Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks
复制标题
DOI：
10.1109/tmi.2016.2642839
复制
发表时间：
2017-04-01
影响因子：
10.6
通讯作者：
Heng, Pheng-Ann
中科院分区：
文献类型：
--
作者：
Yu, Lequan;Chen, Hao;Heng, Pheng-Ann
由于皮肤病变的低对比度、黑色素瘤的巨大类内变化、黑色素瘤和非黑色素瘤病变之间的高度视觉相似性以及图像中存在许多伪影，皮肤镜图像中的自动黑色素瘤识别是一项非常具有挑战性的任务。为了应对这些挑战，我们提出了一种利用非常深的卷积神经网络（CNN）进行黑色素瘤识别的新方法。与现有的采用低级手工特征或具有较浅架构的CNN的方法相比，我们的更深的网络（超过50层）可以获得更丰富，更具鉴别力的特征，以实现更准确的识别。为了充分利用深度网络，我们提出了一套方案，以确保在有限的训练数据下进行有效的训练和学习。首先，我们应用残差学习来科普网络深入时的退化和过拟合问题。这种技术可以确保我们的网络从增加网络深度所获得的性能增益中受益。然后，我们构建了一个完全卷积残差网络（FCRN），用于准确的皮肤病变分割，并通过结合多尺度上下文信息集成方案进一步增强其能力。最后，我们无缝集成了所提出的FCRN（用于分割）和其他非常深的残差网络（用于分类），以形成一个两阶段框架。该框架使分类网络能够基于分割结果而不是整个皮肤镜图像来提取更具代表性和特异性的特征，进一步缓解了训练数据的不足。在ISBI 2016皮肤病变分析对黑色素瘤检测挑战数据集上对所提出的框架进行了广泛评估。实验结果表明，该框架的显着的性能增益，排名第一，在25个团队和28个团队中，分别在第二的分类和分割。这项研究证实，具有有效训练机制的深度CNN可以用于解决复杂的医学图像分析任务，即使训练数据有限。
Automated melanoma recognition in dermoscopy images is a very challenging task due to the low contrast of skin lesions, the huge intraclass variation of melanomas, the high degree of visual similarity between melanoma and non-melanoma lesions, and the existence of many artifacts in the image. In order to meet these challenges, we propose a novel method for melanoma recognition by leveraging very deep convolutional neural networks (CNNs). Compared with existingmethods employing either low-level hand-crafted features or CNNs with shallower architectures, our substantially deeper networks (more than 50 layers) can acquire richer and more discriminative features for more accurate recognition. To take full advantage of very deep networks, we propose a set of schemes to ensure effective training and learning under limited training data. First, we apply the residual learning to cope with the degradation and overfitting problems when a network goes deeper. This technique can ensure that our networks benefit from the performance gains achieved by increasing network depth. Then, we construct a fully convolutional residual network (FCRN) for accurate skin lesion segmentation, and further enhance its capability by incorporating a multi-scale contextual information integration scheme. Finally, we seamlessly integrate the proposed FCRN (for segmentation) and other very deep residual networks (for classification) to form a two-stage framework. This framework enables the classificationnetwork to extract more representative and specific features based on segmented results instead of the whole dermoscopy images, further alleviating the insufficiency of training data. The proposed framework is extensively evaluated on ISBI 2016 Skin Lesion Analysis Towards Melanoma Detection Challenge dataset. Experimental results demonstrate the significant performance gains of the proposed framework, ranking the first in classification and the second in segmentation among 25 teams and 28 teams, respectively. This study corroborates that very deep CNNs with effective training mechanisms can beemployed to solve complicatedmedical image analysis tasks, even with limited training data.