Limits...
Automated tissue classification framework for reproducible chronic wound assessment.

Mukherjee R, Manohar DD, Das DK, Achar A, Mitra A, Chakraborty C - Biomed Res Int (2014)

Bottom Line: A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques.It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively.The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793).

View Article: PubMed Central - PubMed

Affiliation: School of Medical Science & Technology, Indian Institute of Technology, Kharagpur, West Bengal 721302, India.

ABSTRACT
The aim of this paper was to develop a computer assisted tissue classification (granulation, necrotic, and slough) scheme for chronic wound (CW) evaluation using medical image processing and statistical machine learning techniques. The red-green-blue (RGB) wound images grabbed by normal digital camera were first transformed into HSI (hue, saturation, and intensity) color space and subsequently the "S" component of HSI color channels was selected as it provided higher contrast. Wound areas from 6 different types of CW were segmented from whole images using fuzzy divergence based thresholding by minimizing edge ambiguity. A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques. Finally, statistical learning algorithms, namely, Bayesian classification and support vector machine (SVM), were trained and tested for wound tissue classification in different CW images. The performance of the wound area segmentation protocol was further validated by ground truth images labeled by clinical experts. It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively. The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793).

Show MeSH

Related in: MedlinePlus

Segmented results of chronic wound areas using fuzzy divergence based thresholding: (a) original chronic wound images [burn, diabetic ulcer, malignant ulcer, pyoderma gangrenosum, venous ulcer, and pressure ulcer]; (b) saturation (S) component image under HSI color space transformation; (c) segmented wound areas; (d) ground truth marked by the clinician; (e) types of wound tissues (granulation, necrotic, and slough) characterized pseudocolored pixels; (e) representing % of granulation (G), slough (S), and necrotic (N) tissue pixels.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4121018&req=5

fig6: Segmented results of chronic wound areas using fuzzy divergence based thresholding: (a) original chronic wound images [burn, diabetic ulcer, malignant ulcer, pyoderma gangrenosum, venous ulcer, and pressure ulcer]; (b) saturation (S) component image under HSI color space transformation; (c) segmented wound areas; (d) ground truth marked by the clinician; (e) types of wound tissues (granulation, necrotic, and slough) characterized pseudocolored pixels; (e) representing % of granulation (G), slough (S), and necrotic (N) tissue pixels.

Mentions: The median filtered wound images of RGB format (downloaded from Medetec Image Database) were transformed into HSI color space where “S” component images for different wounds were considered for segmentation. Thereafter, wound areas were segmented using fuzzy divergence based thresholding where Gaussian membership based divergence value for wound was 0.45 ± 0.02. The corresponding gray value for S component wound images was 207.4 ± 10.4. The machine generated segmented wound areas were also validated on ground truth images by clinical experts (Figure 5). From the wound database, medical experts identified total 767 tissue regions describing 222 regions as granulation tissue, 451 regions as slough tissue, and 94 regions as necrotic tissue based on 74 wound images. Five color and ten textural features were extracted for all the selected regions. Six local binary pattern (LBP) features, namely, LBP-1 for 8, LBP-2 for 16, and LBP-3 for 24 neighborhood points were computed. Out of the total 675 extracted features, 50 features were found to be statistically significant (P < 0.001) having F-value more than 21. Out of five color features only mean color value was significant. And mean values of LBP-1, LBP-2, and LBP-3 were the three features selected out of ten textural features form various color channels. Using selected features, wound tissues were classified into red granulation tissue, yellow slough tissue, and black necrotic tissue based on Bayesian and SVM classifiers. The proposed methodology was applied on various types of wound images and wound tissue pixels were recognized (Figure 6). For example, in case of the 1st image in Figure 6, red granulation, yellow slough, and black tissue were estimated as 64.3%, 16.6%, and 19.1%, respectively. From Table 1, it can be observed that Bayesian method provided 81.15% overall accuracy in predicting three types of tissue pixels.


Automated tissue classification framework for reproducible chronic wound assessment.

Mukherjee R, Manohar DD, Das DK, Achar A, Mitra A, Chakraborty C - Biomed Res Int (2014)

Segmented results of chronic wound areas using fuzzy divergence based thresholding: (a) original chronic wound images [burn, diabetic ulcer, malignant ulcer, pyoderma gangrenosum, venous ulcer, and pressure ulcer]; (b) saturation (S) component image under HSI color space transformation; (c) segmented wound areas; (d) ground truth marked by the clinician; (e) types of wound tissues (granulation, necrotic, and slough) characterized pseudocolored pixels; (e) representing % of granulation (G), slough (S), and necrotic (N) tissue pixels.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4121018&req=5

fig6: Segmented results of chronic wound areas using fuzzy divergence based thresholding: (a) original chronic wound images [burn, diabetic ulcer, malignant ulcer, pyoderma gangrenosum, venous ulcer, and pressure ulcer]; (b) saturation (S) component image under HSI color space transformation; (c) segmented wound areas; (d) ground truth marked by the clinician; (e) types of wound tissues (granulation, necrotic, and slough) characterized pseudocolored pixels; (e) representing % of granulation (G), slough (S), and necrotic (N) tissue pixels.
Mentions: The median filtered wound images of RGB format (downloaded from Medetec Image Database) were transformed into HSI color space where “S” component images for different wounds were considered for segmentation. Thereafter, wound areas were segmented using fuzzy divergence based thresholding where Gaussian membership based divergence value for wound was 0.45 ± 0.02. The corresponding gray value for S component wound images was 207.4 ± 10.4. The machine generated segmented wound areas were also validated on ground truth images by clinical experts (Figure 5). From the wound database, medical experts identified total 767 tissue regions describing 222 regions as granulation tissue, 451 regions as slough tissue, and 94 regions as necrotic tissue based on 74 wound images. Five color and ten textural features were extracted for all the selected regions. Six local binary pattern (LBP) features, namely, LBP-1 for 8, LBP-2 for 16, and LBP-3 for 24 neighborhood points were computed. Out of the total 675 extracted features, 50 features were found to be statistically significant (P < 0.001) having F-value more than 21. Out of five color features only mean color value was significant. And mean values of LBP-1, LBP-2, and LBP-3 were the three features selected out of ten textural features form various color channels. Using selected features, wound tissues were classified into red granulation tissue, yellow slough tissue, and black necrotic tissue based on Bayesian and SVM classifiers. The proposed methodology was applied on various types of wound images and wound tissue pixels were recognized (Figure 6). For example, in case of the 1st image in Figure 6, red granulation, yellow slough, and black tissue were estimated as 64.3%, 16.6%, and 19.1%, respectively. From Table 1, it can be observed that Bayesian method provided 81.15% overall accuracy in predicting three types of tissue pixels.

Bottom Line: A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques.It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively.The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793).

View Article: PubMed Central - PubMed

Affiliation: School of Medical Science & Technology, Indian Institute of Technology, Kharagpur, West Bengal 721302, India.

ABSTRACT
The aim of this paper was to develop a computer assisted tissue classification (granulation, necrotic, and slough) scheme for chronic wound (CW) evaluation using medical image processing and statistical machine learning techniques. The red-green-blue (RGB) wound images grabbed by normal digital camera were first transformed into HSI (hue, saturation, and intensity) color space and subsequently the "S" component of HSI color channels was selected as it provided higher contrast. Wound areas from 6 different types of CW were segmented from whole images using fuzzy divergence based thresholding by minimizing edge ambiguity. A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques. Finally, statistical learning algorithms, namely, Bayesian classification and support vector machine (SVM), were trained and tested for wound tissue classification in different CW images. The performance of the wound area segmentation protocol was further validated by ground truth images labeled by clinical experts. It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively. The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793).

Show MeSH
Related in: MedlinePlus