Saved in:
Bibliographic Details
Main Authors: Meng, Yan, Cook, Jack, Han, X. Y., Duman, Kaan, Otto, Shauna, Pangal, Dhiraj, Chainey, Jonathan, Lau, Ruth, Masson-Forsythe, Margaux, Donoho, Daniel A., Levy, Danielle, Zada, Gabriel, Froelich, Sébastien, Fernandez-Miranda, Juan, Chang, Mike
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.24897
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917362314248192
author Meng, Yan
Cook, Jack
Han, X. Y.
Duman, Kaan
Otto, Shauna
Pangal, Dhiraj
Chainey, Jonathan
Lau, Ruth
Masson-Forsythe, Margaux
Donoho, Daniel A.
Levy, Danielle
Zada, Gabriel
Froelich, Sébastien
Fernandez-Miranda, Juan
Chang, Mike
author_facet Meng, Yan
Cook, Jack
Han, X. Y.
Duman, Kaan
Otto, Shauna
Pangal, Dhiraj
Chainey, Jonathan
Lau, Ruth
Masson-Forsythe, Margaux
Donoho, Daniel A.
Levy, Danielle
Zada, Gabriel
Froelich, Sébastien
Fernandez-Miranda, Juan
Chang, Mike
contents Accurate surgical phase recognition is essential for analyzing procedural workflows, supporting intraoperative decision-making, and enabling data-driven improvements in surgical education and performance evaluation. In this work, we present a comprehensive framework for phase recognition in pituitary tumor surgery (PTS) videos, combining self-supervised representation learning, robust temporal modeling, and scalable data annotation strategies. Our method achieves 90\% accuracy on a held-out test set, outperforming current state-of-the-art approaches and demonstrating strong generalization across variable surgical cases. A central contribution of this work is the integration of a collaborative online platform designed for surgeons to upload surgical videos, receive automated phase analysis, and contribute to a growing dataset. This platform not only facilitates large-scale data collection but also fosters knowledge sharing and continuous model improvement. To address the challenge of limited labeled data, we pretrain a ResNet-50 model using the self-supervised framework on 251 unlabeled PTS videos, enabling the extraction of high-quality feature representations. Fine-tuning is performed on a labeled dataset of 81 procedures using a modified training regime that incorporates focal loss, gradual layer unfreezing, and dynamic sampling to address class imbalance and procedural variability.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24897
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform
Meng, Yan
Cook, Jack
Han, X. Y.
Duman, Kaan
Otto, Shauna
Pangal, Dhiraj
Chainey, Jonathan
Lau, Ruth
Masson-Forsythe, Margaux
Donoho, Daniel A.
Levy, Danielle
Zada, Gabriel
Froelich, Sébastien
Fernandez-Miranda, Juan
Chang, Mike
Computer Vision and Pattern Recognition
Accurate surgical phase recognition is essential for analyzing procedural workflows, supporting intraoperative decision-making, and enabling data-driven improvements in surgical education and performance evaluation. In this work, we present a comprehensive framework for phase recognition in pituitary tumor surgery (PTS) videos, combining self-supervised representation learning, robust temporal modeling, and scalable data annotation strategies. Our method achieves 90\% accuracy on a held-out test set, outperforming current state-of-the-art approaches and demonstrating strong generalization across variable surgical cases. A central contribution of this work is the integration of a collaborative online platform designed for surgeons to upload surgical videos, receive automated phase analysis, and contribute to a growing dataset. This platform not only facilitates large-scale data collection but also fosters knowledge sharing and continuous model improvement. To address the challenge of limited labeled data, we pretrain a ResNet-50 model using the self-supervised framework on 251 unlabeled PTS videos, enabling the extraction of high-quality feature representations. Fine-tuning is performed on a labeled dataset of 81 procedures using a modified training regime that incorporates focal loss, gradual layer unfreezing, and dynamic sampling to address class imbalance and procedural variability.
title SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.24897