Seidenari Stefania, Grana Costantino, Pellacani Giovanni
Department of Dermatology, University of Modena and Reggio Emilia, Modena, Italy.
Dermatology. 2007;214(2):137-43. doi: 10.1159/000098573.
To overcome subjectivity and variability in the interpretation of dermoscopic images, image analysis programs, enabling the numerical description of melanocytic lesion images, have been developed.
Our aim was to assess a method for the description of colours in melanocytic lesion images, based on the subdivision of image colours into red, green and blue clusters.
Melanomas and naevi of the test set were described by means of 23 colour clusters previously selected by a training set comprising 369 melanocytic lesion images. The diagnostic performance obtained by this automated method was compared to sensitivity and specificity of diagnosis of 4 dermatologists.
Colour cluster values significantly differed between melanomas and naevi. Moreover, sensitivity and specificity values of computer diagnosis were similar to those achieved by the dermatologists.
Our image analysis program based on the assessment of one single parameter has the diagnostic accuracy of dermatologists employing dermoscopy on a regular basis.
为克服皮肤镜图像解读中的主观性和变异性，已开发出能够对黑素细胞病变图像进行数值描述的图像分析程序。
我们的目的是评估一种基于将图像颜色细分为红色、绿色和蓝色簇来描述黑素细胞病变图像颜色的方法。
通过先前由包含369张黑素细胞病变图像的训练集选择的23个颜色簇来描述测试集的黑色素瘤和痣。将这种自动化方法获得的诊断性能与4名皮肤科医生的诊断敏感性和特异性进行比较。
黑色素瘤和痣之间的颜色簇值有显著差异。此外，计算机诊断的敏感性和特异性值与皮肤科医生的相似。
我们基于单一参数评估的图像分析程序具有皮肤科医生定期使用皮肤镜检查的诊断准确性。
