Detection of atypical texture features in early malignant melanoma

Abstract

Background The presence of an atypical (irregular) pigment network (APN) can indicate a diagnosis of melanoma. This study sought to analyze the APN with texture measures. Methods For 106 dermoscopy images including 28 melanomas and 78 benign dysplastic nevi, the areas of APN were selected manually. Ten texture measures in the CVIPtools image analysis system were applied. Results Of the 10 texture measures used, correlation average provided the highest discrimination accuracy, an average of 95.4%. Discrimination of melanomas was optimal at a pixel distance of 20 for the 768 × 512 images, consistent with a melanocytic lesion texel size estimate of 4–5 texels per mm. Conclusion Texture analysis, in particular correlation average at an optimized pixel spacing, may afford automatic detection of an irregular pigment network in early malignant melanoma.

Modeling the Dermoscopic Structure Pigment Network Using a Clinically Inspired Feature Set

“…The automated detection of pigment network has received some recent attention [4,5,6,7,8,9,10]. Fleming et al [4] report techniques for extracting and visualizing pigment network via morphological operators.…”

“…All work to date has either: 1) not reported quantitative validation [4,5]; 2) validated against a small (n < 100) number of images [7]; 3) only considered or reported results for the 2-class problem (e.g. Absent /Present rather than Absent /Typical /Atypical ) [6,7,8,9,10]; 4) not explicitly identified the location of the network [6]; or 5) has made use of unrealistic exclusion criteria and other manual interventions [9]. This paper presents an effective method for pigment network segmentation and classification, which is validated on a large (n = 436) 'real-world' dataset.…”

“…al. [9] begin with a set of 106 images where the location of the APN has been manually segmented. If no APN is present, then the location of the most 'irregular texture' is manually selected.…”

Detection and Analysis of Irregular Streaks in Dermoscopic Images of Skin Lesions

“…As a fundamental step towards computer-aided diagnosis of skin cancers, automatic detection and analysis of local dermoscopic structures [16]- [23] and global patterns [24]- [28] have been frequently addressed in the literature. However, even though the presence of Irregular streaks is highly suggestive for malignancy of a lesion, the modeling, detection, and analysis of streak lines and starburst pattern have very rarely been used for automated skin lesion diagnosis.…”

“…The entropy is a statistical measure of randomness and the motivating idea behind the entropy is that Irregular streaks with unpredictable orientation change have a high entropy while Regular streaks with a speci c smooth orientation change show a relatively low entropy. For with lines , entropy is denoted by , and is de ned as (16) where is the probability function of and contains the histogram counts of bins where .…”