Neuro-endoscopic technical skills (NETS) training dataset is obtained from Neuro-endoscope box trainer, which is a box trainer used for imparting neuro-endoscopic skills. The activity performed on the trainer includes transferring 6 rings in a pre-defined manner using a biopsy forceps and endoscope. The activity of ring transfer is recorded by an auxiliary camera placed on the top of the trainer at 25 fps. T he whole activity is split into small videos or surgemes containing one ring transfer per video (approach, grasp, transfer and retract) and is used for evaluation. The videos were obtained from 6 neuro-endoscopic experts and 6 trainees with experience of > 10 and < 1 years respectively and were divided into 100 surgemes. All 100 short videos were given for blinded subjective evaluation by an expert neurosurgeon o n a scoring scale of 1-10 (1-least, 10-highest). 25 videos from this set are randomly selected as a test set and evaluated again at a later point in time to find intra-rater correlation.
To obtain the dataset, please fill and sign this License Agreement, and send it to Dr. Ashish Suri and Dr. Chetan Arora. After duly verifying the License Agreement, we will mail the dataset download link to you. Student Researchers must ask their Supervisor/ Head of the Department to fill and send the agreement to us.
@inproceedings{xiang2018s3d,
title={S3d: Stacking segmental p3d for action quality assessment},
author={Baby, Britty and Chasmai, Mustafa and Banerjee, Tamajit and Suri, Ashish and Banerjee, Subhashis, and Arora, Chetan},
booktitle={2022 29th IEEE International conference on image processing (ICIP)},
pages={xxx},
year={2022},
organization={IEEE}
}