期刊
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
卷 18, 期 1, 页码 40-52出版社
IEEE COMPUTER SOC
DOI: 10.1109/TCBB.2019.2963873
关键词
Medical image segmentation; fuzzy clustering; transfer learning; negative transfer
类别
资金
- National Natural Science Foundation of China [61806026, 61702225, 61772241, 61711540041]
- Natural Science Foundation of Jiangsu Province [BK20180956, BK20161268, BK20160187]
- Fundamental Re-search Funds for the Central Universities [JUSRP51614A, JUSRP11737]
- Qinglan Project of Jiangsu Province
- Six Talent Peaks Project of Jiangsu Province [XYDXX-127]
Traditional clustering algorithms for medical image segmentation often struggle with noise and outliers, but transfer learning can improve learning performance by leveraging knowledge from related domains. The proposed negative-transfer-resistant mechanism calculates weights of transferred knowledge to achieve positive transfer and avoid negative transfer. The NTR-FC-SCT model, integrating negative-transfer-resistant and MMD, outperformed traditional non-transfer and related transfer clustering algorithms in experiments.
Traditional clustering algorithms for medical image segmentation can only achieve satisfactory clustering performance under relatively ideal conditions, in which there is adequate data from the same distribution, and the data is rarely disturbed by noise or outliers. However, a sufficient amount of medical images with representative manual labels are often not available, because medical images are frequently acquired with different scanners (or different scan protocols) or polluted by various noises. Transfer learning improves learning in the target domain by leveraging knowledge from related domains. Given some target data, the performance of transfer learning is determined by the degree of relevance between the source and target domains. To achieve positive transfer and avoid negative transfer, a negative-transfer-resistant mechanism is proposed by computing the weight of transferred knowledge. Extracting a negative-transfer-resistant fuzzy clustering model with a shared cross-domain transfer latent space (called NTR-FC-SCT) is proposed by integrating negative-transfer-resistant and maximum mean discrepancy (MMD) into the framework of fuzzy c-means clustering. Experimental results show that the proposed NTR-FC-SCT model outperformed several traditional non-transfer and related transfer clustering algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据