A deep learning approach for (18)F-FDG PET attenuation correction.

A deep learning approach for (18)F-FDG PET attenuation correction.
复制标题

DOI:
10.1186/s40658-018-0225-8
复制
发表时间:
2018-11-12
期刊:
影响因子:
4
通讯作者:
McMillan AB
McMillan AB
中科院分区:
医学2区
文献类型:
--
作者:
Liu F;Jang H;Kijowski R;Zhao G;Bradshaw T;McMillan AB

文献摘要

参考文献

被引文献

相似文献

开发和评估数据驱动的深度学习方法 (deepAC) 的可行性,用于无需解剖成像的正电子发射断层扫描 (PET) 图像衰减校正。利用深度学习开发了 PET 衰减校正流程,从未校正的 18F-氟脱氧葡萄糖 (18F-FDG) PET 图像生成连续有价值的伪计算机断层扫描 (CT) 图像。训练深度卷积编码器-解码器网络来识别与 CT 数据共同配准的体积未校正 PET 图像中的组织对比度。使用一组 100 张回顾性 3D FDG PET 头部图像来训练模型。通过使用 Dice 系数和平均绝对误差 (MAE) 将生成的伪 CT 与采集的 CT 进行比较,最后通过比较使用伪 CT 和采集的 CT 重建的 PET 图像进行衰减校正,在另外 28 名患者中对该模型进行了评估。使用配对样本 t 检验进行统计分析,以比较使用 deepAC 与基于 CT 的衰减校正的 PET 重建误差。相对于 PET/CT 数据集,deepAC 生成的伪 CT 的空气 Dice 系数为 0.80±0.02,软组织为 0.94±0.01,骨骼为 0.75±0.03,MAE 为 111±16 HU。 deepAC 提供定量准确的 18F-FDG PET 结果,大多数大脑区域的平均误差小于 1%。我们开发了一种自动化方法 (deepAC),可以从单个 18F-FDG 非衰减校正 (NAC) PET 图像生成连续值的伪 CT,并在 PET/CT 脑成像中对其进行评估。
To develop and evaluate the feasibility of a data-driven deep learning approach (deepAC) for positron-emission tomography (PET) image attenuation correction without anatomical imaging. A PET attenuation correction pipeline was developed utilizing deep learning to generate continuously valued pseudo-computed tomography (CT) images from uncorrected 18F-fluorodeoxyglucose (18F-FDG) PET images. A deep convolutional encoder-decoder network was trained to identify tissue contrast in volumetric uncorrected PET images co-registered to CT data. A set of 100 retrospective 3D FDG PET head images was used to train the model. The model was evaluated in another 28 patients by comparing the generated pseudo-CT to the acquired CT using Dice coefficient and mean absolute error (MAE) and finally by comparing reconstructed PET images using the pseudo-CT and acquired CT for attenuation correction. Paired-sample t tests were used for statistical analysis to compare PET reconstruction error using deepAC with CT-based attenuation correction. deepAC produced pseudo-CTs with Dice coefficients of 0.80 ± 0.02 for air, 0.94 ± 0.01 for soft tissue, and 0.75 ± 0.03 for bone and MAE of 111 ± 16 HU relative to the PET/CT dataset. deepAC provides quantitatively accurate 18F-FDG PET results with average errors of less than 1% in most brain regions. We have developed an automated approach (deepAC) that allows generation of a continuously valued pseudo-CT from a single 18F-FDG non-attenuation-corrected (NAC) PET image and evaluated it in PET/CT brain imaging.
DOI: 10.1002/mrm.26953
发表时间: 2018-06
影响因子: 3.3
作者:
Jang H;Liu F;Bradshaw T;McMillan AB
通讯作者: McMillan AB
DOI: 10.1109/tns.1979.4330535
发表时间: 1979-01-01
影响因子: 1.8
作者:
CENSOR, Y;GUSTAFSON, DE;TUY, H
通讯作者: TUY, H
DOI: 10.1118/1.4941014
发表时间: 2016-03-01
期刊: MEDICAL PHYSICS
影响因子: 3.8
作者:
Mehranian, Abolfazl;Arabi, Hossein;Zaidi, Habib
通讯作者: Zaidi, Habib
DOI: 10.1148/radiol.2017170700
发表时间: 2018-02-01
期刊: RADIOLOGY
影响因子: 19.7
作者:
Liu, Fang;Jang, Hyungseok;McMillan, Alan B.
通讯作者: McMillan, Alan B.
DOI: 10.1007/s00259-002-0796-3
发表时间: 2002-07-01
影响因子: 9.1
作者:
Burger, C;Goerres, G;von Schulthess, GK
通讯作者: von Schulthess, GK