LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation.

LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation.
复制标题

LIFE:用于3D OCT-A血管分割的可推广的自学管道。

DOI:
10.1007/978-3-030-87193-2_49
复制
发表时间:
2021-09
期刊:
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
影响因子:
--
通讯作者:
Oguz I
Oguz I
中科院分区:
其他
文献类型:
--
作者:
Hu D;Cui C;Li H;Larson KE;Tao YK;Oguz I

文献摘要

参考文献

相似文献

光学相干层析成像(OCT)是一种广泛应用于眼科的非侵入性成像技术。它可以扩展到OCT血管成像(OCT-A),它以更好的对比度显示视网膜血管。最近的深度学习算法产生了有希望的血管分割结果;然而,由于缺乏人工标注的训练数据,3D视网膜血管分割仍然困难。我们提出了一种基于学习的方法,该方法只由一个自合成的模式监督,称为局部强度融合(LIF)。LIF是直接从输入OCT-A计算的毛细血管增强体积。然后,我们构造了局部强度融合编码器(LIFE)来将给定的OCT-A体积及其对应的LIF映射到共享的潜在空间。生命的潜在空间与输入数据具有相同的维度,它包含两种模式的共同特征。通过对这个潜在空间进行二值化,我们得到了一个体积血管分割。我们的方法在一个人的中心凹OCT-A和三个带有手动标记的斑马鱼OCT-A卷上进行了评估。它在人类数据上的Dice得分为0.7736,在斑马鱼数据上的Dice得分为0.8594±0.0275,与现有的无监督算法相比,这是一个巨大的改进。
Optical coherence tomography (OCT) is a non-invasive imaging technique widely used for ophthalmology. It can be extended to OCT angiography (OCT-A), which reveals the retinal vasculature with improved contrast. Recent deep learning algorithms produced promising vascular segmentation results; however, 3D retinal vessel segmentation remains difficult due to the lack of manually annotated training data. We propose a learning-based method that is only supervised by a self-synthesized modality named local intensity fusion (LIF). LIF is a capillary-enhanced volume computed directly from the input OCT-A. We then construct the local intensity fusion encoder (LIFE) to map a given OCT-A volume and its LIF counterpart to a shared latent space. The latent space of LIFE has the same dimensions as the input data and it contains features common to both modalities. By binarizing this latent space, we obtain a volumetric vessel segmentation. Our method is evaluated in a human fovea OCT-A and three zebrafish OCT-A volumes with manual labels. It yields a Dice score of 0.7736 on human data and 0.8594 ± 0.0275 on zebrafish data, a dramatic improvement over existing unsupervised algorithms.
DOI: 10.1117/1.jmi.6.1.014006
发表时间: 2019-01-01
影响因子: 2.4
作者:
Alom, Md Zahangir;Yakopcic, Chris;Asari, Vijayan K.
通讯作者: Asari, Vijayan K.
DOI: 10.1364/oe.20.004710
发表时间: 2012-02-13
期刊: Optics express
影响因子: 3.8
作者:
Jia Y;Tan O;Tokayer J;Potsaid B;Wang Y;Liu JJ;Kraus MF;Subhash H;Fujimoto JG;Hornegger J;Huang D
通讯作者: Huang D
DOI: 10.1002/jbio.201700268
发表时间: 2018-04
影响因子: 2.8
作者:
El-Haddad MT;Bozic I;Tao YK
通讯作者: Tao YK
DOI: 10.1038/s41598-019-51062-7
发表时间: 2019-10-08
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Devalla, Sripad Krishna;Subramanian, Giridhar;Girard, Michael J. A.
通讯作者: Girard, Michael J. A.
DOI: 10.1167/iovs.15-19043
发表时间: 2016-07-01
影响因子: 4.4
作者:
Gao SS;Jia Y;Zhang M;Su JP;Liu G;Hwang TS;Bailey ST;Huang D
通讯作者: Huang D