System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Ppublish

PubMed: 42777601 DOI: 10.1016/j.media.2026.104313

Advancing automated phase recognition in cataract surgery through the SICS-155 challenge.

Med Image Anal 115:104313

Authors: Simon Mueller, Bhuvan Sachdeva, Singri Niharika Prasad, Raphael Lechtenboehmer, Frank G Holz, Robert P Finger, Christopher Nielsen, Patrick Gooi, Adrian Gooi, Nils D Forkert, Yasser El Jarida, Youssef Iraqi, Loubna Mekouar, Yiran Kong, Zhihai Huang, Jiawei Du, Huiqi Li, Lasse Renz-Kiefel, Eric L Wisotzky, Dong Zheng, Jiacheng Lin, Miao Hu, Yanwu Xu, Mohit Jain, Kaushik Murali, Maximilian W M Wintergerst, Thomas Schultz

Affiliations

  • B-IT and Department of Computer Science, University of Bonn, Bonn, Germany; Department of Ophthalmology, University Hospital Bonn, Bonn, Germany.
  • Microsoft Research, Bengaluru, India; Sankara Eye Hospital, Bengaluru, Karnataka, India.
  • Sankara Eye Hospital, Bengaluru, Karnataka, India.
  • Department of Ophthalmology, University Hospital Bonn, Bonn, Germany.
  • Department of Ophthalmology, University Medical Center Mannheim, Heidelberg University, Germany.
  • Cumming School of Medicine, University of Calgary, Calgary, Canada; Biomedical Engineering Program, University of Calgary, Calgary, Canada.
  • Department of Ophthalmology, University of Calgary, Calgary, Canada.
  • Max Rady College of Medicine, University of Manitoba, Winnipeg, Canada; Department of Otolaryngology, University of British Columbia, Vancouver, Canada; School of Medicine, Simon Fraser University, Burnaby, Canada.
  • Department of Radiology, University of Calgary, Calgary, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; Alberta Children's Hospital Research Institute, University of Calgary, Calgary, Canada.
  • College of Computing, University Mohammed VI Polytechnic, Morocco.
  • School of Information and Electronics, Beijing Institute of Technology, Beijing, China.
  • Computer Vision and Graphics, Vision and Imaging Technologies, Fraunhofer HHI, Berlin, Germany; Klinik und Poliklinik für Hals-Nasen-Ohrenheilkunde, Kopf- und Halschirurgie Otto Körner, Universitätsmedizin Rostock, Germany.
  • Computer Vision and Graphics, Vision and Imaging Technologies, Fraunhofer HHI, Berlin, Germany; Visual Computing, Humboldt University of Berlin, Berlin, Germany.
  • Hang Zhou Dianzi University, Hangzhou, Zhejiang, China.
  • South China University of Technology, Guangdong, China.
  • Microsoft Research, Bengaluru, India.
  • Department of Ophthalmology, University Hospital Bonn, Bonn, Germany; Augenzentrum Grischun, Chur, Switzerland.
  • B-IT and Department of Computer Science, University of Bonn, Bonn, Germany; Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany.

Abstract

Manual Small-Incision Cataract Surgery (SICS) is a prevalent technique in low- and middle-income countries (LMICs). Automated analysis of SICS videos based on artificial intelligence (AI) would benefit self-evaluation, training, monitoring, and ultimately facilitate computer aided surgical assistance. However, this procedure remains understudied in terms of automated surgical analysis due to a lack of publicly available data. To advance this field, we organized the SICS-155 phase recognition challenge at MICCAI 2025. It was based on a dataset with 155 videos recorded at Sankara Eye Hospital in Bengaluru, India with an average duration of 13:05 minutes, annotated with 19 distinct surgical phases. In this work, we first present the results and findings of that challenge in accordance with the BIAS guidelines. Second, we integrated key technical innovations from the participating teams to develop a new, state-of-the-art approach for phase recognition in a post-operative, offline setting. This approach uses a boundary-aware FACT architecture, which we evaluated using videos of both SICS and phacoemulsification. Our approach achieved an accuracy of 87.98% [95%-CI: ±2.06], an edit score of 90.80% [95%-CI: ±1.47], and a segmental F1-score of 89.56% [95%-CI: ±1.92] on the SICS-155 challenge dataset, as well as an accuracy of 97.61%/ 93.36%, a precision of 98.42%/ 95.27%, and a recall of 97.97%/ 93.32% on the Cataract-101 phacoemulsification public dataset (depending on the data split). Building on these promising results, our future work will investigate potential real-time quality assessment and complication recognition in SICS and facilitate the development of clinical training and surgical quality monitoring software for ophthalmologists in LMICs.

MeSH

Phacoemulsification, Work, Cataract, Artificial Intelligence