Intelligent surgical workflow recognition-based skill assessment for minimally invasive submandibular gland resection
5 affiliations
- 1State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases & Department of Head and Neck Oncology West China Hospital of Stomatology, Sichuan University, Chengdu, China
- 2College of Computer Science, Sichuan University, Chengdu, China
- 3Department of Oral and Maxillofacial Surgery, The Second Clinical Medical College of North Sichuan Medical College, Nanchong Central Hospital, Nanchong, China
- 4Nanjing Stomatology Hospital, Medical School of Nanjing University, Nanjing, China
- 5Department of Oral and Maxillofacial Surgery, The Affiliated Hospital of Stomatology, Harbin Medical University, Harbin, China
Abstract
Artificial Intelligence (AI) is transforming clinical dental practice, with most applications focusing on static images like radiographs. However, the integration of AI in analyzing video data, particularly in surgical settings rich in dynamic information, remains underexplored in oral medicine. This study introduces AI-miSMG, an intelligent surgical workflow recognition model designed for minimally invasive submandibular gland (SMG) resection. Building upon our previous work, we established a standardized annotation protocol to efficiently label endoscopic SMG resection procedures, which are divided into Creation, Position, Separation, Inspection, and Idle phases. The AI-miSMG model was trained on a dataset of 73 high-quality endoscopic SMG resection videos, comprising 386,122 labeled frames. To evaluate its performance, we used a multicenter dataset consisting of surgical videos from four different centers, totaling 85,913 images. The model achieved an overall accuracy of 0.87 on the external validation dataset. Additionally, it was explored for workflow-based analysis of surgical fluency across surgeons with different experience levels. Furthermore, our model reduced annotation time by approximately 47%, decreasing from 94.00 min to 49.90 min. Overall, we developed a deep learning-based workflow recognition model for minimally invasive SMG resection and demonstrated its feasibility for surgical phase recognition, workflow analysis, and model-assisted annotation.
Related
- A Hybrid Approach for a Minimally Invasive Resection of a Gastrointestinal Stromal Tumor
- Minimally invasive resection of multifocal duodeno-jejunal gastrointestinal stromal tumors in neurofibromatosis type 1
- Minimally invasive vs standard surgical treatment: A systematic review comparing prostatic artery embolization and transurethral resection of the prostate for benign prostatic hyperplasia.
- Intelligent thermoregulation strategy versus routine thermal management on myocardial injury after noncardiac surgery during gastrointestinal tumor resection in elderly patients (SAGE): a multicenter, parallel-group, superiority trial.
- Multimodal digital assessment of early recovery after chest tube omission in early-stage lung cancer patients undergoing wedge resection: a post hoc analysis of a prospective cohort
BibTeX
@article{ma2026intelligent,
title = {{Intelligent surgical workflow recognition-based skill assessment for minimally invasive submandibular gland resection}},
author = {Zhongkai Ma and Yufei Hua and Lin Que and Bing Yan and Jialiang Huang and Huawei Ming and Xiaowei Hong and Songlin Piao and Chenwei Tang and Zhiyong Guo and Guiquan Zhu and Chunjie Li},
journal = {NPJ Digital Medicine},
year = {2026},
month = jul,
doi = {10.1038/s41746-026-02976-w},
url = {https://doi.org/10.1038/s41746-026-02976-w},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Intelligent surgical workflow recognition-based skill assessment for minimally invasive submandibular gland resection
AU - Zhongkai Ma
AU - Yufei Hua
AU - Lin Que
AU - Bing Yan
AU - Jialiang Huang
AU - Huawei Ming
AU - Xiaowei Hong
AU - Songlin Piao
AU - Chenwei Tang
AU - Zhiyong Guo
AU - Guiquan Zhu
AU - Chunjie Li
PY - 2026
DA - 2026/07/07
JO - NPJ Digital Medicine
DO - 10.1038/s41746-026-02976-w
UR - https://doi.org/10.1038/s41746-026-02976-w
AB - Artificial Intelligence (AI) is transforming clinical dental practice, with most applications focusing on static images like radiographs. However, the integration of AI in analyzing video data, particularly in surgical settings rich in dynamic information, remains underexplored in oral medicine. This study introduces AI-miSMG, an intelligent surgical workflow recognition model designed for minimally invasive submandibular gland (SMG) resection. Building upon our previous work, we established a standardized annotation protocol to efficiently label endoscopic SMG resection procedures, which are divided into Creation, Position, Separation, Inspection, and Idle phases. The AI-miSMG model was trained on a dataset of 73 high-quality endoscopic SMG resection videos, comprising 386,122 labeled frames. To evaluate its performance, we used a multicenter dataset consisting of surgical videos from four different centers, totaling 85,913 images. The model achieved an overall accuracy of 0.87 on the external validation dataset. Additionally, it was explored for workflow-based analysis of surgical fluency across surgeons with different experience levels. Furthermore, our model reduced annotation time by approximately 47%, decreasing from 94.00 min to 49.90 min. Overall, we developed a deep learning-based workflow recognition model for minimally invasive SMG resection and demonstrated its feasibility for surgical phase recognition, workflow analysis, and model-assisted annotation.
SN - 2398-6352
ER -