Mapping the ocular surface from monocular videos with an application to dry eye disease grading
This work addresses the need for objective and reproducible diagnosis of Dry Eye Disease, a common ophthalmological condition, by introducing a novel video-based approach, though it is domain-specific and incremental in its method.
The paper tackles the problem of subjective and non-reproducible diagnosis of Dry Eye Disease by proposing a method to track the ocular surface in 3-D from monocular videos and grade severity, achieving a mean Euclidean tracking error as low as 0.48% of image width and improving classification by a 0.20 AUC difference.
With a prevalence of 5 to 50%, Dry Eye Disease (DED) is one of the leading reasons for ophthalmologist consultations. The diagnosis and quantification of DED usually rely on ocular surface analysis through slit-lamp examinations. However, evaluations are subjective and non-reproducible. To improve the diagnosis, we propose to 1) track the ocular surface in 3-D using video recordings acquired during examinations, and 2) grade the severity using registered frames. Our registration method uses unsupervised image-to-depth learning. These methods learn depth from lights and shadows and estimate pose based on depth maps. However, DED examinations undergo unresolved challenges including a moving light source, transparent ocular tissues, etc. To overcome these and estimate the ego-motion, we implement joint CNN architectures with multiple losses incorporating prior known information, namely the shape of the eye, through semantic segmentation as well as sphere fitting. The achieved tracking errors outperform the state-of-the-art, with a mean Euclidean distance as low as 0.48% of the image width on our test set. This registration improves the DED severity classification by a 0.20 AUC difference. The proposed approach is the first to address DED diagnosis with supervision from monocular videos