Direct Cup-to-Disc Ratio Estimation for Glaucoma Screening via Semi-Supervised Learning

• Published in: IEEE journal of biomedical and health informatics 2020-04, Vol.24 (4), p.1104-1113
• Main Authors: Zhao, Rongchang, Chen, Xuanlin, Liu, Xiyao, Chen, Zailiang, Guo, Fan, Li, Shuo
• Format: Article
• Language: English
• Subjects: Adaptive optics; Artificial neural networks; Biomedical optical imaging; Cup-to-disc ratio (CDR); Datasets; Diagnostic Techniques, Ophthalmological; direct estimation; Estimation; Eye diseases; Feature extraction; Glaucoma; Glaucoma - diagnostic imaging; glaucoma screening; Humans; Image Interpretation, Computer-Assisted - methods; Image segmentation; Machine learning; Medical imaging; Neural networks; Optic Disk - diagnostic imaging; Optic nerve; Optical imaging; Optical variables measurement; representation learning; Representations; Screening; Semi-supervised learning; Supervised Machine Learning
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2019.2934477

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The Cup-to-Disc Ratio (CDR) serves as the most important indicator for glaucoma screening and plays a significant role in clinical screening and early diagnosis of glaucoma. In general, obtaining CDR is subjected to measuring on manually or automatically segmented optic disc and cup. Despite great efforts have been devoted, obtaining CDR values automatically with high accuracy and robustness is still a great challenge due to the heavy overlap between optic cup and neuroretinal rim regions. In this paper, a direct CDR estimation method is proposed based on the well-designed semi-supervised learning scheme, in which CDR estimation is formulated as a general regression problem while optic disc/cup segmentation is cancelled. The method directly regresses CDR value based on the feature representation of optic nerve head via deep learning technique while bypassing intermediate segmentation. The scheme is a two-stage cascaded approach comprised of two phases: unsupervised feature representation of fundus image with a convolutional neural networks (MFPPNet) and CDR value regression by random forest regressor. The proposed scheme is validated on the challenging glaucoma dataset Direct-CSU and public ORIGA, and the experimental results demonstrate that our method can achieve a lower average CDR error of 0.0563 and a higher correlation of around 0.726 with measurement before manual segmentation of optic disc/cup by human experts. Our estimated CDR values are also tested for glaucoma screening, which achieves the areas under curve of 0.905 on dataset of 421 fundus images. The experiments show that the proposed method is capable of state-of-the-art CDR estimation and satisfactory glaucoma screening with calculated CDR value.