Your browser doesn't support javascript.
loading
Adaptable texture-based segmentation by variance and intensity for automatic detection of semitranslucent and pink blush areas in basal cell carcinoma.
Kefel, S; Pelin Kefel, S; LeAnder, R W; Kaur, R; Kasmi, R; Mishra, N K; Rader, R K; Cole, J G; Woolsey, Z T; Stoecker, W V.
Affiliation
  • Kefel S; Department of Electrical and Computer Engineering, Southern Illinois University, Edwardsville, IL, USA.
  • Pelin Kefel S; Department of Electrical and Computer Engineering, Southern Illinois University, Edwardsville, IL, USA.
  • LeAnder RW; Department of Electrical and Computer Engineering, Southern Illinois University, Edwardsville, IL, USA. rleande@siue.edu.
  • Kaur R; Department of Electrical and Computer Engineering, Southern Illinois University, Edwardsville, IL, USA.
  • Kasmi R; Department of Electrical Engineering, University of Bejaia, Bejaia, Algeria.
  • Mishra NK; Stoecker & Associates, Rolla, MO, USA.
  • Rader RK; Stoecker & Associates, Rolla, MO, USA.
  • Cole JG; School of Medicine, University of Missouri, Columbia, MO, USA.
  • Woolsey ZT; Stoecker & Associates, Rolla, MO, USA.
  • Stoecker WV; Stoecker & Associates, Rolla, MO, USA.
Skin Res Technol ; 22(4): 412-422, 2016 Nov.
Article in En | MEDLINE | ID: mdl-26991418
BACKGROUND: Pink blush is a common feature in basal cell carcinoma (BCC). A related feature, semitranslucency, appears as smooth pink or orange regions resembling skin color. We introduce an automatic method for detection of these features based on smoothness and brightness. We also introduce a neighborhood correction method for texture area correction. METHODS: Smoothness and brightness were analyzed over four bands: luminance, red, green, and blue, then merged using variance-based dynamic thresholding. Dermoscopic images of 100 biopsy-proven BCCs and 254 competitive benign mimics were used to train the algorithm. Sixteen color and texture features were extracted from the automatically detected areas. The confusion matrix for the algorithm showed 15 classification errors in the training set for the 354 images: three errors in the BCC set and 12 errors in the benign set. RESULTS: Logistic regression analysis on a separate 1024-image test set was able to achieve good separation of BCC from benign lesions with an area under the receiver operating characteristic curve (ROC) of 0.878 and 0.877 using manually-created and automatically-generated BCC border masks, respectively. CONCLUSION: This pilot study indicates that automatic detection of semitranslucent and pink blush areas in BCC is feasible using colors and first-order texture statistics.
Subject(s)
Key words

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Skin Neoplasms / Pattern Recognition, Automated / Carcinoma, Basal Cell / Colorimetry / Dermoscopy / Machine Learning Type of study: Diagnostic_studies Limits: Aged / Female / Humans / Male / Middle aged Language: En Journal: Skin Res Technol Journal subject: DERMATOLOGIA Year: 2016 Document type: Article Affiliation country: United States Country of publication: United kingdom

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Skin Neoplasms / Pattern Recognition, Automated / Carcinoma, Basal Cell / Colorimetry / Dermoscopy / Machine Learning Type of study: Diagnostic_studies Limits: Aged / Female / Humans / Male / Middle aged Language: En Journal: Skin Res Technol Journal subject: DERMATOLOGIA Year: 2016 Document type: Article Affiliation country: United States Country of publication: United kingdom