当前位置: X-MOL 学术Eur. J. Nucl. Med. Mol. Imaging › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An encoder-decoder network for direct image reconstruction on sinograms of a long axial field of view PET
European Journal of Nuclear Medicine and Molecular Imaging ( IF 9.1 ) Pub Date : 2022-07-11 , DOI: 10.1007/s00259-022-05861-2
Ruiyao Ma 1, 2, 3 , Jiaxi Hu 2 , Hasan Sari 2, 4 , Song Xue 2 , Clemens Mingels 2 , Marco Viscione 2 , Venkata Sai Sundar Kandarpa 5 , Wei Bo Li 3 , Dimitris Visvikis 5 , Rui Qiu 1 , Axel Rominger 2 , Junli Li 1 , Kuangyu Shi 2
Affiliation  

Purpose

Deep learning is an emerging reconstruction method for positron emission tomography (PET), which can tackle complex PET corrections in an integrated procedure. This paper optimizes the direct PET reconstruction from sinogram on a long axial field of view (LAFOV) PET.

Methods

This paper proposes a novel deep learning architecture to reduce the biases during direct reconstruction from sinograms to images. This architecture is based on an encoder-decoder network, where the perceptual loss is used with pre-trained convolutional layers. It is trained and tested on data of 80 patients acquired from recent Siemens Biograph Vision Quadra long axial FOV (LAFOV) PET/CT. The patients are randomly split into a training dataset of 60 patients, a validation dataset of 10 patients, and a test dataset of 10 patients. The 3D sinograms are converted into 2D sinogram slices and used as input to the network. In addition, the vendor reconstructed images are considered as ground truths. Finally, the proposed method is compared with DeepPET, a benchmark deep learning method for PET reconstruction.

Results

Compared with DeepPET, the proposed network significantly reduces the root-mean-squared error (NRMSE) from 0.63 to 0.6 (p < 0.01) and increases the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) from 0.93 to 0.95 (p < 0.01) and from 82.02 to 82.36 (p < 0.01), respectively. The reconstruction time is approximately 10 s per patient, which is shortened by 23 times compared with the conventional method. The errors of mean standardized uptake values (SUVmean) for lesions between ground truth and the predicted result are reduced from 33.5 to 18.7% (p = 0.03). In addition, the error of max SUV is reduced from 32.7 to 21.8% (p = 0.02).

Conclusion

The results demonstrate the feasibility of using deep learning to reconstruct images with acceptable image quality and short reconstruction time. It is shown that the proposed method can improve the quality of deep learning-based reconstructed images without additional CT images for attenuation and scattering corrections. This study demonstrated the feasibility of deep learning to rapidly reconstruct images without additional CT images for complex corrections from actual clinical measurements on LAFOV PET. Despite improving the current development, AI-based reconstruction does not work appropriately for untrained scenarios due to limited extrapolation capability and cannot completely replace conventional reconstruction currently.



中文翻译:

一种编码器-解码器网络,用于在长轴视场 PET 的正弦图上进行直接图像重建

目的

深度学习是一种新兴的正电子发射断层扫描 (PET) 重建方法,可以在集成过程中处理复杂的 PET 校正。本文优化了长轴视场 (LAFOV) PET 正弦图的直接 PET 重建。

方法

本文提出了一种新颖的深度学习架构,以减少从正弦图到图像的直接重建过程中的偏差。该架构基于编码器-解码器网络,其中感知损失与预训练的卷积层一起使用。它是根据从最近的 Siemens Biograph Vision Quadra 长轴 FOV (LAFOV) PET/CT 获得的 80 名患者的数据进行训练和测试的。患者被随机分为 60 名患者的训练数据集、10 名患者的验证数据集和 10 名患者的测试数据集。3D 正弦图被转换为 2D 正弦图切片并用作网络的输入。此外,供应商重建的图像被视为基本事实。最后,将所提出的方法与用于 PET 重建的基准深度学习方法 DeepPET 进行了比较。

结果

与 DeepPET 相比,所提出的网络将均方根误差 (NRMSE) 从 0.63 显着降低到 0.6 ( p  < 0.01),并将结构相似性指数 (SSIM) 和峰值信噪比 (PSNR) 从 0.93 提高到 0.95 ( p  < 0.01) 和从 82.02 到 82.36 ( p  < 0.01),分别。每位患者的重建时间约为10秒,与传统方法相比缩短了23倍。真值和预测结果之间病变的平均标准化摄取值 (SUVmean) 的误差从 33.5% 减少到 18.7% ( p  = 0.03)。此外,最大 SUV 的误差从 32.7% 减少到 21.8% ( p  = 0.02)。

结论

结果证明了使用深度学习以可接受的图像质量和较短的重建时间重建图像的可行性。结果表明,所提出的方法可以提高基于深度学习的重建图像的质量,而无需额外的 CT 图像进行衰减和散射校正。这项研究证明了深度学习快速重建图像的可行性,而无需额外的 CT 图像以对 LAFOV PET 上的实际临床测量进行复杂校正。尽管目前的发展有所改善,但由于外推能力有限,基于人工智能的重建不适用于未经训练的场景,目前还不能完全取代传统的重建。

更新日期:2022-07-12
down
wechat
bug