AUTHOR=Xu Shuai , Yang Xiaoyan , Zhang Shuxian , Zheng Xuan , Zheng Fang , Liu Yin , Zhang Hanyu , Li Lihua , Ye Qing 

TITLE=Evaluation of the corneal topography based on deep learning

JOURNAL=Frontiers in Medicine

VOLUME=Volume 10 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1264659

DOI=10.3389/fmed.2023.1264659

ISSN=2296-858X

ABSTRACT=Purpose: The current paper designed a unique type of corneal topography evaluation method based on deep learning and traditional image processing algorithms. Type of corneal topography of patients was evaluated through the segmentation of important medical zones and the calculation of relevant medical indicators of orthokeratology (OK) lenses. 
Methods: The clinical data of 1302 myopic subjects were collected retrospectively. A series of neural networks-based U-Net were used to segment the pupil and the treatment zone in the corneal topography, and the decentration, effective defocusing contact range and other indicators were calculated according to the image processing algorithm. The type of corneal topography was evaluated according to the evaluation criteria given by the optometrist. Finally, the method described in this paper was used to evaluate the type of corneal topography, and compared with the type classified by the optometrist.
Results: When the important medical zones in the corneal topography were segmented, the precision and recall of the treatment zone reached 0.9587 and 0.9459, respectively, and the precision and recall of the pupil reached 0.9771 and 0.9712. Finally, the method described in this paper was used to evaluate the type of corneal topography. Compared with the type of corneal topography marked by the experienced optometrist, the evaluated results based on deep learning and image processing algorithms showed high accuracy with more than 98%. 
Conclusion: The current paper provided an effective and accurate deep learning algorithm to evaluate the type of corneal topography. Deep learning algorithm played an auxiliary role in the OK lens fitting, which could help optometrists select the parameters of OK lenses effectively.