Classification for Dermoscopy Images Using Convolutional Neural Networks Based on Region Average Pooling
Classification for Dermoscopy Images Using Convolutional Neural Networks Based on Region Average Pooling
复制标题
DOI：
10.1109/access.2018.2877587
复制
发表时间：
2018-10
期刊：
影响因子：
3.9
通讯作者：
Jiawen Yang;Feng-ying Xie;Haidi Fan;Zhi-guo Jiang;Jie Liu
中科院分区：
文献类型：
--
作者：
Jiawen Yang;Feng-ying Xie;Haidi Fan;Zhi-guo Jiang;Jie Liu
本文提出了一种基于卷积神经网络的皮肤镜图像黑色素瘤分类方法。首先引入区域平均池化（RAPooling）方法，使特征提取能够集中在感兴趣的区域；然后设计了结合分割信息的端到端分类框架，利用分割后的病变区域引导RAPooling进行分类。最后，利用基于ROC曲线下面积的线性分类器RankOpt进行优化，得到最终的分类结果。该方法将分割信息融入到分类任务中，并通过RankOpt的优化，获得了对不平衡皮肤镜图像数据集更好的分类性能。在ISBI 2017皮肤病变分析上对黑色素瘤检测挑战数据集进行了实验，并与其他最先进的方法进行了比较，证明了我们的方法的有效性。
In this paper, a novel melanoma classification method based on convolutional neural networks is proposed for dermoscopy images. First a region average pooling (RAPooling) method is introduced which makes feature extraction can focus on the region of interest. Then an end-to-end classification framework combining with segmentation information is designed, which uses the segmented lesion region to guide the classification by RAPooling. Finally, a linear classifier RankOpt based on the area under the ROC curve is used to optimize and obtain the final classification result. The proposed method integrates segmentation information into the classification task, and in addition, by the optimization of RankOpt, a better classification performance for imbalanced dermoscopy image dataset is obtained. Experiments are conducted on ISBI 2017 skin lesion analysis towards melanoma detection challenge dataset, and comparisons with the other state-of-the-art methods demonstrate the effectiveness of our method.