arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.07097cs.CV
收藏

CELNet:基于弱监督学习的病理图像证据定位

CELNet: Evidence Localization for Pathology Images using Weakly Supervised Learning

The Hong Kong University of Science and Technology(香港科技大学)

Yongxiang Huang, Albert C. S. Chung

摘要:

尽管深度卷积神经网络提高了数字病理分析中图像分类和分割的性能,但它们通常在临床应用的可解释性方面较弱,或者需要大量注释来实现对象定位。为了克服这个问题,我们提出了一个弱监督学习为基础的方法,可以有效地学习本地化的歧视性证据的诊断标签从弱标记的训练数据。实验结果表明,我们所提出的方法可以可靠地查明癌症证据的位置,支持感兴趣的决定,同时仍然实现了具有竞争力的表现,在一瞥级和幻灯片级的组织病理学癌症检测任务。

英文摘要:

Despite deep convolutional neural networks boost the performance of image classification and segmentation in digital pathology analysis, they are usually weak in interpretability for clinical applications or require heavy annotations to achieve object localization. To overcome this problem, we propose a weakly supervised learning-based approach that can effectively learn to localize the discriminative evidence for a diagnostic label from weakly labeled training data. Experimental results show that our proposed method can reliably pinpoint the location of cancerous evidence supporting the decision of interest, while still achieving a competitive performance on glimpse-level and slide-level histopathologic cancer detection tasks.

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。

↑