Deep Active Learning for Cryo-Electron Tomography Classification

Deep Active Learning for Cryo-Electron Tomography Classification
复制标题

DOI：
10.1109/icip46576.2022.9898002
复制
发表时间：
2022-10
期刊：
2022 IEEE International Conference on Image Processing (ICIP)
影响因子：
--
通讯作者：
Tianyang Wang;Bo Li;Jing Zhang;Xiangrui Zeng;Mostofa Rafid Uddin;Wei Wu;Min Xu
Tianyang Wang;Bo Li;Jing Zhang;Xiangrui Zeng;Mostofa Rafid Uddin;Wei Wu;Min Xu
中科院分区：
其他
文献类型：
--
作者：
Tianyang Wang;Bo Li;Jing Zhang;Xiangrui Zeng;Mostofa Rafid Uddin;Wei Wu;Min Xu

文献摘要

相似文献

低温电子断层成像（cryo-ET）是一种新兴的三维成像技术，在结构生物学研究中显示出巨大的潜力。其中一个主要的挑战是执行由冷冻ET捕获的大分子的分类。最近的努力利用深度学习来应对这一挑战。然而，训练可靠的深度模型通常需要大量有监督的标记数据。注释低温ET数据可以说是非常昂贵的。深度主动学习（DAL）可以用来降低标记成本，同时不会过多地牺牲任务性能。然而，大多数现有的方法诉诸辅助模型或复杂的方式（如对抗学习）的不确定性估计，DAL的核心。这些模型需要针对需要3D网络的冷冻ET任务进行高度定制，并且调整这些模型也必不可少，这给冷冻ET任务的部署带来了困难。为了解决这些挑战，我们提出了一种新的DAL数据选择指标，它也可以作为经验损失的正则化器，进一步提升任务模型。我们证明了我们的方法的优越性，通过模拟和真实的冷冻ET数据集上的广泛实验。我们的源代码和附录可以在这个URL中找到。
Cryo-Electron Tomography (cryo-ET) is an emerging 3D imaging technique which shows great potentials in structural biology research. One of the main challenges is to perform classification of macromolecules captured by cryo-ET. Re-cent efforts exploit deep learning to address this challenge. However, training reliable deep models usually requires a huge amount of labeled data in supervised fashion. Annotating cryo-ET data is arguably very expensive. Deep Active Learning (DAL) can be used to reduce labeling cost while not sacrificing the task performance too much. Nevertheless, most existing methods resort to auxiliary models or complex fashions (e.g. adversarial learning) for uncertainty estimation, the core of DAL. These models need to be highly customized for cryo-ET tasks which require 3D networks, and extra efforts are also indispensable for tuning these models, rendering a difficulty of deployment on cryo-ET tasks. To address these challenges, we propose a novel metric for data selection in DAL, which can also be leveraged as a regularizer of the empirical loss, further boosting the task model. We demonstrate the superiority of our method via extensive experiments on both simulated and real cryo-ET datasets. Our source Code and Appendix can be found at this URL.