期刊
IEEE TRANSACTIONS ON MEDICAL IMAGING
卷 38, 期 10, 页码 2293-2302出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2019.2899364
关键词
Image segmentation; Training; Adaptation models; Training data; Task analysis; Data models; Pipelines; Histology; adversarial networks; segmentation; unsupervised; kidney; image-to-image translation
类别
资金
- German Research Foundation [DFG ME3737/3-1, SFB/TRR57, SFB/TRR219, BO3755/3-1, BO3755/6-1]
- German Ministry of Education and Research [BMBF STOP-FSGS-01GM1518A]
A major challenge in the field of segmentation in digital pathology is given by the high effort for manual data annotations in combination with many sources introducing variability in the image domain. This requires methods that are able to cope with variability without requiring to annotate a large amount of samples for each characteristic. In this paper, we develop approaches based on adversarial models for image-to-image translation relying on unpaired training. Specifically, we propose approaches for stain-independent supervised segmentation relying on image-to-image translation for obtaining an intermediate representation. Furthermore, we develop a fully-unsupervised segmentation approach exploiting image-to-image translation to convert from the image to the label domain. Finally, both approaches are combined to obtain optimum performance in unsupervised segmentation independent of the characteristics of the underlying stain. Experiments on patches showing kidney histology proof that stain-translation can be performed highly effectively and can be used for domain adaptation to obtain independence of the underlying stain. It is even capable of facilitating the underlying segmentation task, thereby boosting the accuracy if an appropriate intermediate stain is selected. Combining domain adaptation with unsupervised segmentation finally showed the most significant improvements.
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