Fuzzy logic techniques for blotch feature evaluation in dermoscopy images

Abstract

Blotches, also called structureless areas, are critical in differentiating malignant melanoma from benign lesions in dermoscopy skin lesion images. In this paper, fuzzy logic techniques are investigated for the automatic detection of blotch features for malignant melanoma discrimination. Four fuzzy sets representative of blotch size and relative and absolute blotch colors are used to extract blotchy areas from a set of dermoscopy skin lesion images. Five previously reported blotch features are computed from the extracted blotches as well as four new features. Using a neural network classifier, malignant melanoma discrimination results are optimized over the range of possible alphacuts and compared with results using crisp blotch features. Features computed from blotches using the fuzzy logic techniques based on three plane relative color and blotch size yield the highest diagnostic accuracy of 81.2%.

Computer Aided Diagnostic Support System for Skin Cancer: A Review of Techniques and Algorithms

“…which experts are more familiar with. Some of the dermoscopic feature extraction studies include atypical pigment networks [ 72 , 110 , 139 ], globules/dots/blotches [ 72 , 140 – 143 ], streaks [ 144 ], granularity [ 145 ], and blue-white veil [ 87 , 146 ]. It is noteworthy that diagnostic systems based on extraction of critical high level features show an increase in the diagnostic accuracy of computerized dermoscopy image analysis systems.…”

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks

“…Asymmetry Index A 3—another approach that highlights the quadrants of an object that are not similar is so-called quadrant asymmetry. The proposed version is adapted from [ 45 , 46 ]. The object is divided into four quadrants and the centroids and center of masses of object and each quadrant are established.…”

Fuzzy logic color detection: Blue areas in melanoma dermoscopy images

“…To determine the color parameters for the blue area membership functions, we examined fuzzy set representations to define the parameters of each color shade by extending previous research using fuzzy sets to characterize color in skin lesion histograms [19] and blotches in dermoscopy skin lesion images [20]. In this research, a fuzzy set is specified to provide high membership to pixels within the skin lesion image that perceptually contribute to identifying blue areas.…”

“…Some of the fuzzy logic methods investigated in previous research for color and skin analysis include color histogram analysis for color labeling and skin lesion discrimination [19], blotch size estimation for skin lesion discrimination [20], blotch detection in skin lesions using fuzzy clustering and texture segmentation [21], fuzzy clustering for adaptively removing background skin color for skin color region segmentation [22], fuzzy c-means clustering for skin lesion segmentation [23], adaptive fuzzy c-means using local spatial continuity for cluster prototype estimation [24], and skin region segmentation using fuzzy decision tree modeling [25]. …”