Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks
Skin lesion segmentation in dermoscopy images via deep full resolution convolutional networks
复制标题
DOI：
10.1016/j.cmpb.2018.05.027
复制
发表时间：
2018-08-01
影响因子：
6.1
通讯作者：
Kim, Tae-Seong
中科院分区：
文献类型：
--
作者：
Al-Masni, Mohammed A.;Al-antari, Mugahed A.;Kim, Tae-Seong
背景和目的：皮肤镜图像中的皮肤病灶由于其形状变化大、边界模糊等特点，其自动分割一直是一个具有挑战性的课题。皮肤病变的准确分割是任何计算机辅助诊断系统识别皮肤melanoma.Methods的关键先决条件：在本文中，我们提出了一种新的分割方法，通过全分辨率卷积网络（FrCN）。所提出的FrCN方法直接学习输入数据的每个单独像素的全分辨率特征，而不需要预处理或后处理操作，例如伪影去除、低对比度调整或进一步增强分割的皮肤病变边界。我们使用两个公开的数据库，IEEE国际生物医学成像研讨会（ISBI）2017挑战和PH 2数据集评估了所提出的方法。为了评估所提出的方法，我们将分割性能与最新的深度学习分割方法（如全卷积网络（FCN）、U-Net和SegNet）进行了比较。实验结果表明，FrCN方法分割皮肤病变的平均Jaccard指数为77.11%，整体分割准确率为94.03%对于ISBI 2017测试数据集，分别为84.79%和95.08%。与FCN、U-Net和SegNet相比，FrCN的Jaccard指数分别高出它们4.94%、15.47%和7.48%，分割精度分别高出它们1.31%、3.89%和2.27%。此外，在ISBI 2017测试数据集中，FrCN对一些典型的临床良性病例、黑色素瘤病例和脂溢性角化病病例的分割准确率分别达到95.62%、90.78%和91.29%，表现出优于FCN、U-Net和SegNet的性能。我们的结论是，使用输入图像的全空间分辨率可以使学习更好的具体和突出的功能，从而提高分割性能。(C)2018 Elsevier B. V.版权所有。
Background and objective: Automatic segmentation of skin lesions in dermoscopy images is still a challenging task due to the large shape variations and indistinct boundaries of the lesions. Accurate segmentation of skin lesions is a key prerequisite step for any computer-aided diagnostic system to recognize skin melanoma.Methods: In this paper, we propose a novel segmentation methodology via full resolution convolutional networks (FrCN). The proposed FrCN method directly learns the full resolution features of each individual pixel of the input data without the need for pre- or post-processing operations such as artifact removal, low contrast adjustment, or further enhancement of the segmented skin lesion boundaries. We evaluated the proposed method using two publicly available databases, the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Challenge and PH2 datasets. To evaluate the proposed method, we compared the segmentation performance with the latest deep learning segmentation approaches such as the fully convolutional network (FCN), U-Net, and SegNet.Results: Our results showed that the proposed FrCN method segmented the skin lesions with an average Jaccard index of 77.11% and an overall segmentation accuracy of 94.03% for the ISBI 2017 test dataset and 84.79% and 95.08%, respectively, for the PH2 dataset. In comparison to FCN, U-Net, and SegNet, the proposed FrCN outperformed them by 4.94%, 15.47%, and 7.48% for the Jaccard index and 1.31%, 3.89%, and 2.27% for the segmentation accuracy, respectively. Furthermore, the proposed FrCN achieved a segmentation accuracy of 95.62% for some representative clinical benign cases, 90.78% for the melanoma cases, and 91.29% for the seborrheic keratosis cases in the ISBI 2017 test dataset, exhibiting better performance than those of FCN, U-Net, and SegNet.Conclusions: We conclude that using the full spatial resolutions of the input image could enable to learn better specific and prominent features, leading to an improvement in the segmentation performance. (C) 2018 Elsevier B.V. All rights reserved.