Abstract

Purpose: Bronchoscopy is useful in lung cancer detection, but cannot be used to differentiate cancer types. A computer-aided diagnosis (CAD) system was proposed to distinguish malignant cancer types to achieve objective diagnoses. Methods: Bronchoscopic images of 12 adenocarcinoma and 10 squamous cell carcinoma patients were collected. The images were transformed from a red–blue–green (RGB) to a hue–saturation–value (HSV) color space to obtain more meaningful color textures. By combining significant textural features (P < 0.05) in a machine learning classifier, a prediction model of malignant types was established. Results: The performance of the CAD system achieved an accuracy of 86% (19/22), a sensitivity of 90% (9/10), a specificity of 83% (10/12), a positive predictive value of 82% (9/11), and a negative predictive value of 91% (10/11) in distinguishing lung cancer types. The area under the receiver operating characteristic curve was 0.82. Conclusions: On the basis of extracted HSV textures of bronchoscopic images, the CAD system can provide recommendations for clinical diagnoses of lung cancer types.

Original languageEnglish
JournalMedical Physics
DOIs
Publication statusAccepted/In press - Jan 1 2018

Fingerprint

Lung Neoplasms
Color
Bronchoscopy
ROC Curve
Squamous Cell Carcinoma
Neoplasms
Adenocarcinoma
Machine Learning

Keywords

  • bronchoscopy
  • color texture
  • computer-aided diagnosis
  • lung cancer

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

A machine learning texture model for classifying lung cancer subtypes using preliminary bronchoscopic findings. / Feng, Po Hao; Lin, Yin Tzu; Lo, Chung Ming.

In: Medical Physics, 01.01.2018.

Research output: Contribution to journalArticle

@article{a63c2d8a7d8442d690c1a405671c6994,
title = "A machine learning texture model for classifying lung cancer subtypes using preliminary bronchoscopic findings",
abstract = "Purpose: Bronchoscopy is useful in lung cancer detection, but cannot be used to differentiate cancer types. A computer-aided diagnosis (CAD) system was proposed to distinguish malignant cancer types to achieve objective diagnoses. Methods: Bronchoscopic images of 12 adenocarcinoma and 10 squamous cell carcinoma patients were collected. The images were transformed from a red–blue–green (RGB) to a hue–saturation–value (HSV) color space to obtain more meaningful color textures. By combining significant textural features (P < 0.05) in a machine learning classifier, a prediction model of malignant types was established. Results: The performance of the CAD system achieved an accuracy of 86{\%} (19/22), a sensitivity of 90{\%} (9/10), a specificity of 83{\%} (10/12), a positive predictive value of 82{\%} (9/11), and a negative predictive value of 91{\%} (10/11) in distinguishing lung cancer types. The area under the receiver operating characteristic curve was 0.82. Conclusions: On the basis of extracted HSV textures of bronchoscopic images, the CAD system can provide recommendations for clinical diagnoses of lung cancer types.",
keywords = "bronchoscopy, color texture, computer-aided diagnosis, lung cancer, bronchoscopy, color texture, computer-aided diagnosis, lung cancer",
author = "Feng, {Po Hao} and Lin, {Yin Tzu} and Lo, {Chung Ming}",
year = "2018",
month = "1",
day = "1",
doi = "10.1002/mp.13241",
language = "English",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",

}

TY - JOUR

T1 - A machine learning texture model for classifying lung cancer subtypes using preliminary bronchoscopic findings

AU - Feng, Po Hao

AU - Lin, Yin Tzu

AU - Lo, Chung Ming

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Purpose: Bronchoscopy is useful in lung cancer detection, but cannot be used to differentiate cancer types. A computer-aided diagnosis (CAD) system was proposed to distinguish malignant cancer types to achieve objective diagnoses. Methods: Bronchoscopic images of 12 adenocarcinoma and 10 squamous cell carcinoma patients were collected. The images were transformed from a red–blue–green (RGB) to a hue–saturation–value (HSV) color space to obtain more meaningful color textures. By combining significant textural features (P < 0.05) in a machine learning classifier, a prediction model of malignant types was established. Results: The performance of the CAD system achieved an accuracy of 86% (19/22), a sensitivity of 90% (9/10), a specificity of 83% (10/12), a positive predictive value of 82% (9/11), and a negative predictive value of 91% (10/11) in distinguishing lung cancer types. The area under the receiver operating characteristic curve was 0.82. Conclusions: On the basis of extracted HSV textures of bronchoscopic images, the CAD system can provide recommendations for clinical diagnoses of lung cancer types.

AB - Purpose: Bronchoscopy is useful in lung cancer detection, but cannot be used to differentiate cancer types. A computer-aided diagnosis (CAD) system was proposed to distinguish malignant cancer types to achieve objective diagnoses. Methods: Bronchoscopic images of 12 adenocarcinoma and 10 squamous cell carcinoma patients were collected. The images were transformed from a red–blue–green (RGB) to a hue–saturation–value (HSV) color space to obtain more meaningful color textures. By combining significant textural features (P < 0.05) in a machine learning classifier, a prediction model of malignant types was established. Results: The performance of the CAD system achieved an accuracy of 86% (19/22), a sensitivity of 90% (9/10), a specificity of 83% (10/12), a positive predictive value of 82% (9/11), and a negative predictive value of 91% (10/11) in distinguishing lung cancer types. The area under the receiver operating characteristic curve was 0.82. Conclusions: On the basis of extracted HSV textures of bronchoscopic images, the CAD system can provide recommendations for clinical diagnoses of lung cancer types.

KW - bronchoscopy

KW - color texture

KW - computer-aided diagnosis

KW - lung cancer

KW - bronchoscopy

KW - color texture

KW - computer-aided diagnosis

KW - lung cancer

UR - http://www.scopus.com/inward/record.url?scp=85056179773&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056179773&partnerID=8YFLogxK

U2 - 10.1002/mp.13241

DO - 10.1002/mp.13241

M3 - Article

AN - SCOPUS:85056179773

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

ER -