Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy

1606 Views
1451 Downloads
Export citation: ABNT
FINKŠT, Tomaž ;TASIČ, Jurij Franc;ZORMAN TERČELJ, Marjeta ;MEŽA, Marko .
Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 63, n.12, p. 685-695, june 2018. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/classification-of-malignancy-suspicious-lesions-in-autofluorescence-bronchoscopy/>. Date accessed: 05 dec. 2021. 
doi:http://dx.doi.org/10.5545/sv-jme.2016.4019.
Finkšt, T., Tasič, J., Zorman Terčelj, M., & Meža, M.
(2017).
Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy.
Strojniški vestnik - Journal of Mechanical Engineering, 63(12), 685-695.
doi:http://dx.doi.org/10.5545/sv-jme.2016.4019
@article{sv-jmesv-jme.2016.4019,
	author = {Tomaž  Finkšt and Jurij Franc Tasič and Marjeta  Zorman Terčelj and Marko  Meža},
	title = {Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {63},
	number = {12},
	year = {2017},
	keywords = {image segmentation; edge detection; autofluorescence bronchoscopy; machine learning},
	abstract = {This paper presents a novel approach to the classification of bronchial tissue as either malignant or precancerous based on autofluorescence bronchoscopy (AFB) images. The study consisted of 44 images, of which 22 were confirmed as malignant and 22 as nonmalignant precancerous cases. Our approach starts with the detection of a region of interest (ROI). This is followed by an analysis of semi-normal intensity distributions in gray-scale images of red and green components of the previously identified ROI. Based on the results of this analysis, features are computed, which are then used to build an image-classification model. This model classifies the tissue images into malignant/nonmalignant classes. We utilized several classification algorithms, i.e., naive Bayes, K-nearest-neighbor (K-NN), and support vector machine (SVM) with dot kernel. The criteria used when testing their performance were accuracy, sensitivity, specificity, and the area under the curve. Wilcoxon’s signed-rank test was used to confirm the accuracy of the classification method. The proposed method was compared to a similar approach reported by Buountris et al., who analyzed the texture features in a gray-level co-occurrence matrix (GLCM). Using the bestperforming classification algorithm (SVM with dot kernel), the accuracy of the proposed approach (95.8 %) was better than that reported by Bountris et al. (92.1 %).},
	issn = {0039-2480},	pages = {685-695},	doi = {10.5545/sv-jme.2016.4019},
	url = {https://www.sv-jme.eu/article/classification-of-malignancy-suspicious-lesions-in-autofluorescence-bronchoscopy/}
}
Finkšt, T.,Tasič, J.,Zorman Terčelj, M.,Meža, M.
2017 June 63. Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 63:12
%A Finkšt, Tomaž 
%A Tasič, Jurij Franc
%A Zorman Terčelj, Marjeta 
%A Meža, Marko 
%D 2017
%T Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy
%B 2017
%9 image segmentation; edge detection; autofluorescence bronchoscopy; machine learning
%! Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy
%K image segmentation; edge detection; autofluorescence bronchoscopy; machine learning
%X This paper presents a novel approach to the classification of bronchial tissue as either malignant or precancerous based on autofluorescence bronchoscopy (AFB) images. The study consisted of 44 images, of which 22 were confirmed as malignant and 22 as nonmalignant precancerous cases. Our approach starts with the detection of a region of interest (ROI). This is followed by an analysis of semi-normal intensity distributions in gray-scale images of red and green components of the previously identified ROI. Based on the results of this analysis, features are computed, which are then used to build an image-classification model. This model classifies the tissue images into malignant/nonmalignant classes. We utilized several classification algorithms, i.e., naive Bayes, K-nearest-neighbor (K-NN), and support vector machine (SVM) with dot kernel. The criteria used when testing their performance were accuracy, sensitivity, specificity, and the area under the curve. Wilcoxon’s signed-rank test was used to confirm the accuracy of the classification method. The proposed method was compared to a similar approach reported by Buountris et al., who analyzed the texture features in a gray-level co-occurrence matrix (GLCM). Using the bestperforming classification algorithm (SVM with dot kernel), the accuracy of the proposed approach (95.8 %) was better than that reported by Bountris et al. (92.1 %).
%U https://www.sv-jme.eu/article/classification-of-malignancy-suspicious-lesions-in-autofluorescence-bronchoscopy/
%0 Journal Article
%R 10.5545/sv-jme.2016.4019
%& 685
%P 11
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 63
%N 12
%@ 0039-2480
%8 2018-06-27
%7 2018-06-27
Finkšt, Tomaž, Jurij Franc Tasič, Marjeta  Zorman Terčelj, & Marko  Meža.
"Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy." Strojniški vestnik - Journal of Mechanical Engineering [Online], 63.12 (2017): 685-695. Web.  05 Dec. 2021
TY  - JOUR
AU  - Finkšt, Tomaž 
AU  - Tasič, Jurij Franc
AU  - Zorman Terčelj, Marjeta 
AU  - Meža, Marko 
PY  - 2017
TI  - Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2016.4019
KW  - image segmentation; edge detection; autofluorescence bronchoscopy; machine learning
N2  - This paper presents a novel approach to the classification of bronchial tissue as either malignant or precancerous based on autofluorescence bronchoscopy (AFB) images. The study consisted of 44 images, of which 22 were confirmed as malignant and 22 as nonmalignant precancerous cases. Our approach starts with the detection of a region of interest (ROI). This is followed by an analysis of semi-normal intensity distributions in gray-scale images of red and green components of the previously identified ROI. Based on the results of this analysis, features are computed, which are then used to build an image-classification model. This model classifies the tissue images into malignant/nonmalignant classes. We utilized several classification algorithms, i.e., naive Bayes, K-nearest-neighbor (K-NN), and support vector machine (SVM) with dot kernel. The criteria used when testing their performance were accuracy, sensitivity, specificity, and the area under the curve. Wilcoxon’s signed-rank test was used to confirm the accuracy of the classification method. The proposed method was compared to a similar approach reported by Buountris et al., who analyzed the texture features in a gray-level co-occurrence matrix (GLCM). Using the bestperforming classification algorithm (SVM with dot kernel), the accuracy of the proposed approach (95.8 %) was better than that reported by Bountris et al. (92.1 %).
UR  - https://www.sv-jme.eu/article/classification-of-malignancy-suspicious-lesions-in-autofluorescence-bronchoscopy/
@article{{sv-jme}{sv-jme.2016.4019},
	author = {Finkšt, T., Tasič, J., Zorman Terčelj, M., Meža, M.},
	title = {Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {63},
	number = {12},
	year = {2017},
	doi = {10.5545/sv-jme.2016.4019},
	url = {https://www.sv-jme.eu/article/classification-of-malignancy-suspicious-lesions-in-autofluorescence-bronchoscopy/}
}
TY  - JOUR
AU  - Finkšt, Tomaž 
AU  - Tasič, Jurij Franc
AU  - Zorman Terčelj, Marjeta 
AU  - Meža, Marko 
PY  - 2018/06/27
TI  - Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 63, No 12 (2017): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 10.5545/sv-jme.2016.4019
KW  - image segmentation, edge detection, autofluorescence bronchoscopy, machine learning
N2  - This paper presents a novel approach to the classification of bronchial tissue as either malignant or precancerous based on autofluorescence bronchoscopy (AFB) images. The study consisted of 44 images, of which 22 were confirmed as malignant and 22 as nonmalignant precancerous cases. Our approach starts with the detection of a region of interest (ROI). This is followed by an analysis of semi-normal intensity distributions in gray-scale images of red and green components of the previously identified ROI. Based on the results of this analysis, features are computed, which are then used to build an image-classification model. This model classifies the tissue images into malignant/nonmalignant classes. We utilized several classification algorithms, i.e., naive Bayes, K-nearest-neighbor (K-NN), and support vector machine (SVM) with dot kernel. The criteria used when testing their performance were accuracy, sensitivity, specificity, and the area under the curve. Wilcoxon’s signed-rank test was used to confirm the accuracy of the classification method. The proposed method was compared to a similar approach reported by Buountris et al., who analyzed the texture features in a gray-level co-occurrence matrix (GLCM). Using the bestperforming classification algorithm (SVM with dot kernel), the accuracy of the proposed approach (95.8 %) was better than that reported by Bountris et al. (92.1 %).
UR  - https://www.sv-jme.eu/article/classification-of-malignancy-suspicious-lesions-in-autofluorescence-bronchoscopy/
Finkšt, Tomaž, Tasič, Jurij, Zorman Terčelj, Marjeta, AND Meža, Marko.
"Classification of Malignancy in Suspicious Lesions Using Autofluorescence Bronchoscopy" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 63 Number 12 (27 June 2018)

Authors

Affiliations

  • University of Ljubljana, Faculty of Mechanical Engineering, Slovenia 1
  • University of Ljubljana, Faculty of Electrical Engineering, Slovenia 2
  • University Medical Centre, Clinical Department of Pulmonary Diseases and Allergy, Slovenia 3

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 63(2017)12, 685-695

https://doi.org/10.5545/sv-jme.2016.4019

This paper presents a novel approach to the classification of bronchial tissue as either malignant or precancerous based on autofluorescence bronchoscopy (AFB) images. The study consisted of 44 images, of which 22 were confirmed as malignant and 22 as nonmalignant precancerous cases. Our approach starts with the detection of a region of interest (ROI). This is followed by an analysis of semi-normal intensity distributions in gray-scale images of red and green components of the previously identified ROI. Based on the results of this analysis, features are computed, which are then used to build an image-classification model. This model classifies the tissue images into malignant/nonmalignant classes. We utilized several classification algorithms, i.e., naive Bayes, K-nearest-neighbor (K-NN), and support vector machine (SVM) with dot kernel. The criteria used when testing their performance were accuracy, sensitivity, specificity, and the area under the curve. Wilcoxon’s signed-rank test was used to confirm the accuracy of the classification method. The proposed method was compared to a similar approach reported by Buountris et al., who analyzed the texture features in a gray-level co-occurrence matrix (GLCM). Using the bestperforming classification algorithm (SVM with dot kernel), the accuracy of the proposed approach (95.8 %) was better than that reported by Bountris et al. (92.1 %).

image segmentation; edge detection; autofluorescence bronchoscopy; machine learning