Concentric decile segmentation of white and hypopigmented areas in dermoscopy images of skin lesions allows discrimination of malignant melanoma.
Concentric decile segmentation of white and hypopigmented areas in dermoscopy images of skin lesions allows discrimination of malignant melanoma.
复制标题
DOI：
10.1016/j.compmedimag.2010.09.009
复制
发表时间：
2011-03
影响因子：
5.7
通讯作者：
Perry, Lindall A.
中科院分区：
文献类型：
--
作者：
Dalal, Ankur;Moss, Randy H.;Stanley, R. Joe;Stoecker, William V.;Gupta, Kapil;Calcara, David A.;Xu, Jin;Shrestha, Bijaya;Drugge, Rhett;Malters, Joseph M.;Perry, Lindall A.
皮肤镜检查，也称为皮肤表面透光显微镜检查或皮表镜检查，能够使肉眼检查无法识别的色素性黑素细胞肿瘤的特征可视化。白色区域在早期恶性黑素瘤和原位黑素瘤中较为显著，有助于这些病变的早期检测。
已经研究了一种自适应检测方法，用于根据病变的直方图统计数据识别白色和色素减退区域。利用欧几里得距离变换，将病变按同心十分位数进行分割。确定白色区域在病变十分位数上的覆盖情况。自动检测到的白色区域的计算特征包括病变十分位数比率、白色区域的标准化数量、最大白色区域的绝对和相对大小、所有白色区域的相对大小以及白色区域的离心率、离散度和不规则性。
利用反向传播神经网络，白色区域的统计数据对黑素瘤与良性痣的诊断准确率超过95%。黑素瘤中的白色和色素减退区域往往位于中心或近中心位置。多变量分析中最有力的四个特征是病变十分位数比率。
利用病变统计数据可以自动检测黑素瘤中的白色和色素减退区域。神经网络利用这些区域能够很好地区分黑素瘤和良性痣。病变十分位数比率是有用的白色区域特征。
Dermoscopy, also known as dermatoscopy or epiluminescence microscopy (ELM), permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. White areas, prominent in early malignant melanoma and melanoma in situ, contribute to early detection of these lesions. An adaptive detection method has been investigated to identify white and hypopigmented areas based on lesion histogram statistics. Using the Euclidean distance transform, the lesion is segmented in concentric deciles. Overlays of the white areas on the lesion deciles are determined. Calculated features of automatically detected white areas include lesion decile ratios, normalized number of white areas, absolute and relative size of largest white area, relative size of all white areas, and white area eccentricity, dispersion, and irregularity. Using a back-propagation neural network, the white area statistics yield over 95% diagnostic accuracy of melanomas from benign nevi. White and hypopigmented areas in melanomas tend to be central or paracentral. The four most powerful features on multivariate analysis are lesion decile ratios. Automatic detection of white and hypopigmented areas in melanoma can be accomplished using lesion statistics. A neural network can achieve good discrimination of melanomas from benign nevi using these areas. Lesion decile ratios are useful white area features.
登录
查看更多内容
影响因子：
254.7
作者：
Jemal, Ahmedin;Siegel, Rebecca;Thun, Michael J.
通讯作者：
Thun, Michael J.
影响因子：
2.2
作者：
Seidenari, S;Pellacani, G;Grana, C
通讯作者：
Grana, C
影响因子：
5.7
作者：
Celebi, M. Emre;Iyatomi, Hitoshi;Schaefer, Gerald;Stoecker, William V.
通讯作者：
Stoecker, William V.
影响因子：
13.8
作者：
Argenziano, G;Soyer, HP;Wolff, K
通讯作者：
Wolff, K
影响因子：
2.4
作者：
Salopek, TG;Kopf, AW;Yadav, S
通讯作者：
Yadav, S