A novel dual-network architecture for mixed-supervised medical image segmentation.

A novel dual-network architecture for mixed-supervised medical image segmentation.
复制标题

DOI:
10.1016/j.compmedimag.2020.101841
复制
发表时间:
2021-04
期刊:
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
影响因子:
--
通讯作者:
Jayender J
Jayender J
中科院分区:
其他
文献类型:
--
作者:
Wang D;Li M;Ben-Shlomo N;Corrales CE;Cheng Y;Zhang T;Jayender J

文献摘要

参考文献

相似文献

在医学图像分割任务中,基于深度学习的模型通常需要密集且精确的注释数据集来训练,这是耗时且昂贵的准备。一种可能的解决方案是使用混合监督数据集进行训练,其中只有一部分数据使用分割图进行密集注释,其余部分使用某种弱形式进行注释,例如边界框。在本文中,我们提出了一种新的网络架构称为混合监督双网(MSDN),它由两个单独的网络分别为分割和检测任务,和一系列的连接模块之间的两个网络的层。这些连接模块用于从检测任务中提取和传输有用的信息,以帮助分割任务。我们在连接模块中利用了最近设计的一种称为“挤压和激励”的技术的变体,以促进两个任务之间的信息传输。与已有的共享主干多分支模型相比,该模型具有灵活的、可训练的特征共享方式,因而更有效、更稳定。我们在4个医学图像分割数据集上进行了实验,实验结果表明,提出的MSDN模型优于多个基线。
In medical image segmentation tasks, deep learning-based models usually require densely and precisely annotated datasets to train, which are time-consuming and expensive to prepare. One possible solution is to train with the mixed-supervised dataset, where only a part of data is densely annotated with segmentation map and the rest is annotated with some weak form, such as bounding box. In this paper, we propose a novel network architecture called Mixed-Supervised Dual-Network (MSDN), which consists of two separate networks for the segmentation and detection tasks respectively, and a series of connection modules between the layers of the two networks. These connection modules are used to extract and transfer useful information from the detection task to help the segmentation task. We exploit a variant of a recently designed technique called ‘Squeeze and Excitation’ in the connection module to boost the information transfer between the two tasks. Compared with existing model with shared backbone and multiple branches, our model has flexible and trainable feature sharing fashion and thus is more effective and stable. We conduct experiments on 4 medical image segmentation datasets, and experiment results show that the proposed MSDN model outperforms multiple baselines.
DOI: 10.1016/j.media.2019.02.009
发表时间: 2019-05-01
影响因子: 10.9
作者:
Kervadec, Hoel;Dolz, Jose;Ben Ayed, Ismail
通讯作者: Ben Ayed, Ismail
DOI: 10.1109/tpami.2018.2844175
发表时间: 2020-02-01
影响因子: 23.6
作者:
He, Kaiming;Gkioxari, Georgia;Girshick, Ross
通讯作者: Girshick, Ross
DOI: 10.1109/tpami.2017.2699184
发表时间: 2018-04-01
影响因子: 23.6
作者:
Chen, Liang-Chieh;Papandreou, George;Yuille, Alan L.
通讯作者: Yuille, Alan L.
DOI: 10.3174/ajnr.a6070
发表时间: 2019-06-01
影响因子: 3.5
作者:
Fan, G.;Liu, H.;He, S.
通讯作者: He, S.
DOI: 10.1109/tmi.2018.2857800
发表时间: 2019-01
影响因子: 10.6
作者:
Jiang J;Hu YC;Liu CJ;Halpenny D;Hellmann MD;Deasy JO;Mageras G;Veeraraghavan H
通讯作者: Veeraraghavan H