Advancing Automated Phase Recognition in Cataract Surgery through the SICS-155 challenge

@article{MUELLER2026104313,
title = {Advancing Automated Phase Recognition in Cataract Surgery through the SICS-155 challenge},
journal = {Medical Image Analysis},
pages = {104313},
year = {2026},
issn = {1361-8415},
doi = {https://doi.org/10.1016/j.media.2026.104313},
url = {https://www.sciencedirect.com/science/article/pii/S1361841526003828},
author = {Simon Mueller and Bhuvan Sachdeva and Singri Niharika Prasad and Raphael Lechtenboehmer and Frank G Holz and Robert P Finger and Christopher Nielsen and Patrick Gooi and Adrian Gooi and Nils D. Forkert and Yasser El Jarida and Youssef Iraqi and Loubna Mekouar and Yiran Kong and Zhihai Huang and Jiawei Du and Huiqi Li and Lasse Renz-Kiefel and Eric L. Wisotzky and Dong Zheng and Jiacheng Lin and Miao Hu and Yanwu Xu and Mohit Jain and Kaushik Murali and Maximilian W M Wintergerst and Thomas Schultz},
keywords = {Manual Small-Incision Cataract Surgery, Phacoemulsification, Artificial Intelligence, Temporal Action Segmentation, Phase Recognition, Video Dataset, Vision Transformers},
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 an anonym hospital in an LMIC 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.}
}