Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.16371 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917465708036096 |
|---|---|
| author | Ahmadi, Mohammad Javad Gandomi, Iman Abdi, Parisa Mohammadi, Seyed-Farzad Taslimi, Amirhossein Khodaparast, Mehdi Hashemi, Hassan Tavakoli, Mahdi Taghirad, Hamid D. |
| author_facet | Ahmadi, Mohammad Javad Gandomi, Iman Abdi, Parisa Mohammadi, Seyed-Farzad Taslimi, Amirhossein Khodaparast, Mehdi Hashemi, Hassan Tavakoli, Mahdi Taghirad, Hamid D. |
| contents | Computer-assisted surgery research requires large, deeply annotated video datasets that capture clinical and technical variability. Existing cataract surgery resources lack the diversity and annotation depth required to train generalizable deep-learning models. To address this gap, we present a dataset of 3,000 phacoemulsification cataract surgery videos acquired at two surgical centers from surgeons with varying expertise. The dataset provides four annotation layers: temporal surgical phases, instance segmentation of instruments and anatomical structures, instrument-tissue interaction tracking, and quantitative skill scores based on competency rubrics adapted from ICO-OSCAR and GRASIS. We demonstrate the technical utility of the dataset through benchmarking deep learning models across four tasks: workflow recognition, scene segmentation, instrument-tissue interaction tracking, and automated skill assessment. Furthermore, we establish a domain-adaptation baseline for phase recognition and instance segmentation by training on one surgical center and evaluating on a held-out center. Ultimately, these multi-source acquisitions, multi-layer annotations, and paired skill-kinematic labels facilitate the development of generalizable multi-task models for surgical workflow analysis, scene understanding, and competency-based training research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16371 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis Ahmadi, Mohammad Javad Gandomi, Iman Abdi, Parisa Mohammadi, Seyed-Farzad Taslimi, Amirhossein Khodaparast, Mehdi Hashemi, Hassan Tavakoli, Mahdi Taghirad, Hamid D. Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Computer-assisted surgery research requires large, deeply annotated video datasets that capture clinical and technical variability. Existing cataract surgery resources lack the diversity and annotation depth required to train generalizable deep-learning models. To address this gap, we present a dataset of 3,000 phacoemulsification cataract surgery videos acquired at two surgical centers from surgeons with varying expertise. The dataset provides four annotation layers: temporal surgical phases, instance segmentation of instruments and anatomical structures, instrument-tissue interaction tracking, and quantitative skill scores based on competency rubrics adapted from ICO-OSCAR and GRASIS. We demonstrate the technical utility of the dataset through benchmarking deep learning models across four tasks: workflow recognition, scene segmentation, instrument-tissue interaction tracking, and automated skill assessment. Furthermore, we establish a domain-adaptation baseline for phase recognition and instance segmentation by training on one surgical center and evaluating on a held-out center. Ultimately, these multi-source acquisitions, multi-layer annotations, and paired skill-kinematic labels facilitate the development of generalizable multi-task models for surgical workflow analysis, scene understanding, and competency-based training research. |
| title | Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.16371 |