@InProceedings{10.1007/978-3-030-00949-6_28,

author="Sun, Xu
and Xu, Yanwu
and Tan, Mingkui
and Fu, Huazhu
and Zhao, Wei
and You, Tianyuan
and Liu, Jiang",

editor="Stoyanov, Danail
and Taylor, Zeike
and Ciompi, Francesco
and Xu, Yanwu
and Martel, Anne
and Maier-Hein, Lena
and Rajpoot, Nasir
and van der Laak, Jeroen
and Veta, Mitko
and McKenna, Stephen
and Snead, David
and Trucco, Emanuele
and Garvin, Mona K.
and Chen, Xin Jan
and Bogunovic, Hrvoje",

title="Localizing Optic Disc and Cup for Glaucoma Screening via Deep Object Detection Networks",

booktitle="Computational Pathology and Ophthalmic Medical Image Analysis",

year="2018",

publisher="Springer International Publishing",

address="Cham",

pages="236--244",

abstract="Segmentation of the optic disc (OD) and optic cup (OC) from a retinal fundus image plays an important role for glaucoma screening and diagnosis. However, most existing methods only focus on pixel-level representations, and ignore the high level representations. In this work, we consider the high level concept, i.e., objectness constraint, for fundus structure analysis. Specifically, we introduce a deep object detection network to localize OD and OC simultaneously. The end-to-end architecture guarantees to learn more discriminative representations. Moreover, data from a similar domain can further contributes to our algorithm through transfer learning techniques. Experimental results show that our method achieves state-of-the-art OD and OC segmentation/localization results on ORIGA dataset. Moreover, the proposed method also obtains satisfactory glaucoma screening performance with the calculated vertical cup-to-disc ratio (CDR).",
isbn="978-3-030-00949-6"
}