TU Darmstadt / ULB / TUbiblio

Surgical phase recognition by learning phase transitions

Sahu, Manish ; Szengel, Angelika ; Mukhopadhyay, Anirban ; Zachow, Stefan (2020):
Surgical phase recognition by learning phase transitions.
In: Current Directions in Biomedical Engineering, 6 (1), p. 4. De Gruyter, ISSN 23645504,
DOI: 10.1515/cdbme-2020-0037,
[Article]

Abstract

Automatic recognition of surgical phases is an important component for developing an intra-operative context-aware system. Prior work in this area focuses on recognizing short-term tool usage patterns within surgical phases. However, the difference between intra- and interphase tool usage patterns has not been investigated for automatic phase recognition. We developed a Recurrent Neural Network (RNN), in particular a state-preserving Long Short Term Memory (LSTM) architecture to utilize the long-term evolution of tool usage within complete surgical procedures. For fully automatic tool presence detection from surgical video frames, a Convolutional Neural Network (CNN) based architecture namely ZIBNet is employed. Our proposed approach outperformed EndoNet by 8.1% on overall precision for phase detection tasks and 12.5% on meanAP for tool recognition tasks.

Item Type: Article
Erschienen: 2020
Creators: Sahu, Manish ; Szengel, Angelika ; Mukhopadhyay, Anirban ; Zachow, Stefan
Title: Surgical phase recognition by learning phase transitions
Language: English
Abstract:

Automatic recognition of surgical phases is an important component for developing an intra-operative context-aware system. Prior work in this area focuses on recognizing short-term tool usage patterns within surgical phases. However, the difference between intra- and interphase tool usage patterns has not been investigated for automatic phase recognition. We developed a Recurrent Neural Network (RNN), in particular a state-preserving Long Short Term Memory (LSTM) architecture to utilize the long-term evolution of tool usage within complete surgical procedures. For fully automatic tool presence detection from surgical video frames, a Convolutional Neural Network (CNN) based architecture namely ZIBNet is employed. Our proposed approach outperformed EndoNet by 8.1% on overall precision for phase detection tasks and 12.5% on meanAP for tool recognition tasks.

Journal or Publication Title: Current Directions in Biomedical Engineering
Journal volume: 6
Number: 1
Publisher: De Gruyter
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Date Deposited: 16 Dec 2020 08:18
DOI: 10.1515/cdbme-2020-0037
Additional Information:

Art.No.: 20200037

Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details