Unsupervised MRI Homogenization: Application to Pediatric Anterior Visual Pathway Segmentation.

Unsupervised MRI Homogenization: Application to Pediatric Anterior Visual Pathway Segmentation.
复制标题

DOI:
10.1007/978-3-030-59861-7_19
复制
发表时间:
2020-10
期刊:
Machine learning in medical imaging. MLMI (Workshop)
影响因子:
--
通讯作者:
Linguraru MG
Linguraru MG
中科院分区:
其他
文献类型:
--
作者:
Tor-Diez C;Porras AR;Packer RJ;Avery RA;Linguraru MG

文献摘要

参考文献

相似文献

深度学习策略已经成为医学图像分析中无处不在的优化工具。在适当的数据量下,这些方法在各种图像处理任务中优于经典方法。然而,罕见病和儿科影像学往往缺乏广泛的数据。特别是,MRI是不常见的,因为它们需要在幼儿镇静。此外,MRI协议中缺乏标准化在不同数据集之间引入了很强的可变性。在本文中,我们提出了一种用于MRI均匀化的通用深度学习架构,该架构还提供了感兴趣解剖区域的分割图。均匀化是使用基于变分自动编码器的无监督架构与循环生成对抗网络实现的,该网络使用未配对的图像到图像转换网络学习公共空间(即最佳成像协议的表示)。分割是同时产生的监督学习策略。我们使用三个脑T1加权MRI数据集(可变协议和供应商)评估了我们的方法分割具有挑战性的前部视觉通路。我们的方法显著优于非同质化多协议U-Net。
Deep learning strategies have become ubiquitous optimization tools for medical image analysis. With the appropriate amount of data, these approaches outperform classic methodologies in a variety of image processing tasks. However, rare diseases and pediatric imaging often lack extensive data. Specially, MRI are uncommon because they require sedation in young children. Moreover, the lack of standardization in MRI protocols introduces a strong variability between different datasets. In this paper, we present a general deep learning architecture for MRI homogenization that also provides the segmentation map of an anatomical region of interest. Homogenization is achieved using an unsupervised architecture based on variational autoencoder with cycle generative adversarial networks, which learns a common space (i.e. a representation of the optimal imaging protocol) using an unpaired image-to-image translation network. The segmentation is simultaneously generated by a supervised learning strategy. We evaluated our method segmenting the challenging anterior visual pathway using three brain T1-weighted MRI datasets (variable protocols and vendors). Our method significantly outperformed a non-homogenized multi-protocol U-Net.
DOI: 10.1016/j.nicl.2014.08.008
发表时间: 2014
期刊: NeuroImage. Clinical
影响因子: --
作者:
Shinohara RT;Sweeney EM;Goldsmith J;Shiee N;Mateen FJ;Calabresi PA;Jarso S;Pham DL;Reich DS;Crainiceanu CM;Australian Imaging Biomarkers Lifestyle Flagship Study of Ageing;Alzheimer's Disease Neuroimaging Initiative
通讯作者: Alzheimer's Disease Neuroimaging Initiative
DOI: 10.1016/j.media.2011.05.001
发表时间: 2011-12
影响因子: 10.9
作者:
Noble, Jack H.;Dawant, Benoit M.
通讯作者: Dawant, Benoit M.
DOI: 10.1016/j.mri.2003.09.001
发表时间: 2004-01-01
影响因子: 2.5
作者:
Collewet, G;Strzelecki, M;Mariette, F
通讯作者: Mariette, F
DOI: 10.1016/j.zemedi.2018.11.004
发表时间: 2019-01-01
影响因子: 2
作者:
Jacobsen, Nina;Deistung, Andreas;Guellmar, Daniel
通讯作者: Guellmar, Daniel
DOI: 10.1109/tmi.2010.2046908
发表时间: 2010-06
影响因子: 10.6
作者:
Tustison NJ;Avants BB;Cook PA;Zheng Y;Egan A;Yushkevich PA;Gee JC
通讯作者: Gee JC