Medizinische Universität Graz - Research portal

Go directly to the nagivation.
Go directly to the content.

Navigation/Search

Selected Publication:

SHR Neuro Cancer Cardio Lipid Metab Microb

Sokolova, N; Schoeffmann, K; Taschwer, M; Sarny, S; Putzgruber-Adamitsch, D; El-Shabrawi, Y.
Automatic detection of pupil reactions in cataract surgery videos.
PLoS One. 2021; 16(10): e0258390 Doi: 10.1371/journal.pone.0258390 [OPEN ACCESS]
Web of Science PubMed FullText FullText_MUG

Co-authors Med Uni Graz: El-Shabrawi Yosuf; Sarny Stephanie
Altmetrics:
Dimensions Citations:
Plum Analytics:
Scite (citation analytics):
Abstract:: In the light of an increased use of premium intraocular lenses (IOL), such as EDOF IOLs, multifocal IOLs or toric IOLs even minor intraoperative complications such as decentrations or an IOL tilt, will hamper the visual performance of these IOLs. Thus, the post-operative analysis of cataract surgeries to detect even minor intraoperative deviations that might explain a lack of a post-operative success becomes more and more important. Up-to-now surgical videos are evaluated by just looking at a very limited number of intraoperative data sets, or as done in studies evaluating the pupil changes that occur during surgeries, in a small number intraoperative picture only. A continuous measurement of pupil changes over the whole surgery, that would achieve clinically more relevant data, has not yet been described. Therefore, the automatic retrieval of such events may be a great support for a post-operative analysis. This would be especially true if large data files could be evaluated automatically. In this work, we automatically detect pupil reactions in cataract surgery videos. We employ a Mask R-CNN architecture as a segmentation algorithm to segment the pupil and iris with pixel-based accuracy and then track their sizes across the entire video. We can detect pupil reactions with a harmonic mean (H) of Recall, Precision, and Ground Truth Coverage Rate (GTCR) of 60.9% and average prediction length (PL) of 18.93 seconds. However, we consider the best configuration for practical use the one with the H value of 59.4% and PL of 10.2 seconds, which is much shorter. We further investigate the generalization ability of this method on a slightly different dataset without retraining the model. In this evaluation, we achieve the H value of 49.3% with the PL of 18.15 seconds.
Find related publications in this database (using NLM MeSH Indexing): Cataract Extraction - administration & dosage; Lenses, Intraocular - administration & dosage; Pupil - administration & dosage