Cataract-1K Dataset for Deep-Learning-Assisted Analysis of Cataract Surgery Videos.

Autor: Ghamsarian N; Center for Artificial Intelligence in Medicine (CAIM), Department of Medicine, University of Bern, Bern, Switzerland., El-Shabrawi Y; Department of Ophthalmology, Klinikum Klagenfurt, Klagenfurt, Austria., Nasirihaghighi S; Department of Information Technology, University of Klagenfurt, Klagenfurt, Austria., Putzgruber-Adamitsch D; Department of Ophthalmology, Klinikum Klagenfurt, Klagenfurt, Austria., Zinkernagel M; Department of Ophthalmology, Inselspital, Bern, Switzerland., Wolf S; Department of Ophthalmology, Inselspital, Bern, Switzerland., Schoeffmann K; Department of Information Technology, University of Klagenfurt, Klagenfurt, Austria. ks@itec.aau.at., Sznitman R; Center for Artificial Intelligence in Medicine (CAIM), Department of Medicine, University of Bern, Bern, Switzerland.
Jazyk: angličtina
Zdroj: Scientific data [Sci Data] 2024 Apr 12; Vol. 11 (1), pp. 373. Date of Electronic Publication: 2024 Apr 12.
DOI: 10.1038/s41597-024-03193-4
Abstrakt: In recent years, the landscape of computer-assisted interventions and post-operative surgical video analysis has been dramatically reshaped by deep-learning techniques, resulting in significant advancements in surgeons' skills, operation room management, and overall surgical outcomes. However, the progression of deep-learning-powered surgical technologies is profoundly reliant on large-scale datasets and annotations. In particular, surgical scene understanding and phase recognition stand as pivotal pillars within the realm of computer-assisted surgery and post-operative assessment of cataract surgery videos. In this context, we present the largest cataract surgery video dataset that addresses diverse requisites for constructing computerized surgical workflow analysis and detecting post-operative irregularities in cataract surgery. We validate the quality of annotations by benchmarking the performance of several state-of-the-art neural network architectures for phase recognition and surgical scene segmentation. Besides, we initiate the research on domain adaptation for instrument segmentation in cataract surgery by evaluating cross-domain instrument segmentation performance in cataract surgery videos. The dataset and annotations are publicly available in Synapse.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: