当前位置: X-MOL 学术IEEE J. Biomed. Health Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Multi-Source Transfer Learning Via Multi-Kernel Support Vector Machine Plus for B-Mode Ultrasound-Based Computer-Aided Diagnosis of Liver Cancers
IEEE Journal of Biomedical and Health Informatics ( IF 7.7 ) Pub Date : 2021-04-16 , DOI: 10.1109/jbhi.2021.3073812
Huili Zhang 1 , Lehang Guo 2 , Dan Wang 3 , Jun Wang 4 , Lili Bao 5 , Shihui Ying 6 , Huixiong Xu 7 , Jun Shi 8
Affiliation  

B-mode ultrasound (BUS) imaging is a routine tool for diagnosis of liver cancers, while contrast-enhanced ultrasound (CEUS) provides additional information to BUS on the local tissue vascularization and perfusion to promote diagnostic accuracy. In this work, we propose to improve the BUS-based computer aided diagnosis for liver cancers by transferring knowledge from the multi-view CEUS images, including the arterial phase, portal venous phase, and delayed phase, respectively. To make full use of the shared labels of paired of BUS and CEUS images to guide knowledge transfer, support vector machine plus (SVM+), a specifically designed transfer learning (TL) classifier for paired data with shared labels, is adopted for this supervised TL. A nonparallel hyperplane based SVM+ (NHSVM+) is first proposed to improve the TL performance by transferring the per-class knowledge from source domain to the corresponding target domain. Moreover, to handle the issue of multi-source TL, a multi-kernel learning based NHSVM+ (MKL-NHSVM+) algorithm is further developed to effectively transfer multi-source knowledge from multi-view CEUS images. The experimental results indicate that the proposed MKL-NHSVM+ outperforms all the compared algorithms for diagnosis of liver cancers, whose mean classification accuracy, sensitivity, and specificity are 88.18 ± 3.16 %, 86.98 ± 4.77 %, and 89.42±3.77%, respectively.

中文翻译:

通过多核支持向量机 Plus 进行多源转移学习,用于基于 B 型超声的肝癌计算机辅助诊断

B 型超声 (BUS) 成像是诊断肝癌的常规工具,而对比增强超声 (CEUS) 为 BUS 提供有关局部组织血管化和灌注的额外信息,以提高诊断准确性。在这项工作中,我们建议通过从多视图 CEUS 图像(分别包括动脉期、门静脉期和延迟期)中转移知识来改进基于 BUS 的计算机辅助肝癌诊断。为了充分利用成对的 BUS 和 CEUS 图像的共享标签来指导知识转移,支持向量机加 (SVM+),一种专门设计的用于具有共享标签的配对数据的转移学习 (TL) 分类器,用于此监督 TL . 首先提出了一种基于非平行超平面的 SVM+(NHSVM+),通过将每类知识从源域转移到相应的目标域来提高 TL 性能。此外,为了处理多源 TL 问题,进一步开发了基于多核学习的 NHSVM+ (MKL-NHSVM+) 算法,以有效地从多视图 CEUS 图像中传输多源知识。实验结果表明,所提出的 MKL-NHSVM+ 优于所有用于肝癌诊断的比较算法,其平均分类准确度、灵敏度和特异性分别为 88.18±3.16%、86.98±4.77% 和 89.42±3.77%。进一步开发了基于多核学习的 NHSVM+ (MKL-NHSVM+) 算法,以有效地从多视图 CEUS 图像中传输多源知识。实验结果表明,所提出的 MKL-NHSVM+ 优于所有用于肝癌诊断的比较算法,其平均分类准确度、敏感性和特异性分别为 88.18±3.16%、86.98±4.77% 和 89.42±3.77%。进一步开发了基于多核学习的 NHSVM+ (MKL-NHSVM+) 算法,以有效地从多视图 CEUS 图像中传输多源知识。实验结果表明,所提出的 MKL-NHSVM+ 优于所有用于肝癌诊断的比较算法,其平均分类准确度、灵敏度和特异性分别为 88.18±3.16%、86.98±4.77% 和 89.42±3.77%。
更新日期:2021-04-16
down
wechat
bug