用于长轴视野PET正弦图直接图像重建的编码器-解码器网络
本研究提出一种基于编码器-解码器网络的新型深度学习架构,结合感知损失与预训练卷积层,用于长轴视野(LAFOV)PET正弦图的直接图像重建,以减少重建偏差。在80例西门子Biograph Vision Quadra LAFOV PET/CT患者数据上训练与测试,其中训练集60例、验证集10例、测试集10例,以厂商重建图像为金标准,并与DeepPET基准方法比较。结果显示,所提网络较DeepPET显著降低NRMSE(从0.63降至0.6,p<0.01),提高SSIM(从0.93升至0.95,p<0.01)和PSNR(从82.02升至82.36,p<0.01),每例重建时间约10秒,较传统方法缩短23倍;病灶SUVmean误差从33.5%降至18.7%(p=0.03),SUVmax误差从32.7%降至21.8%(p=0.02)。结论表明深度学习在LAFOV PET上无需额外CT图像进行衰减和散射校正即可快速重建出可接受质量的图像,但AI重建因外推能力有限,对未训练场景效果不佳,目前尚不能完全替代传统重建。
要点
- 所提编码器-解码器网络在LAFOV PET正弦图直接重建中,较DeepPET显著降低NRMSE(0.63 vs 0.6,p<0.01)。
- 所提网络较DeepPET显著提高SSIM(0.93 vs 0.95,p<0.01)和PSNR(82.02 vs 82.36,p<0.01)。
- 病灶SUVmean误差从33.5%降至18.7%(p=0.03),SUVmax误差从32.7%降至21.8%(p=0.02),重建时间约10秒/例,较传统方法缩短23倍。
核心结论
- 深度学习用于LAFOV PET图像重建具有可行性,可获得可接受的图像质量和较短的重建时间。
- 所提方法无需额外CT图像进行衰减和散射校正即可提高深度学习重建图像质量。
- AI重建因外推能力有限,对未训练场景效果不佳,目前尚不能完全替代传统重建。
研究设计与样本
- 本研究为方法学研究,提出基于编码器-解码器网络的新型深度学习架构,采用感知损失与预训练卷积层。
- 数据来自80例在西门子Biograph Vision Quadra LAFOV PET/CT上采集的患者,随机分为训练集60例、验证集10例和测试集10例。
- 将3D正弦图转换为2D正弦图切片作为网络输入,以厂商重建图像为金标准,并与DeepPET基准深度学习方法比较。
主要发现
- 所提网络较DeepPET显著降低NRMSE(从0.63降至0.6,p<0.01)。
- 所提网络较DeepPET显著提高SSIM(从0.93升至0.95,p<0.01)和PSNR(从82.02升至82.36,p<0.01)。
- 每例重建时间约10秒,较传统方法缩短23倍。
- 病灶SUVmean误差从33.5%降至18.7%(p=0.03),SUVmax误差从32.7%降至21.8%(p=0.02)。
局限性
- AI重建因外推能力有限,对未训练场景效果不佳。
- AI重建目前尚不能完全替代传统重建。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
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.
引用
- Ma R, Hu J, Sari H, et al. An encoder-decoder network for direct image reconstruction on sinograms of a long axial field of view PET. Eur J Nucl Med Mol Imaging. 2022. PMID: 35819497. doi:10.1007/s00259-022-05861-2
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。