Literature DB >> 31037493

Segmenting and classifying activities in robot-assisted surgery with recurrent neural networks.

Robert DiPietro1, Narges Ahmidi2, Anand Malpani2, Madeleine Waldram2, Gyusung I Lee3, Mija R Lee3, S Swaroop Vedula2, Gregory D Hager2.   

Abstract

PURPOSE: Automatically segmenting and classifying surgical activities is an important prerequisite to providing automated, targeted assessment and feedback during surgical training. Prior work has focused almost exclusively on recognizing gestures, or short, atomic units of activity such as pushing needle through tissue, whereas we also focus on recognizing higher-level maneuvers, such as suture throw. Maneuvers exhibit more complexity and variability than the gestures from which they are composed, however working at this granularity has the benefit of being consistent with existing training curricula.
METHODS: Prior work has focused on hidden Markov model and conditional-random-field-based methods, which typically leverage unary terms that are local in time and linear in model parameters. Because maneuvers are governed by long-term, nonlinear dynamics, we argue that the more expressive unary terms offered by recurrent neural networks (RNNs) are better suited for this task. Four RNN architectures are compared for recognizing activities from kinematics: simple RNNs, long short-term memory, gated recurrent units, and mixed history RNNs. We report performance in terms of error rate and edit distance, and we use a functional analysis-of-variance framework to assess hyperparameter sensitivity for each architecture.
RESULTS: We obtain state-of-the-art performance for both maneuver recognition from kinematics (4 maneuvers; error rate of [Formula: see text]; normalized edit distance of [Formula: see text]) and gesture recognition from kinematics (10 gestures; error rate of [Formula: see text]; normalized edit distance of [Formula: see text]).
CONCLUSIONS: Automated maneuver recognition is feasible with RNNs, an exciting result which offers the opportunity to provide targeted assessment and feedback at a higher level of granularity. In addition, we show that multiple hyperparameters are important for achieving good performance, and our hyperparameter analysis serves to aid future work in RNN-based activity recognition.

Keywords:  Gesture recognition; Maneuver recognition; Recurrent neural networks; Robot-assisted surgery; Surgical activity recognition

Mesh:

Year:  2019        PMID: 31037493     DOI: 10.1007/s11548-019-01953-x

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  14 in total

1.  Learning to forget: continual prediction with LSTM.

Authors:  F A Gers; J Schmidhuber; F Cummins
Journal:  Neural Comput       Date:  2000-10       Impact factor: 2.026

Review 2.  Deliberate practice and the acquisition and maintenance of expert performance in medicine and related domains.

Authors:  K Anders Ericsson
Journal:  Acad Med       Date:  2004-10       Impact factor: 6.893

3.  Learning long-term dependencies with gradient descent is difficult.

Authors:  Y Bengio; P Simard; P Frasconi
Journal:  IEEE Trans Neural Netw       Date:  1994

4.  Learning long-term dependencies in NARX recurrent neural networks.

Authors:  T Lin; B G Horne; P Tino; C L Giles
Journal:  IEEE Trans Neural Netw       Date:  1996

5.  Surgical skill and complication rates after bariatric surgery.

Authors:  John D Birkmeyer; Jonathan F Finks; Amanda O'Reilly; Mary Oerline; Arthur M Carlin; Andre R Nunn; Justin Dimick; Mousumi Banerjee; Nancy J O Birkmeyer
Journal:  N Engl J Med       Date:  2013-10-10       Impact factor: 91.245

6.  The changing face of surgical education: simulation as the new paradigm.

Authors:  Daniel J Scott; Juan C Cendan; Carla M Pugh; Rebecca M Minter; Gary L Dunnington; Rosemary A Kozar
Journal:  J Surg Res       Date:  2008-03-13       Impact factor: 2.192

7.  Why Johnny cannot operate.

Authors:  Richard H Bell
Journal:  Surgery       Date:  2009-10       Impact factor: 3.982

8.  Doctor scores on national qualifying examinations predict quality of care in future practice.

Authors:  Elizabeth Wenghofer; Daniel Klass; Michal Abrahamowicz; Dale Dauphinee; André Jacques; Sydney Smee; David Blackmore; Nancy Winslade; Kristen Reidel; Ilona Bartman; Robyn Tamblyn
Journal:  Med Educ       Date:  2009-12       Impact factor: 6.251

9.  Long short-term memory.

Authors:  S Hochreiter; J Schmidhuber
Journal:  Neural Comput       Date:  1997-11-15       Impact factor: 2.026

10.  Teaching and assessing technical proficiency in surgical subspecialty fellowships.

Authors:  Susan L Gearhart; Ming-Hsien Wang; Marta M Gilson; Belinda Chen; David E Kern
Journal:  J Surg Educ       Date:  2012 Jul-Aug       Impact factor: 2.891

View more
  3 in total

1.  Self-supervised representation learning for surgical activity recognition.

Authors:  Daniel Paysan; Luis Haug; Michael Bajka; Markus Oelhafen; Joachim M Buhmann
Journal:  Int J Comput Assist Radiol Surg       Date:  2021-09-20       Impact factor: 2.924

2.  Gauze Detection and Segmentation in Minimally Invasive Surgery Video Using Convolutional Neural Networks.

Authors:  Guillermo Sánchez-Brizuela; Francisco-Javier Santos-Criado; Daniel Sanz-Gobernado; Eusebio de la Fuente-López; Juan-Carlos Fraile; Javier Pérez-Turiel; Ana Cisnal
Journal:  Sensors (Basel)       Date:  2022-07-11       Impact factor: 3.847

3.  Surgical Hand Gesture Recognition Utilizing Electroencephalogram as Input to the Machine Learning and Network Neuroscience Algorithms.

Authors:  Somayeh B Shafiei; Mohammad Durrani; Zhe Jing; Michael Mostowy; Philippa Doherty; Ahmed A Hussein; Ahmed S Elsayed; Umar Iqbal; Khurshid Guru
Journal:  Sensors (Basel)       Date:  2021-03-03       Impact factor: 3.576

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.