Transfer Learning of a Neural Network for Robotic Surgical Assessment

Completed

• Conditions: Robot Surgery
• Interventions: Other: observational study

• Registration Number: NCT06612606
• Lead Sponsor: Aalborg University

Brief Summary

The goal of this observational study is to explore how pretrained artificial intelligence (AI) models, trained on preclinical data, can improve the accuracy of action recognition and skills assessment in robot-assisted surgery (RAS) in urological patients by the use of transfer learning. The main questions it aims to answer are:

* Can pretrained AI models accurately assess action recognition and skills assessment in clinical surgeries?

* How do different training approaches of transfer learning affect the performance of the AI models? A baseline model developed from scratch using clinical data will be compared to pretrained models that are (1) directly applied to clinical data (2) fine-tuned by training only some layers of the AI model, and (3) fully retrained to see if these approaches improve performance.

Participants who are robot surgeons will:

* Undergo RAS procedures on patients, with no intervention, where video data will be collected for later action recognition and skills assessment.

* Contribute to model training and evaluation through clinical dataset integration.

Detailed Description

Not available

Study Timeline

• Study Start: 2023-05-22
• Primary Completion: 2023-05-26
• Study Completion: 2023-05-26
• Status Verified: 2024-09
• Study First Submitted: 2024-09-22
• Study First Submitted QC: 2024-09-22
• Last Update Submitted: 2024-09-22
• Study First Posted: 2024-09-25
• Last Update Posted: 2024-09-25

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 5

Inclusion Criteria

• Robot surgeons who are experienced with more than 100 cases.
• Robot surgical fellows with less than 100 cases.
• Robot surgeons who worked at the urological department of Aalborg University Hospital.

Exclusion Criteria

Not provided

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Experienced robot surgeons	observational study	Robot surgeons with 100 or more performed robot surgical cases.
Novice robot surgeons	observational study	Robot surgeons with less than 100 performed robot surgical cases.

Primary Outcome Measures

Name	Time	Method
Accuracy of action recognition using clinical data from scratch	From start to end of a the robot surgical procedure that is being assessed in terms of action recognition.	Accuracy of the deep learning algorithm for action recognition, when training the model from scratch using clinical data from robot surgical procedures.
Accuracy of skills assessment using clinical data from scratch	From start to end of a the robot surgical procedure that is being assessed in terms of action recognition.	Accuracy of the deep learning algorithm for skills assessment, when training the model from scratch using clinical data from robot surgical procedures.
Accuracy of action recognition using the pretrained network directly on clinical data	From start to end of a the robot surgical procedure that is being assessed in terms of action recognition.	Accuracy of the pretrained deep learning algorithm for action recognition, when using the model directly on clinical data from robot surgical procedures.
Accuracy of skills assessment using the pretrained model directly on clinical data	From start to end of a the robot surgical procedure that is being assessed in terms of skills assessment.	Accuracy of the pretrained deep learning algorithm for skills assessment, when using the model directly on clinical data from robot surgical procedures.
K fold accuracies for action recognition and skills assessment for the complete retraining of the pretrained network.	From the start to the end of the clinical procedures.	K fold cross-validation accuracies when retraining the complete pretrained model on the clinical data for both action recognition and skills assessment.
K fold accuracies for action recognition and skills assessment for the partial retraining of the pretrained network.	From the start to the end of the clinical procedures.	K fold cross validation accuracies for action recognition and skills assessment for the retraining of the LSTM and dense layers of the pretrained network using clinical data.

Secondary Outcome Measures

Name	Time	Method
Weighted recall/sensitivity, precision and F1 score for action recognition of the clinical network trained from scratch	From start to end of a the robot surgical procedure that is being assessed in terms of action recognition.	Based on the performance of action recognition from the clinical network trained from scratch.
Weighted recall/sensitivity, precision and F1 score for Skills Assessment of the clinical network trained from scratch	From start to end of a the robot surgical procedure that is being assessed in terms of skills assessment..	Based on the performance of skills assessment from the clinical network trained from scratch.
Predictive certainty of the action recognition and skills assessment of the network trained from scratch on the clinical data.	From the start to the end of the clinical procedures.	Predictive certainty with overall mean, minimum and maximum and depicted in probability plots for action recognition and skills assessment of the network trained from scratch on clinical data.
Predictive certainty of the action recognition and skills assessment of the network partially retrained network.	From the start to the end of the clinical procedures.	Predictive certainty with overall mean, minimum and maximum and depicted in probability plots for action recognition and skills assessment of the partially retrained network, where only the LSTM and deep layers of the network was trained on clinical data.

Trial Locations

Locations (1)

Department of urology, Aalborg University Hospital; 🇩🇰 Aalborg, North Jutland, Denmark