Title of Paper:ECLNet: Center localization of eye structures based on Adaptive Gaussian Ellipse Heatmap

Hits:

Affiliation of Author(s):[1]Taiyuan Univ Technol, Coll Elect & Power Engn, Taiyuan 030024, Peoples R China;[2]Univ Elect Sci & Technol China, Sch Elect Sci & Engn, Chengdu 611731, Peoples R China;[3]Beijing Univ Chinese Med, Affiliated Hosp 3, Beijing 100029, Peoples R China;[4]Taiyuan Univ Technol, Coll Informat & Comp, Jinzhong 030600, Peoples R China

Journal:COMPUTERS IN BIOLOGY AND MEDICINE

Key Words:Deep learning; Center localization; Gaussian heatmap; Medical image

Abstract:Accurately localizing the center of specific biological structures in medical images is of great significance for clinical treatment. The center localization task can be viewed as an estimation problem of keypoints, and the heatmap is often used to describe the probability of the location of keypoints during estimation. Existing methods construct the heatmap from a Gaussian kernel function with a fixed standard deviation, therefore cannot adapt to morphologic changes of the target region. In this paper, we build a deep network, ECLNet, to localize the center of eye-related structures in medical images. Meanwhile, we propose a method called Adaptive Gaussian Ellipse Heatmap (AGEH), which can efficiently utilize the gradient feature of the target region to adjust the morphology of the heatmap. The ECLNet localizes the optic disc and fovea center with mean Euclidean Distance of 17.995 and 39.446 pixels, respectively, for IDRiD dataset. The ECLNet also successfully localizes the eye center with the mean absolute Position Error of 0.186 +/- 0.027 mm for CATARACT dataset. The results show that our proposed method has a better performance compared with some state-of-the-art methods.

Document Type:Article

Volume:153

ISSN No.:0010-4825

Translation or Not:no