arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.08650cs.CV
收藏

有侧边损失的生物医学图像复合图形分离

Compound Figure Separation of Biomedical Images with Side Loss

Vanderbilt University(范德堡大学);Tufts University(塔夫茨大学);Vanderbilt University Medical Center(范德堡大学医学中心)
Tianyuan Yao, Chang Qu, Quan Liu, Ruining Deng, Yuanhan Tian, Jiachen Xu, Aadarsh Jha, Shunxing Bao, Mengyang Zhao, Agnes B. Fogo, Bennett A. Landman, Catie Cha… 展开作者

Tianyuan Yao, Chang Qu, Quan Liu, Ruining Deng, Yuanhan Tian, Jiachen Xu, Aadarsh Jha, Shunxing Bao, Mengyang Zhao, Agnes B. Fogo, Bennett A. Landman, Catie Chang, Haichun Yang, Yuankai Huo

摘要:

无监督学习算法(例如,自监督学习、自动编码器、对比学习)允许深度学习模型从大规模未标记数据中学习有效的图像表示。在医学图像分析中,即使是未注释的数据也很难为单个实验室获得。幸运的是,国家一级已经做出努力,提供有效的途径,从以前的科学出版物中获得生物医学图像数据。例如,国家卫生研究院推出了Open-i搜索引擎,提供免费访问的大型图像数据库。然而,科学出版物中的图像由相当数量的带有子图的复合图组成。为了提取和管理单个子图,已经开发了许多不同的复合图形分离方法,特别是随着深度学习的最新进展。然而,以前的方法通常需要资源扩展限界框注释来训练检测模型。在本文中,我们提出了一个简单的复合图分离(SimCFS)框架,使用弱分类注释从个别图像。我们的技术贡献是三方面的:(1)我们引入了一个新的侧损失,设计用于复合图形分离;(2)我们引入了一个类内图像增强方法来模拟硬情况;(3)所提出的框架,使一个有效的部署到新的图像类,而不需要资源广泛的限界框注释。根据结果,SimCFS在ImageCLEF 2016复合图分离数据库上实现了新的最先进性能。SimCFS的源代码可在https://github.com/hrlblab/ImageSeperation上公开获取。

英文摘要:

Unsupervised learning algorithms (e.g., self-supervised learning, auto-encoder, contrastive learning) allow deep learning models to learn effective image representations from large-scale unlabeled data. In medical image analysis, even unannotated data can be difficult to obtain for individual labs. Fortunately, national-level efforts have been made to provide efficient access to obtain biomedical image data from previous scientific publications. For instance, NIH has launched the Open-i search engine that provides a large-scale image database with free access. However, the images in scientific publications consist of a considerable amount of compound figures with subplots. To extract and curate individual subplots, many different compound figure separation approaches have been developed, especially with the recent advances in deep learning. However, previous approaches typically required resource extensive bounding box annotation to train detection models. In this paper, we propose a simple compound figure separation (SimCFS) framework that uses weak classification annotations from individual images. Our technical contribution is three-fold: (1) we introduce a new side loss that is designed for compound figure separation; (2) we introduce an intra-class image augmentation method to simulate hard cases; (3) the proposed framework enables an efficient deployment to new classes of images, without requiring resource extensive bounding box annotations. From the results, the SimCFS achieved a new state-of-the-art performance on the ImageCLEF 2016 Compound Figure Separation Database. The source code of SimCFS is made publicly available at https://github.com/hrlblab/ImageSeperation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑