Visualization of Optic Nerve Structural Patterns in Papilledema Using Deep Learning Variational Autoencoders.

Visualization of Optic Nerve Structural Patterns in Papilledema Using Deep Learning Variational Autoencoders.
复制标题

DOI:
10.1167/tvst.13.1.13
复制
发表时间:
2024-01-02
影响因子:
3
通讯作者:
Kardon, Randy H.
Kardon, Randy H.
中科院分区:
医学3区
文献类型:
--
作者:
Wang, Jui-Kai (Ray);Linton, Edward F.;Johnson, Brett A.;Kupersmith, Mark J.;Garvin, Mona K.;Kardon, Randy H.

文献摘要

参考文献

相似文献

可视化和量化治疗期间视乳头水肿中遇到的视神经水肿的结构模式。使用来自特发性颅内高压治疗试验 (IIHTT) 的 125 名受试者随时间的 1498 次光学相干断层扫描 (OCT) 扫描和来自爱荷华大学的 96 名对照受试者的 791 次 OCT 扫描来训练一种新型双通道深度学习变分自动编码器 (biVAE) 模型。使用来自 70 名视乳头水肿受试者的 70 只眼睛的独立测试数据集来评估 biVAE 模型仅使用两个变量根据输入 OCT 扫描量化和重建视乳头水肿空间模式的能力。 biVAE 模型生成的视网膜神经纤维层 (RNFL) 和视网膜总厚度 (TRT) 的蒙太奇彩色图提供了视盘水肿的各种形态模式(包括相似厚度水平的不同模式)的有组织的可视化。乙酰唑胺与安慰剂相比在 IIHTT 中的治疗效果也在潜伏空间中得到了证实。在图像重建中,平均符号视盘周围视网膜神经纤维层厚度(pRNFLT)差异±SD为-0.12±17.34μm,绝对pRNFLT差异为13.68±10.65μm,RNFL结构相似性指数达到0.91±0.05。视乳头水肿的多种结构模式,将视盘水肿的程度与下面的视盘和视网膜形态相结合,只需两个潜在变量即可量化。 biVAE 模型对结构模式以及通道之间的相关性进行编码,可用于在整个治疗过程中可视化患有视乳头水肿的个体或群体。
To visualize and quantify structural patterns of optic nerve edema encountered in papilledema during treatment. A novel bi-channel deep-learning variational autoencoder (biVAE) model was trained using 1498 optical coherence tomography (OCT) scans of 125 subjects over time from the Idiopathic Intracranial Hypertension Treatment Trial (IIHTT) and 791 OCT scans of 96 control subjects from the University of Iowa. An independent test dataset of 70 eyes from 70 papilledema subjects was used to evaluate the ability of the biVAE model to quantify and reconstruct the papilledema spatial patterns from input OCT scans using only two variables. The montage color maps of the retinal nerve fiber layer (RNFL) and total retinal thickness (TRT) produced by the biVAE model provided an organized visualization of the variety of morphological patterns of optic disc edema (including differing patterns at similar thickness levels). Treatment effects of acetazolamide versus placebo in the IIHTT were also demonstrated in the latent space. In image reconstruction, the mean signed peripapillary retinal nerve fiber layer thickness (pRNFLT) difference ± SD was −0.12 ± 17.34 µm, the absolute pRNFLT difference was 13.68 ± 10.65 µm, and the RNFL structural similarity index reached 0.91 ± 0.05. A wide array of structural patterns of papilledema, integrating the magnitude of disc edema with underlying disc and retinal morphology, can be quantified by just two latent variables. A biVAE model encodes structural patterns, as well as the correlation between channels, and may be applied to visualize individuals or populations with papilledema throughout treatment.
DOI: 10.1167/iovs.14-14960
发表时间: 2014-12-01
影响因子: 4.4
作者:
Auinger, Peggy;Durbin, Mary;Werner, John S.
通讯作者: Werner, John S.
DOI: 10.1109/tpami.2006.19
发表时间: 2006-01-01
影响因子: 23.6
作者:
Li, K;Wu, XD;Sonka, M
通讯作者: Sonka, M
DOI: 10.1038/s41598-019-54653-6
发表时间: 2019-12-02
期刊: SCIENTIFIC REPORTS
影响因子: 4.6
作者:
Berchuck, Samuel I.;Mukherjee, Sayan;Medeiros, Felipe A.
通讯作者: Medeiros, Felipe A.
DOI: 10.1002/jemt.23865
发表时间: 2021-07-08
影响因子: 2.5
作者:
Saba, Tanzila;Akbar, Shahzad;Ali Bahaj, Saeed
通讯作者: Ali Bahaj, Saeed
DOI: 10.1097/wno.0000000000000162
发表时间: 2014-09-01
影响因子: 2.9
作者:
Kardon, Randy
通讯作者: Kardon, Randy