computer-vision

Surgical tool detection

3260 papers • 126 benchmarks • 313 datasets

Presence detection of various classes of surgical instruments in endoscopy videos.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in surgical-tool-detection

Trend

Dataset

Best Model

Actions

Cholec80

HeiChole Benchmark

Libraries

i

Use these libraries to find surgical-tool-detection models and implementations

Datasets

Subtasks

No subtasks available.

Most implemented papers

SSD: Single Shot MultiBox Detector

Christian Szegedy, D. Erhan, A. Berg, Scott E. Reed, W. Liu, Dragomir Anguelov, Cheng-Yang Fu•Mon Dec 07 2015

The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.

33666

Content

0

Paper Graph

EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos

N. Padoy, A. P. Twinanda, S. Shehata, D. Mutter, J. Marescaux, M. Mathelin•Mon Feb 08 2016

This paper proposes a novel method for phase recognition that uses a convolutional neural network (CNN) to automatically learn features from cholecystectomy videos and that relies uniquely on visual information.

1013 0

Paper Graph

Weakly-Supervised Learning for Tool Localization in Laparoscopic Videos

N. Padoy, D. Mutter, J. Marescaux, A. Vardazaryan•Wed Jun 13 2018

A deep architecture, trained solely on image level annotations, that can be used for both tool presence detection and localization in surgical videos, and relies on a fully convolutional neural network, trained end-to-end.

66 0

Paper Graph

Weakly supervised convolutional LSTM approach for tool tracking in laparoscopic videos

N. Padoy, D. Mutter, J. Marescaux, C. Nwoye•Mon Dec 03 2018

It is demonstrated that binary presence labels are sufficient for training a deep learning tracking model using the proposed method, and it is shown that the ConvLSTM can leverage the spatiotemporal coherence of consecutive image frames across a surgical video to improve tool presence detection, spatial localization, and motion tracking.

141 0

Paper Graph

Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis

Q. Dou, P. Heng, Hao Chen, Chi-Wing Fu, Yueming Jin, J. Qin, Huaxia Li•Fri Jul 12 2019

A novel method by developing a multi-task recurrent convolutional network with correlation loss (MTRCNet-CL) to exploit their relatedness to simultaneously boost the performance of both surgical tool presence detection and phase recognition.

206 0

Paper Graph

Dissecting Self-Supervised Learning Methods for Surgical Computer Vision

Deepak Alapatt, Luca Sestini, N. Padoy, V. Srivastav, C. Nwoye, Tong Yu, Sanat Ramesh, Aditya Murali, Idris Hamoud, A. Fleurentin, Georgios Exarchakis, A. Karargyris•Thu Jun 30 2022

Correct transfer of these methods to surgery leads to substantial performance gains over generic uses of SSL - up to 7.4% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%.

70 0

Paper Graph

PWISeg: Point-based Weakly-supervised Instance Segmentation for Surgical Instruments

Zhen Sun, Huan XU, Jinlin Wu, Zhen Chen, Zhen Lei, Hongbin Liu•Wed Nov 15 2023

The accuracy of surgical instrument segmentation is improved, surpassing most methods of instance segmentation via weakly supervised bounding boxes and when applied to the public HOSPI-Tools dataset.

1 0

Paper Graph

A semi-supervised Teacher-Student framework for surgical tool detection and localization

Sharib Ali, M. A. Teevno, Gilberto Ochoa-Ruiz•Sat Aug 20 2022

This paper introduces an SSL framework in the surgical tool detection paradigm, which aims to mitigate training data scarcity and data imbalance problems through a knowledge distillation approach.

14 0

Paper Graph

CholecTriplet2022: Show me a tool and tell me the triplet - an endoscopic vision challenge for surgical action triplet detection

L. Maier-Hein, N. Navab, P. Mascagni, Deepak Alapatt, N. Padoy, D. Mutter, Saurav Sharma, Wolfgang Reiter, C. Nwoye, Tong Yu, Cristians Gonzalez, B. Seeliger, Jonas Hajek, Estevão Lima, A. Vardazaryan, Satoshi Kondo, Binod Bhattarai, E. Vazquez, Ege Özsoy, T. Tran, Tobias Czempiel, Aditya Murali, Kun Yuan, A. Yamlahi, Finn-Henri Smidt, Xiaoyang Zou, G. Zheng, Bruno Oliveira, Helena R. Torres, S. Kasai, Felix Holm, Shuangchun Gui, Han Li, Sista Raviteja, R. Sathish, Pranav Poudel, Ziheng Wang, Guo Rui, Melanie Schellenberg, Joao L. Vilacca, Zhenkun Wang, Debdoot Sheet, S. Thapa, Max Berniker, Patrick Godau, P. Morais, Sudarshan Regmi, J. Fonseca, Jan-Hinrich Nolke•Sun Feb 12 2023

The CholecTriplet2022 challenge is presented, which extends surgical action triplet modeling from recognition to detection, and includes weakly-supervised bounding box localization of every visible surgical instrument (or tool), as the key actors, and the modeling of each tool-activity in the form of ‹instrument, verb, target› triplet.

38 0

Paper Graph

EgoSurgery-Tool: A Dataset of Surgical Tool and Hand Detection from Egocentric Open Surgery Videos

Ryo Fujii, Hideo Saito, Hiroyuki Kajita•Tue Jun 04 2024

EgoSurgery-Tool is introduced, an extension of the existing EgoSurgery-Phase dataset, which contains real open surgery videos captured using an egocentric camera attached to the surgeon's head, along with phase annotations, and is superior to existing datasets due to its larger scale, greater variety of surgical tools, more annotations, and denser scenes.

6 0

Paper Graph

Adding a benchmark result helps the community track progress.