Name
Title | ||
|---|---|---|
Spatial fuzzy c-means algorithm with adaptive fuzzy exponent selection for robust vermilion border detection in healthy and diseased lower lips. |
Abstract | ||
|---|---|---|
Accurate lip contour identification is demanding since variations in color, form and surface texture, even in normal lips, introduce artifacts in non-adapted segmentation algorithms. Herein, a method for vermilion border detection and quantification in healthy and diseased lower lips is presented.To quantify the morphological irregularities of lower lip border, to validate its discriminative power in solar cheilosis diagnosis and to provide supportive tools toward, cost effective, non invasive, disease monitoring.Segmentation algorithm for lower lip border was based on spatial fuzzy c-means clustering algorithm with adaptive selection of fuzzy exponent m. Lip features measuring morphological lip border deviations were estimated. The method of lip border extraction and quantitative description was evaluated in a gold standard set of 25 young volunteers without onset of lip diseases. Quantitative descriptors were evaluated in terms of correct classification rates in differentiating 30 healthy control cases from 41 patients with solar cheilosis and were further applied to quantify the therapeutic outcome after immunocryosurgery in eight patients with solar cheilosis.Adaptive estimation of fuzzy exponent m substantially boosted the segmentation quality in gold standard cases yielding quite smooth lip contours and uniformly low values of lip irregularity features. Discriminant analysis highlighted the distance between the extracted and modeled vermilion border as a feature with excellent diagnostic accuracy (sensitivity and specificity 98% and 93% respectively). Results on patients with solar cheilosis followed up after treatment with immunocryosurgery showed that proposed quantitative lip marker was able to trace the improvement of disease after treatment.Correct lip border recognition is the prerequisite for extracting essential morphological descriptors from lips with epithelial diseases like solar cheilosis. In this paper we presented an efficient method for the automatic identification and quantitative description of lower lip vermilion border morphology in health and disease using digital photography and image analysis techniques. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1016/j.cmpb.2014.02.017 | Computer Methods and Programs in Biomedicine |
Keywords | Field | DocType |
actinic cheilitis,immunocryosurgery,fuzzy clustering,image analysis,solar cheilosis,lip detection | Fuzzy clustering,Computer vision,Lip Diseases,Segmentation,Computer science,Fuzzy logic,Vermilion border,Algorithm,Artificial intelligence,Linear discriminant analysis,Cluster analysis,Discriminative model | Journal |
Volume | Issue | ISSN |
114 | 3 | 1872-7565 |
Citations | PageRank | References |
4 | 0.42 | 17 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Panagiota Spyridonos | 1 | 222 | 17.43 |
| Georgios Gaitanis | 2 | 6 | 1.50 |
| Margaret Tzaphlidou | 3 | 10 | 1.60 |
| Ioannis D Bassukas | 4 | 6 | 1.50 |