Department of Electronics and Electrical Communications Engineering, Faculty of Engineering, Tanta University, Tanta, Egypt.
Department of Computer Science, University of Illinois at Springfield, Springfield, IL, USA.
Comput Methods Programs Biomed. 2018 Oct;165:163-174. doi: 10.1016/j.cmpb.2018.08.009. Epub 2018 Aug 24.
Melanoma is one of the major death causes while basal cell carcinoma (BCC) is the utmost incident skin lesion type. At their early stages, medical experts may be confused between both types with benign nevus and pigmented benign keratoses (BKL). This inspired the current study to develop an accurate automated, user-friendly skin lesion identification system.
The current work targets a novel discrimination technique of four pre-mentioned skin lesion classes. A novel proposed texture feature, named cumulative level-difference mean (CLDM) based on the gray-level difference method (GLDM) is extracted. The asymmetry, border irregularity, color variation and diameter are summed up as the ABCD rule feature vector is originally used to classify the melanoma from benign lesions. The proposed method improved the ABCD rule to also classify BCC and BKL by using the proposed modified-ABCD feature vector. In the modified set of ABCD features, each border feature, such as compact index, fractal dimension, and edge abruptness is considered a separate feature. Then, the composite feature vector having the pre-mentioned features is ranked using the Eigenvector Centrality (ECFS) feature ranking method. The ranked features are then classified by a cubic support vector machine for different numbers of selected features.
The proposed CLDM texture features combined with the ranked ABCD features achieved outstanding performance to classify the four targeted classes (melanoma, BCC, nevi and BKL). The results report 100% outstanding performance of the sensitivity, accuracy and specificity per each class compared to other features when using the highest seven ranked features.
The proposed system established that Melanoma, BCC, nevus and BKL are efficiently classified using cubic SVM with the new feature set. In addition, the comparative studies proved the superiority of the cubic SVM to classify the four classes.
黑色素瘤是主要的死亡原因之一，而基底细胞癌（BCC）是最常见的皮肤病变类型。在早期，医学专家可能会将其与良性痣和色素性良性角化病（BKL）混淆。这激发了当前的研究，旨在开发一种准确的、用户友好的皮肤病变识别系统。
本研究针对上述四种皮肤病变类型的新型鉴别技术。提取了一种新的基于灰度差法（GLDM）的纹理特征，称为累积水平差均值（CLDM）。不对称性、边界不规则性、颜色变化和直径被总结为 ABCD 规则特征向量，最初用于将黑色素瘤与良性病变分类。通过使用所提出的修改后的 ABCD 特征向量，将所提出的方法改进为也可以将 BCC 和 BKL 分类。在修改后的 ABCD 特征集中，每个边界特征，如紧凑指数、分形维数和边缘急剧度都被视为单独的特征。然后，使用特征向量中心度（ECFS）特征排序方法对具有上述特征的复合特征向量进行排序。然后，使用立方支持向量机对不同数量的选定特征对排序后的特征进行分类。
所提出的 CLDM 纹理特征与排序的 ABCD 特征相结合，在分类四个目标类别（黑色素瘤、BCC、痣和 BKL）方面表现出色。与其他特征相比，当使用最高的七个排序特征时，每个类别都报告了 100%的出色敏感性、准确性和特异性。
该系统建立了使用新特征集的立方 SVM 可以有效地对黑色素瘤、BCC、痣和 BKL 进行分类。此外，比较研究证明了立方 SVM 对四类分类的优越性。
