TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bilal, Muhammad, Alam, Mahmood, Bapu, Deepa, Korsgen, Stephan, Lal, Neeraj, Bach, Simon, Hajivanand, Amir M, Ali, Muhammed, Soomro, Kamran, Qasim, Iqbal, Capik, Paweł, Khan, Aslam, Khan, Zaheer, Vohra, Hunaid, Caputo, Massimo, Beggs, Andrew, Qayyum, Adnan, Qadir, Junaid, Ashraf, Shazad
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910820366024704
author Bilal, Muhammad
Alam, Mahmood
Bapu, Deepa
Korsgen, Stephan
Lal, Neeraj
Bach, Simon
Hajivanand, Amir M
Ali, Muhammed
Soomro, Kamran
Qasim, Iqbal
Capik, Paweł
Khan, Aslam
Khan, Zaheer
Vohra, Hunaid
Caputo, Massimo
Beggs, Andrew
Qayyum, Adnan
Qadir, Junaid
Ashraf, Shazad
author_facet Bilal, Muhammad
Alam, Mahmood
Bapu, Deepa
Korsgen, Stephan
Lal, Neeraj
Bach, Simon
Hajivanand, Amir M
Ali, Muhammed
Soomro, Kamran
Qasim, Iqbal
Capik, Paweł
Khan, Aslam
Khan, Zaheer
Vohra, Hunaid
Caputo, Massimo
Beggs, Andrew
Qayyum, Adnan
Qadir, Junaid
Ashraf, Shazad
contents Indexing endoscopic surgical videos is vital in surgical data science, forming the basis for systematic retrospective analysis and clinical performance evaluation. Despite its significance, current video analytics rely on manual indexing, a time-consuming process. Advances in computer vision, particularly deep learning, offer automation potential, yet progress is limited by the lack of publicly available, densely annotated surgical datasets. To address this, we present TEMSET-24K, an open-source dataset comprising 24,306 trans-anal endoscopic microsurgery (TEMS) video micro-clips. Each clip is meticulously annotated by clinical experts using a novel hierarchical labeling taxonomy encompassing phase, task, and action triplets, capturing intricate surgical workflows. To validate this dataset, we benchmarked deep learning models, including transformer-based architectures. Our in silico evaluation demonstrates high accuracy (up to 0.99) and F1 scores (up to 0.99) for key phases like Setup and Suturing. The STALNet model, tested with ConvNeXt, ViT, and SWIN V2 encoders, consistently segmented well-represented phases. TEMSET-24K provides a critical benchmark, propelling state-of-the-art solutions in surgical data science.
format Preprint
id arxiv_https___arxiv_org_abs_2502_06708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation
Bilal, Muhammad
Alam, Mahmood
Bapu, Deepa
Korsgen, Stephan
Lal, Neeraj
Bach, Simon
Hajivanand, Amir M
Ali, Muhammed
Soomro, Kamran
Qasim, Iqbal
Capik, Paweł
Khan, Aslam
Khan, Zaheer
Vohra, Hunaid
Caputo, Massimo
Beggs, Andrew
Qayyum, Adnan
Qadir, Junaid
Ashraf, Shazad
Computer Vision and Pattern Recognition
Indexing endoscopic surgical videos is vital in surgical data science, forming the basis for systematic retrospective analysis and clinical performance evaluation. Despite its significance, current video analytics rely on manual indexing, a time-consuming process. Advances in computer vision, particularly deep learning, offer automation potential, yet progress is limited by the lack of publicly available, densely annotated surgical datasets. To address this, we present TEMSET-24K, an open-source dataset comprising 24,306 trans-anal endoscopic microsurgery (TEMS) video micro-clips. Each clip is meticulously annotated by clinical experts using a novel hierarchical labeling taxonomy encompassing phase, task, and action triplets, capturing intricate surgical workflows. To validate this dataset, we benchmarked deep learning models, including transformer-based architectures. Our in silico evaluation demonstrates high accuracy (up to 0.99) and F1 scores (up to 0.99) for key phases like Setup and Suturing. The STALNet model, tested with ConvNeXt, ViT, and SWIN V2 encoders, consistently segmented well-represented phases. TEMSET-24K provides a critical benchmark, propelling state-of-the-art solutions in surgical data science.
title TEMSET-24K: Densely Annotated Dataset for Indexing Multipart Endoscopic Videos using Surgical Timeline Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.06708