Literature DB >> 29704196

Exploiting the potential of unlabeled endoscopic video data with self-supervised learning.

Tobias Ross1, David Zimmerer2, Anant Vemuri3, Fabian Isensee2, Manuel Wiesenfarth4, Sebastian Bodenstedt5, Fabian Both6, Philip Kessler6, Martin Wagner7, Beat Müller7, Hannes Kenngott7, Stefanie Speidel5, Annette Kopp-Schneider4, Klaus Maier-Hein2, Lena Maier-Hein3.   

Abstract

PURPOSE: Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions for automatic image annotation, the availability of reference annotations for algorithm training is becoming a major bottleneck in the field. The purpose of this paper was to investigate the concept of self-supervised learning to address this issue.
METHODS: Our approach is guided by the hypothesis that unlabeled video data can be used to learn a representation of the target domain that boosts the performance of state-of-the-art machine learning algorithms when used for pre-training. Core of the method is an auxiliary task based on raw endoscopic video data of the target domain that is used to initialize the convolutional neural network (CNN) for the target task. In this paper, we propose the re-colorization of medical images with a conditional generative adversarial network (cGAN)-based architecture as auxiliary task. A variant of the method involves a second pre-training step based on labeled data for the target task from a related domain. We validate both variants using medical instrument segmentation as target task.
RESULTS: The proposed approach can be used to radically reduce the manual annotation effort involved in training CNNs. Compared to the baseline approach of generating annotated data from scratch, our method decreases exploratively the number of labeled images by up to 75% without sacrificing performance. Our method also outperforms alternative methods for CNN pre-training, such as pre-training on publicly available non-medical (COCO) or medical data (MICCAI EndoVis2017 challenge) using the target task (in this instance: segmentation).
CONCLUSION: As it makes efficient use of available (non-)public and (un-)labeled data, the approach has the potential to become a valuable tool for CNN (pre-)training.

Entities:  

Keywords:  Computer vision; Endoscopic image processing; Endoscopic instrument segmentation; Self-supervised learning; Transfer learning

Mesh:

Year:  2018        PMID: 29704196     DOI: 10.1007/s11548-018-1772-0

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


  2 in total

1.  Can masses of non-experts train highly accurate image classifiers? A crowdsourcing approach to instrument segmentation in laparoscopic images.

Authors:  Lena Maier-Hein; Sven Mersmann; Daniel Kondermann; Sebastian Bodenstedt; Alexandro Sanchez; Christian Stock; Hannes Gotz Kenngott; Mathias Eisenmann; Stefanie Speidel
Journal:  Med Image Comput Comput Assist Interv       Date:  2014

2.  EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos.

Authors:  Andru P Twinanda; Sherif Shehata; Didier Mutter; Jacques Marescaux; Michel de Mathelin; Nicolas Padoy
Journal:  IEEE Trans Med Imaging       Date:  2016-07-22       Impact factor: 10.048

  2 in total
  17 in total

1.  CAI4CAI: The Rise of Contextual Artificial Intelligence in Computer Assisted Interventions.

Authors:  Tom Vercauteren; Mathias Unberath; Nicolas Padoy; Nassir Navab
Journal:  Proc IEEE Inst Electr Electron Eng       Date:  2019-10-23       Impact factor: 10.961

2.  Accurate instance segmentation of surgical instruments in robotic surgery: model refinement and cross-dataset evaluation.

Authors:  Xiaowen Kong; Yueming Jin; Qi Dou; Ziyi Wang; Zerui Wang; Bo Lu; Erbao Dong; Yun-Hui Liu; Dong Sun
Journal:  Int J Comput Assist Radiol Surg       Date:  2021-06-25       Impact factor: 2.924

3.  Image Compositing for Segmentation of Surgical Tools Without Manual Annotations.

Authors:  Luis C Garcia-Peraza-Herrera; Lucas Fidon; Claudia D'Ettorre; Danail Stoyanov; Tom Vercauteren; Sebastien Ourselin
Journal:  IEEE Trans Med Imaging       Date:  2021-04-30       Impact factor: 10.048

4.  Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restoration.

Authors:  Fatemeh Haghighi; Mohammad Reza Hosseinzadeh Taher; Zongwei Zhou; Michael B Gotway; Jianming Liang
Journal:  Med Image Comput Comput Assist Interv       Date:  2020-09-29

Review 5.  Artificial Intelligence-Assisted Surgery: Potential and Challenges.

Authors:  Sebastian Bodenstedt; Martin Wagner; Beat Peter Müller-Stich; Jürgen Weitz; Stefanie Speidel
Journal:  Visc Med       Date:  2020-11-04

6.  Improving Colonoscopy Lesion Classification Using Semi-Supervised Deep Learning.

Authors:  Mayank Golhar; Taylor L Bobrow; Mirmilad Pourmousavi Khoshknab; Simran Jit; Saowanee Ngamruengphong; Nicholas J Durr
Journal:  IEEE Access       Date:  2020-12-25       Impact factor: 3.476

Review 7.  Surgical data science - from concepts toward clinical translation.

Authors:  Lena Maier-Hein; Matthias Eisenmann; Duygu Sarikaya; Keno März; Toby Collins; Anand Malpani; Johannes Fallert; Hubertus Feussner; Stamatia Giannarou; Pietro Mascagni; Hirenkumar Nakawala; Adrian Park; Carla Pugh; Danail Stoyanov; Swaroop S Vedula; Kevin Cleary; Gabor Fichtinger; Germain Forestier; Bernard Gibaud; Teodor Grantcharov; Makoto Hashizume; Doreen Heckmann-Nötzel; Hannes G Kenngott; Ron Kikinis; Lars Mündermann; Nassir Navab; Sinan Onogur; Tobias Roß; Raphael Sznitman; Russell H Taylor; Minu D Tizabi; Martin Wagner; Gregory D Hager; Thomas Neumuth; Nicolas Padoy; Justin Collins; Ines Gockel; Jan Goedeke; Daniel A Hashimoto; Luc Joyeux; Kyle Lam; Daniel R Leff; Amin Madani; Hani J Marcus; Ozanan Meireles; Alexander Seitel; Dogu Teber; Frank Ückert; Beat P Müller-Stich; Pierre Jannin; Stefanie Speidel
Journal:  Med Image Anal       Date:  2021-11-18       Impact factor: 13.828

8.  Entropic Statistical Description of Big Data Quality in Hotel Customer Relationship Management.

Authors:  Lydia González-Serrano; Pilar Talón-Ballestero; Sergio Muñoz-Romero; Cristina Soguero-Ruiz; José Luis Rojo-Álvarez
Journal:  Entropy (Basel)       Date:  2019-04-19       Impact factor: 2.524

9.  Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-Supervised Learning.

Authors:  Fatemeh Haghighi; Mohammad Reza Hosseinzadeh Taher; Zongwei Zhou; Michael B Gotway; Jianming Liang
Journal:  IEEE Trans Med Imaging       Date:  2021-09-30       Impact factor: 11.037

10.  Unravelling the effect of data augmentation transformations in polyp segmentation.

Authors:  Luisa F Sánchez-Peralta; Artzai Picón; Francisco M Sánchez-Margallo; J Blas Pagador
Journal:  Int J Comput Assist Radiol Surg       Date:  2020-09-28       Impact factor: 2.924

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.