Skin lesion segmentation using deep convolution networks guided by local unsupervised learning
Skin lesion segmentation using deep convolution networks guided by local unsupervised learning
复制标题
DOI：
10.1147/jrd.2017.2708283
复制
发表时间：
2017-07-01
影响因子：
1.3
通讯作者：
Garnavi, R.
中科院分区：
文献类型：
--
作者：
Bozorgtabar, B.;Sedai, S.;Garnavi, R.
皮肤镜图像中皮肤病变的自动定位是开发皮肤癌检测决策支持系统的关键一步。然而，病变图像的分割是具有挑战性的，因为这些图像具有各种伪影，扭曲了病变区域的均匀性。近年来，基于深度卷积学习的图像分割技术受到了广泛的关注。这些深度网络产生粗分割，卷积滤波器和池化层导致以低于原始皮肤图像的分辨率分割皮肤病变。为了克服这些缺点，我们提出了一种基于超像素的微调策略，有效地利用皮肤图像像素的特征来准确提取病灶的边界。我们提出的方法不仅可以学习皮肤病变的全局地图，还可以获取病灶边界等局部上下文信息。因此，即使在存在模糊边界和复杂纹理的情况下，它也可以准确地分割给定皮肤图像中的病变。为了评估我们提出的方法的性能，使用2016年国际生物医学成像研讨会数据集进行了实验，这些实验表明了我们提出的方法的有效性。
Automatic localization of skin lesions within dermoscopy images is a crucial step toward developing a decision support system for skin cancer detection. However, segmentation of the lesion image can he challenging, as these images possess various artifacts distorting the uniformity of the lesion area. Recently, deep convolution learning-based techniques have drawn great attention for pixel-wise image segmentation. These deep networks produce coarse segmentation, and convolutional filters and pooling layers result in segmentation of a skin lesion at a lower resolution than the original skin image. To overcome these drawbacks, we have proposed a superpixel-based fine-tuning strategy to effectively utilize the characteristics of the skin image pixels to accurately extract the border of the lesion. Our proposed approach not only learns a global map for skin lesions, hut also acquires the local contextual information, such as lesion boundary. It can, therefore, accurately segment lesions within a given skin image, even in the presence of fuzzy boundaries and complex textures. To evaluate the performance of our proposed method, experiments have been conducted using the 2016 International Symposium on Biomedical Imaging dataset, and these experiments suggest the effectiveness of the proposed method.