Lung nodules detection in chest radiography: Image components analysis

Tao Luo, Xuanqin Mou, Ying Yang, Hao Yan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We aimed to evaluate the effect of different components of chest image on performances of both human observer and channelized Fisher-Hotelling model (CFH) in nodule detection task. Irrelevant and relevant components were separated from clinical chest radiography by employing Principal Component Analysis (PCA) methods. Human observer performance was evaluated in two-alternative forced-choice (2AFC) on original clinical images and anatomical structure only images obtained by PCA methods. Channelized Fisher-Hotelling model with Laguerre-Gauss basis function was evaluated to predict human performance. We show that relevant component is the primary factor influencing on nodule detection in chest radiography. There is obvious difference of detectability between human observer and CFH model for nodule detection in images only containing anatomical structure. CFH model should be used more carefully.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7263
DOIs
StatePublished - 2009
EventMedical Imaging 2009: Image Perception, Observer Performance, and Technology Assessment - Lake Buena Vista, FL, United States
Duration: Feb 11 2009Feb 12 2009

Other

OtherMedical Imaging 2009: Image Perception, Observer Performance, and Technology Assessment
CountryUnited States
CityLake Buena Vista, FL
Period2/11/092/12/09

Fingerprint

chest
nodules
Radiography
radiography
lungs
Thorax
Lung
Principal Component Analysis
principal components analysis
Principal component analysis
human performance

Keywords

  • 2AFC
  • Image quality
  • Observer model
  • PCA

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Luo, T., Mou, X., Yang, Y., & Yan, H. (2009). Lung nodules detection in chest radiography: Image components analysis. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7263). [72631Q] https://doi.org/10.1117/12.813503

Lung nodules detection in chest radiography : Image components analysis. / Luo, Tao; Mou, Xuanqin; Yang, Ying; Yan, Hao.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7263 2009. 72631Q.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Luo, T, Mou, X, Yang, Y & Yan, H 2009, Lung nodules detection in chest radiography: Image components analysis. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7263, 72631Q, Medical Imaging 2009: Image Perception, Observer Performance, and Technology Assessment, Lake Buena Vista, FL, United States, 2/11/09. https://doi.org/10.1117/12.813503
Luo T, Mou X, Yang Y, Yan H. Lung nodules detection in chest radiography: Image components analysis. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7263. 2009. 72631Q https://doi.org/10.1117/12.813503
Luo, Tao ; Mou, Xuanqin ; Yang, Ying ; Yan, Hao. / Lung nodules detection in chest radiography : Image components analysis. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7263 2009.
@inproceedings{0b3caaa8076d408aa76c9f27202637ce,
title = "Lung nodules detection in chest radiography: Image components analysis",
abstract = "We aimed to evaluate the effect of different components of chest image on performances of both human observer and channelized Fisher-Hotelling model (CFH) in nodule detection task. Irrelevant and relevant components were separated from clinical chest radiography by employing Principal Component Analysis (PCA) methods. Human observer performance was evaluated in two-alternative forced-choice (2AFC) on original clinical images and anatomical structure only images obtained by PCA methods. Channelized Fisher-Hotelling model with Laguerre-Gauss basis function was evaluated to predict human performance. We show that relevant component is the primary factor influencing on nodule detection in chest radiography. There is obvious difference of detectability between human observer and CFH model for nodule detection in images only containing anatomical structure. CFH model should be used more carefully.",
keywords = "2AFC, Image quality, Observer model, PCA",
author = "Tao Luo and Xuanqin Mou and Ying Yang and Hao Yan",
year = "2009",
doi = "10.1117/12.813503",
language = "English (US)",
isbn = "9780819475145",
volume = "7263",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Lung nodules detection in chest radiography

T2 - Image components analysis

AU - Luo, Tao

AU - Mou, Xuanqin

AU - Yang, Ying

AU - Yan, Hao

PY - 2009

Y1 - 2009

N2 - We aimed to evaluate the effect of different components of chest image on performances of both human observer and channelized Fisher-Hotelling model (CFH) in nodule detection task. Irrelevant and relevant components were separated from clinical chest radiography by employing Principal Component Analysis (PCA) methods. Human observer performance was evaluated in two-alternative forced-choice (2AFC) on original clinical images and anatomical structure only images obtained by PCA methods. Channelized Fisher-Hotelling model with Laguerre-Gauss basis function was evaluated to predict human performance. We show that relevant component is the primary factor influencing on nodule detection in chest radiography. There is obvious difference of detectability between human observer and CFH model for nodule detection in images only containing anatomical structure. CFH model should be used more carefully.

AB - We aimed to evaluate the effect of different components of chest image on performances of both human observer and channelized Fisher-Hotelling model (CFH) in nodule detection task. Irrelevant and relevant components were separated from clinical chest radiography by employing Principal Component Analysis (PCA) methods. Human observer performance was evaluated in two-alternative forced-choice (2AFC) on original clinical images and anatomical structure only images obtained by PCA methods. Channelized Fisher-Hotelling model with Laguerre-Gauss basis function was evaluated to predict human performance. We show that relevant component is the primary factor influencing on nodule detection in chest radiography. There is obvious difference of detectability between human observer and CFH model for nodule detection in images only containing anatomical structure. CFH model should be used more carefully.

KW - 2AFC

KW - Image quality

KW - Observer model

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=67249105983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67249105983&partnerID=8YFLogxK

U2 - 10.1117/12.813503

DO - 10.1117/12.813503

M3 - Conference contribution

AN - SCOPUS:67249105983

SN - 9780819475145

VL - 7263

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -