Shan Pufang, Wang Yiding, Fu Chong, Song Wei, Chen Junxin
School of Computer Science and Engineering, Northeastern University, Shenyang, 110819, China.
School of Computer Science and Engineering, Northeastern University, Shenyang, 110819, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, 110819, China.
Comput Biol Med. 2020 Aug;123:103762. doi: 10.1016/j.compbiomed.2020.103762. Epub 2020 Jul 17.
Automatic skin lesion segmentation in dermoscopy images is challenging due to the diversity of skin lesion characteristics, low contrast between normal skin and lesions, and the existence of many artefacts in the images. To meet these challenges, we propose a novel segmentation topology called FC-DPN, which is built upon a fully convolutional network (FCN) and dual path network (DPN). The DPN inherits the advantages of residual and densely connected paths, enabling effective feature re-usage and re-exploitation. We replace dense blocks in fully convolutional DenseNets (FC-DenseNets) with two kinds of sub-DPN blocks, namely, sub-DPN projection blocks and sub-DPN processing blocks. This framework enables FC-DPN to acquire more representative and discriminative features for more accurate segmentation. Many images in the original ISBI 2017 Skin Lesion Challenge test dataset are given the incorrect or inaccurate ground truths, and these ground truths have been revised. The revised test dataset is called the modified ISBI 2017 Skin Lesion Challenge test dataset. The proposed method achieves an average Dice coefficient of 88.13% and a Jaccard index of 80.02% on the modified ISBI 2017 Skin Lesion Challenge test dataset and 90.26% and 83.51%, respectively, on the PH2 dataset. Extensive experimental results on the two datasets demonstrate that the proposed method exhibits better performance than FC-DenseNets and other well-established segmentation algorithms.
由于皮肤病变特征的多样性、正常皮肤与病变之间的低对比度以及图像中存在许多伪影，皮肤镜图像中的自动皮肤病变分割具有挑战性。为了应对这些挑战，我们提出了一种名为FC-DPN的新型分割拓扑结构，它基于全卷积网络（FCN）和双路径网络（DPN）构建。DPN继承了残差路径和密集连接路径的优点，能够有效地重复使用和重新利用特征。我们用两种子DPN块，即子DPN投影块和子DPN处理块，替换了全卷积密集网络（FC-DenseNets）中的密集块。该框架使FC-DPN能够获取更具代表性和判别力的特征，以实现更准确的分割。原始的ISBI 2017皮肤病变挑战测试数据集中的许多图像被给出了不正确或不准确的真值，并且这些真值已经被修正。修正后的测试数据集称为修改后的ISBI 2017皮肤病变挑战测试数据集。所提出的方法在修改后的ISBI 2017皮肤病变挑战测试数据集上的平均Dice系数为88.13%，Jaccard指数为80.02%，在PH2数据集上分别为90.26%和83.51%。在这两个数据集上的大量实验结果表明，所提出的方法比FC-DenseNets和其他成熟的分割算法表现出更好的性能。
