Automated delineation of dermal-epidermal junction in reflectance confocal microscopy image stacks of human skin.
Automated delineation of dermal-epidermal junction in reflectance confocal microscopy image stacks of human skin.
复制标题
DOI：
10.1038/jid.2014.379
复制
发表时间：
2015-03
影响因子：
6.5
通讯作者：
Rajadhyaksha, Milind
中科院分区：
文献类型：
--
作者：
Kurugol, Sila;Kose, Kivanc;Park, Brian;Dy, Jennifer G.;Brooks, Dana H.;Rajadhyaksha, Milind
反射共聚焦显微镜（RCM）图像皮肤非侵入性，光学切片和核水平的分辨率与病理学。基于对真皮-表皮连接（DEJ）及其附近的形态学特征的评估，可以以高灵敏度和特异性在体内诊断皮肤癌。然而，当前用于阅读图像的视觉、定性方法导致诊断中的主观可变性。我们假设基于机器学习的算法可以实现更定量、更客观的方法。测试和验证进行了两个算法，可以自动描绘正常人体皮肤的RCM堆栈中的DEJ。测试集由15个白色和15个深色皮肤堆叠（30名受试者）组成，具有专家标签。在黑色素导致对比度高的深色皮肤中，该算法产生的平均误差为7.9±6.4μm。在白皙皮肤中，该算法将DEJ描绘为过渡区，表皮至过渡区边界的平均误差为8.3±5.8μm，过渡区至真皮的平均误差为7.6±5.6μm。我们的研究结果表明，自动化算法可以定量指导DEJ的划定，以协助RCM图像的客观阅读。这些算法的进一步发展可以指导在DEJ的异常形态特征的评估。
Reflectance confocal microscopy (RCM) images skin non-invasively, with optical sectioning and nuclear-level resolution comparable to that of pathology. Based on assessment of the dermal-epidermal junction (DEJ) and morphologic features in its vicinity, skin cancer can be diagnosed in vivo with high sensitivity and specificity. However, the current visual, qualitative approach for reading images leads to subjective variability in diagnosis. We hypothesize that machine learning-based algorithms may enable a more quantitative, objective approach. Testing and validation was performed with two algorithms that can automatically delineate the DEJ in RCM stacks of normal human skin. The test set was composed of 15 fair and 15 dark skin stacks (30 subjects) with expert labellings. In dark skin, in which the contrast is high due to melanin, the algorithm produced an average error of 7.9±6.4μm. In fair skin, the algorithm delineated the DEJ as a transition zone, with average error of 8.3±5.8μm for the epidermis-to-transition zone boundary and 7.6±5.6μm for the transition zone-to-dermis. Our results suggest that automated algorithms may quantitatively guide the delineation of the DEJ, to assist in objective reading of RCM images. Further development of such algorithms may guide assessment of abnormal morphological features at the DEJ.
登录
查看更多内容
影响因子：
3.5
作者：
Kurugol, Sila;Dy, Jennifer G.;Rajadhyaksha, Milind
通讯作者：
Rajadhyaksha, Milind
影响因子：
3.5
作者：
Gareau, Dan;Hennessy, Ricky;Jacques, Steven L.
通讯作者：
Jacques, Steven L.
DOI：
10.1109/34.761261
发表时间：
1999-04-01
影响因子：
23.6
作者：
Randen, T;Husoy, JH
通讯作者：
Husoy, JH
影响因子：
7.5
作者：
CORTES, C;VAPNIK, V
通讯作者：
VAPNIK, V
影响因子：
6.5
作者：
Guitera, Pascale;Menzies, Scott W.;Pellacani, Giovanni
通讯作者：
Pellacani, Giovanni