School of Engineering, Computer, and Mathematical Sciences, Auckland University of Technology, 55 Wellesley street, 1010, Auckland, New Zealand.
School of Innovation Design and Engineering, Mälardalen University, Västerås, Sweden.
BMC Med Imaging. 2022 May 29;22(1):103. doi: 10.1186/s12880-022-00829-y.
Melanoma is the most dangerous and aggressive form among skin cancers, exhibiting a high mortality rate worldwide. Biopsy and histopathological analysis are standard procedures for skin cancer detection and prevention in clinical settings. A significant step in the diagnosis process is the deep understanding of the patterns, size, color, and structure of lesions based on images obtained through dermatoscopes for the infected area. However, the manual segmentation of the lesion region is time-consuming because the lesion evolves and changes its shape over time, making its prediction challenging. Moreover, it is challenging to predict melanoma at the initial stage as it closely resembles other skin cancer types that are not malignant as melanoma; thus, automatic segmentation techniques are required to design a computer-aided system for accurate and timely detection.
As deep learning approaches have gained significant attention in recent years due to their remarkable performance, therefore, in this work, we proposed a novel design of a convolutional neural network (CNN) framework based on atrous convolutions for automatic lesion segmentation. This architecture is built based on the concept of atrous/dilated convolutions which are effective for semantic segmentation. A deep neural network is designed from scratch employing several building blocks consisting of convolutional, batch normalization, leakyReLU layer, and fine-tuned hyperparameters contributing altogether towards higher performance.
The network was tested on three benchmark datasets provided by International Skin Imaging Collaboration (ISIC), i.e., ISIC 2016, ISIC 2017, and ISIC 2018. The experimental results showed that the proposed network achieved an average Jaccard index of 90.4% on ISIC 2016, 81.8% on ISIC 2017, and 89.1% on ISIC 2018 datasets, respectively which is recorded as higher than the top three winners of the ISIC challenge and other state-of-the-art methods. Also, the model successfully extracts lesions from the whole image in one pass in less time, requiring no pre-processing step. The conclusions yielded that network is accurate in performing lesion segmentation on adopted datasets.
黑色素瘤是皮肤癌中最危险和最具侵袭性的形式，在全球范围内死亡率很高。活检和组织病理学分析是临床中皮肤癌检测和预防的标准程序。在诊断过程中，一个重要步骤是根据皮肤科医生获取的受感染区域的图像，深入了解病变的模式、大小、颜色和结构。然而，由于病变会随时间演变并改变形状，因此病变区域的手动分割非常耗时，这使得预测变得具有挑战性。此外，由于黑色素瘤在初始阶段难以预测，因为它与其他非恶性皮肤癌类型非常相似，因此需要自动分割技术来设计用于准确和及时检测的计算机辅助系统。
由于深度学习方法近年来因其出色的性能而受到广泛关注，因此，在这项工作中，我们提出了一种基于空洞卷积的新型卷积神经网络 (CNN) 框架设计，用于自动病变分割。该架构基于空洞/扩张卷积的概念构建，这些卷积对于语义分割非常有效。使用由卷积、批量归一化、泄漏 ReLU 层和微调超参数组成的几个构建块从头开始设计深度神经网络，这些构建块共同提高了性能。
该网络在国际皮肤成像协作 (ISIC) 提供的三个基准数据集上进行了测试，即 ISIC 2016、ISIC 2017 和 ISIC 2018。实验结果表明，所提出的网络在 ISIC 2016 数据集上的平均 Jaccard 指数为 90.4%，在 ISIC 2017 数据集上为 81.8%，在 ISIC 2018 数据集上为 89.1%，分别高于 ISIC 挑战赛的前三名获奖者和其他最先进的方法。此外，该模型成功地在一次传递中从整个图像中提取病变，所需时间更少，且无需预处理步骤。结论表明，该网络在采用的数据集上进行病变分割是准确的。
