Deep learning-enabled prediction of surgical errors during cataract surgery: from simulation to real-world application

Real-time prediction of technical errors from cataract surgical videos can be highly beneficial, particularly for telementoring, which involves remote guidance and mentoring through digital platforms. However, the rarity of surgical errors makes their detection and analysis challenging using artificial intelligence. To tackle this issue, we leveraged videos from the EyeSi Surgical cataract surgery simulator to learn to predict errors and transfer the acquired knowledge to real-world surgical contexts. By employing deep learning models, we demonstrated the feasibility of making real-time predictions using simulator data with a very short temporal history, enabling on-the-fly computations. We then transferred these insights to real-world settings through unsupervised domain adaptation, without relying on labeled videos from real surgeries for training, which are limited. This was achieved by aligning video clips from the simulator with real-world footage and pre-training the models using pretext tasks on both simulated and real surgical data. For a 1-second prediction window on the simulator, we achieved an overall AUC of 0.820 for error prediction using 600$\times$600 pixel images, and 0.784 using smaller 299$\times$299 pixel images. In real-world settings, we obtained an AUC of up to 0.663 with domain adaptation, marking an improvement over direct model application without adaptation, which yielded an AUC of 0.578. To our knowledge, this is the first work to address the tasks of learning surgical error prediction on a simulator using video data only and transferring this knowledge to real-world cataract surgery.

Mapping the ocular surface from monocular videos with an application to dry eye disease grading

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