Automated detection of uninformative frames in pulmonary optical endomicroscopy (OEM)

Antonios Perperidis, Ahsan Akram, Yoann Altmann, Paul McCool, Jody Westerfeld, David Wilson, Kevin Dhaliwal, Stephen McLaughlin

Research output: Contribution to journalArticle

Abstract

Significance: Optical endomicroscopy (OEM) is a novel real-time imaging technology that provides endoscopic images at a microscopic level. The nature of OEM data, as acquired in clinical use, gives rise to the presence of uninformative frames (i.e. pure-noise and motion-artefacts). Uninformative frames can comprise a considerable proportion (up to >25%) of a dataset, increasing the resources required for analysing the data (both manually and automatically), as well as diluting the results of any automated quantification analysis. Objective: There is therefore a need to automatically detect and remove as many of these uninformative frames as possible while keeping frames with structural information intact. Methods: This paper employs Gray Level Co-occurrence Matrix texture measures and detection theory to identify and remove such frames. The detection of pure-noise frames and motion artefacts is treated as two independent problems. Results: Pulmonary OEM frame sequences of the distal lung are employed for the development and assessment of the approach. The proposed approach identifies and removes uninformative frames with a sensitivity of 93% and a specificity of 92.6%. Conclusion: The detection algorithm is accurate and robust in pulmonary OEM frame sequences. Conditional to appropriate model refinement, the algorithms can become applicable in other organs.
Original languageEnglish
Pages (from-to)87-98
Number of pages12
JournalIEEE Transactions on Biomedical Engineering
Volume64
Issue number1
Early online date10 Mar 2016
DOIs
Publication statusPublished - Jan 2017

Fingerprint

Lung
Artifacts
Noise
Technology
Datasets

Keywords

  • Optical Endomicroscopy (OEM)
  • Fibered Confocal Fluorescent Microscopy (FCFM)
  • distal lung imaging
  • image analysis
  • texture analysis
  • frames detection

Cite this

Perperidis, Antonios ; Akram, Ahsan ; Altmann, Yoann ; McCool, Paul ; Westerfeld, Jody ; Wilson, David ; Dhaliwal, Kevin ; McLaughlin, Stephen. / Automated detection of uninformative frames in pulmonary optical endomicroscopy (OEM). In: IEEE Transactions on Biomedical Engineering. 2017 ; Vol. 64, No. 1. pp. 87-98.
@article{05c6566a82d349008b75439db4f03421,
title = "Automated detection of uninformative frames in pulmonary optical endomicroscopy (OEM)",
abstract = "Significance: Optical endomicroscopy (OEM) is a novel real-time imaging technology that provides endoscopic images at a microscopic level. The nature of OEM data, as acquired in clinical use, gives rise to the presence of uninformative frames (i.e. pure-noise and motion-artefacts). Uninformative frames can comprise a considerable proportion (up to >25{\%}) of a dataset, increasing the resources required for analysing the data (both manually and automatically), as well as diluting the results of any automated quantification analysis. Objective: There is therefore a need to automatically detect and remove as many of these uninformative frames as possible while keeping frames with structural information intact. Methods: This paper employs Gray Level Co-occurrence Matrix texture measures and detection theory to identify and remove such frames. The detection of pure-noise frames and motion artefacts is treated as two independent problems. Results: Pulmonary OEM frame sequences of the distal lung are employed for the development and assessment of the approach. The proposed approach identifies and removes uninformative frames with a sensitivity of 93{\%} and a specificity of 92.6{\%}. Conclusion: The detection algorithm is accurate and robust in pulmonary OEM frame sequences. Conditional to appropriate model refinement, the algorithms can become applicable in other organs.",
keywords = "Optical Endomicroscopy (OEM), Fibered Confocal Fluorescent Microscopy (FCFM), distal lung imaging, image analysis, texture analysis, frames detection",
author = "Antonios Perperidis and Ahsan Akram and Yoann Altmann and Paul McCool and Jody Westerfeld and David Wilson and Kevin Dhaliwal and Stephen McLaughlin",
note = "{"}This work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC, United Kingdom) via grant EP/K03197X/1.{"}",
year = "2017",
month = "1",
doi = "10.1109/TBME.2016.2538084",
language = "English",
volume = "64",
pages = "87--98",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE",
number = "1",

}

Automated detection of uninformative frames in pulmonary optical endomicroscopy (OEM). / Perperidis, Antonios; Akram, Ahsan; Altmann, Yoann; McCool, Paul; Westerfeld, Jody; Wilson, David; Dhaliwal, Kevin; McLaughlin, Stephen.

In: IEEE Transactions on Biomedical Engineering, Vol. 64, No. 1, 01.2017, p. 87-98.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated detection of uninformative frames in pulmonary optical endomicroscopy (OEM)

AU - Perperidis, Antonios

AU - Akram, Ahsan

AU - Altmann, Yoann

AU - McCool, Paul

AU - Westerfeld, Jody

AU - Wilson, David

AU - Dhaliwal, Kevin

AU - McLaughlin, Stephen

N1 - "This work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC, United Kingdom) via grant EP/K03197X/1."

PY - 2017/1

Y1 - 2017/1

N2 - Significance: Optical endomicroscopy (OEM) is a novel real-time imaging technology that provides endoscopic images at a microscopic level. The nature of OEM data, as acquired in clinical use, gives rise to the presence of uninformative frames (i.e. pure-noise and motion-artefacts). Uninformative frames can comprise a considerable proportion (up to >25%) of a dataset, increasing the resources required for analysing the data (both manually and automatically), as well as diluting the results of any automated quantification analysis. Objective: There is therefore a need to automatically detect and remove as many of these uninformative frames as possible while keeping frames with structural information intact. Methods: This paper employs Gray Level Co-occurrence Matrix texture measures and detection theory to identify and remove such frames. The detection of pure-noise frames and motion artefacts is treated as two independent problems. Results: Pulmonary OEM frame sequences of the distal lung are employed for the development and assessment of the approach. The proposed approach identifies and removes uninformative frames with a sensitivity of 93% and a specificity of 92.6%. Conclusion: The detection algorithm is accurate and robust in pulmonary OEM frame sequences. Conditional to appropriate model refinement, the algorithms can become applicable in other organs.

AB - Significance: Optical endomicroscopy (OEM) is a novel real-time imaging technology that provides endoscopic images at a microscopic level. The nature of OEM data, as acquired in clinical use, gives rise to the presence of uninformative frames (i.e. pure-noise and motion-artefacts). Uninformative frames can comprise a considerable proportion (up to >25%) of a dataset, increasing the resources required for analysing the data (both manually and automatically), as well as diluting the results of any automated quantification analysis. Objective: There is therefore a need to automatically detect and remove as many of these uninformative frames as possible while keeping frames with structural information intact. Methods: This paper employs Gray Level Co-occurrence Matrix texture measures and detection theory to identify and remove such frames. The detection of pure-noise frames and motion artefacts is treated as two independent problems. Results: Pulmonary OEM frame sequences of the distal lung are employed for the development and assessment of the approach. The proposed approach identifies and removes uninformative frames with a sensitivity of 93% and a specificity of 92.6%. Conclusion: The detection algorithm is accurate and robust in pulmonary OEM frame sequences. Conditional to appropriate model refinement, the algorithms can become applicable in other organs.

KW - Optical Endomicroscopy (OEM)

KW - Fibered Confocal Fluorescent Microscopy (FCFM)

KW - distal lung imaging

KW - image analysis

KW - texture analysis

KW - frames detection

U2 - 10.1109/TBME.2016.2538084

DO - 10.1109/TBME.2016.2538084

M3 - Article

VL - 64

SP - 87

EP - 98

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 1

ER -