU - Cao, Xingxing
AU - Lin, Fengbin
AU - Son, Jaemin
AU - Kim, Sunho
AU - Quellec, Gwenole
AU - Matta, Sarah
AU - Shankaranarayana, Sharath M.
AU - Chen, Yi Ting
AU - Wang, Chuen Heng
AU - Shah, Nisarg A.
AU - Lee, Chia Yen
AU - Hsu, Chih Chung
AU - Xie, Hai
AU - Lei, Baiying
AU - Baid, Ujjwal
AU - Innani, Shubham
AU - Dang, Kang
AU - Shi, Wenxiu
AU - Kamble, Ravi
AU - Singhal, Nitin
AU - Wang, Ching Wei
AU - Lo, Shih Chang
AU - Orlando, Jose Ignacio
AU - Bogunovic, Hrvoje
AU - Zhang, Xiulan
AU - Xu, Yanwu
N1 - Publisher Copyright:
© 1982-2012 IEEE.
PY - 2022/10/1
Y1 - 2022/10/1
N2 - Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss caused by this disease is irreversible and permanent. Color fundus photography is the most cost-effective imaging modality to screen for retinal disorders. Cutting edge deep learning based algorithms have been recently developed for automatically detecting AMD from fundus images. However, there are still lack of a comprehensive annotated dataset and standard evaluation benchmarks. To deal with this issue, we set up the Automatic Detection challenge on Age-related Macular degeneration (ADAM), which was held as a satellite event of the ISBI 2020 conference. The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions. As part of the ADAM challenge, we have released a comprehensive dataset of 1200 fundus images with AMD diagnostic labels, pixel-wise segmentation masks for both optic disc and AMD-related lesions (drusen, exudates, hemorrhages and scars, among others), as well as the coordinates corresponding to the location of the macular fovea. A uniform evaluation framework has been built to make a fair comparison of different models using this dataset. During the ADAM challenge, 610 results were submitted for online evaluation, with 11 teams finally participating in the onsite challenge. This paper introduces the challenge, the dataset and the evaluation methods, as well as summarizes the participating methods and analyzes their results for each task. In particular, we observed that the ensembling strategy and the incorporation of clinical domain knowledge were the key to improve the performance of the deep learning models.
AB - Age-related macular degeneration (AMD) is the leading cause of visual impairment among elderly in the world. Early detection of AMD is of great importance, as the vision loss caused by this disease is irreversible and permanent. Color fundus photography is the most cost-effective imaging modality to screen for retinal disorders. Cutting edge deep learning based algorithms have been recently developed for automatically detecting AMD from fundus images. However, there are still lack of a comprehensive annotated dataset and standard evaluation benchmarks. To deal with this issue, we set up the Automatic Detection challenge on Age-related Macular degeneration (ADAM), which was held as a satellite event of the ISBI 2020 conference. The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions. As part of the ADAM challenge, we have released a comprehensive dataset of 1200 fundus images with AMD diagnostic labels, pixel-wise segmentation masks for both optic disc and AMD-related lesions (drusen, exudates, hemorrhages and scars, among others), as well as the coordinates corresponding to the location of the macular fovea. A uniform evaluation framework has been built to make a fair comparison of different models using this dataset. During the ADAM challenge, 610 results were submitted for online evaluation, with 11 teams finally participating in the onsite challenge. This paper introduces the challenge, the dataset and the evaluation methods, as well as summarizes the participating methods and analyzes their results for each task. In particular, we observed that the ensembling strategy and the incorporation of clinical domain knowledge were the key to improve the performance of the deep learning models.
UR - http://www.scopus.com/inward/record.url?scp=85129676571&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85129676571&partnerID=8YFLogxK
U2 - 10.1109/TMI.2022.3172773
DO - 10.1109/TMI.2022.3172773
M3 - Article
C2 - 35507621
AN - SCOPUS:85129676571
SN - 0278-0062
VL - 41
SP - 2828
EP - 2847
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 10
ER -