期刊
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
卷 24, 期 9, 页码 2473-2480出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2020.2970091
关键词
Object detection; Task analysis; Red blood cells; Gallium nitride; Biological system modeling; Biomedical imaging; CycleGAN; cell detection; data augmentation; machine learning; pathology
类别
资金
- BUPT Excellent Ph.D.
- Students Foundation [CX2019318]
- National Key Research & Development Plan of China [2017YFC1307705]
The object detection, which has been widely applied in the biomedical field already, is of real significance but technically challenging. In practice, the object detection accuracy is vulnerable to labeling quality, which is usually not a big headache for simple algorithm or model verification since there are a bunch of ideal public available datasets whose classes and tags are all well-marked. However, in real scenarios, image data is often partially or even incorrectly labeled. Particularly, in cell detection, this becomes a thorny issue since the labelling of the dataset is incomplete and inaccurate. To address this issue, we propose a data-augmentation algorithm that can generate full labeled cell image data from incomplete labeled ones. First of all, we randomly extract the labeled objects from raw cell images, and meanwhile, keep their corresponding position information. Next, we employ the framework of cycle-consistent adversarial network, but significantly distinguished from the original one, to generate fully labeled data including both objects and backgrounds. We conduct extensive experiments on a blood cell classification dataset called BCCD to evaluate our model, and experimental results show that our proposed method can successfully address the weak annotation problem and improve the performance of object detection.
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