用于大轴向视野PET参数图像重建的深度神经网络
本研究在大轴向视野PET/CT(Biograph Vision Quadra)上纳入20例患者行18F-FDG动态扫描,基于DeepPET深度学习框架从五帧正弦图无输入函数重建直接Patlak Ki图像。测试阶段MSE小于0.03%、PSNR约38 dB、SSIM约0.98,预测Ki与厂商嵌套EM算法重建的Patlak Ki在11个病灶上相关性高。
要点
- 大轴向视野PET约20倍于常规扫描仪的灵敏度为参数成像提供新机会,但动态数据量和复杂性显著增加。
- 深度学习框架以最后五帧正弦图(注射后25分钟,即40-65分钟)为输入、厂商嵌套EM算法Patlak Ki为金标准进行训练与测试。
- 测试阶段MSE小于0.03%、PSNR约38 dB、SSIM约0.98,预测与真实Ki均值在11个病灶上相关性高。
核心结论
- 基于深度学习的方法可从少量投影数据帧、无需输入函数生成高质量参数图像,对解决动态PET长扫描时间与依赖输入函数的困境有很大潜力。
研究设计与样本
- 研究在大轴向视野PET/CT扫描仪(Biograph Vision Quadra)上实施,纳入20例患者行18F-氟脱氧葡萄糖(18F-FDG)动态扫描。
- 训练与测试中,以最后五帧(25分钟,即注射后40-65分钟)正弦图为输入,以厂商嵌套EM算法重建的Patlak Ki图像为金标准。
- 采用均方误差(MSE)、峰值信噪比(PSNR)和结构相似性指数(SSIM)评价预测Ki图像质量,并对高摄取恶性病灶与肿瘤感兴趣体积(VOIs)的预测与真实Ki均值做线性回归。
主要发现
- 测试阶段该方法MSE小于0.03%,SSIM和PSNR分别约为0.98和约38 dB。
- 在11个病灶上,预测Ki与传统重建Patlak Ki均值之间相关性高:DeepPET的[公式见原文]为0.73,自注意力DeepPET的[公式见原文]为0.82。
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: The PET scanners with long axial field of view (AFOV) having ~ 20 times higher sensitivity than conventional scanners provide new opportunities for enhanced parametric imaging but suffer from the dramatically increased volume and complexity of dynamic data. This study reconstructed a high-quality direct Patlak Ki image from five-frame sinograms without input function by a deep learning framework based on DeepPET to explore the potential of artificial intelligence reducing the acquisition time and the dependence of input function in parametric imaging. METHODS: This study was implemented on a large AFOV PET/CT scanner (Biograph Vision Quadra) and twenty patients were recruited with 18F-fluorodeoxyglucose (18F-FDG) dynamic scans. During training and testing of the proposed deep learning framework, the last five-frame (25 min, 40-65 min post-injection) sinograms were set as input and the reconstructed Patlak Ki images by a nested EM algorithm on the vendor were set as ground truth. To evaluate the image quality of predicted Ki images, mean square error (MSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) were calculated. Meanwhile, a linear regression process was applied between predicted and true Ki means on avid malignant lesions and tumor volume of interests (VOIs). RESULTS: In the testing phase, the proposed method achieved excellent MSE of less than 0.03%, high SSIM, and PSNR of ~ 0.98 and ~ 38 dB, respectively. Moreover, there was a high correlation (DeepPET: [Formula: see text]= 0.73, self-attention DeepPET: [Formula: see text]=0.82) between predicted Ki and traditionally reconstructed Patlak Ki means over eleven lesions. CONCLUSIONS: The results show that the deep learning-based method produced high-quality parametric images from small frames of projection data without input function. It has much potential to address the dilemma of the long scan time and dependency on input function that still hamper the clinical translation of dynamic PET.
引用
- Li Y, Hu J, Sari H, et al. A deep neural network for parametric image reconstruction on a large axial field-of-view PET. Eur J Nucl Med Mol Imaging. 2022. PMID: 36326869. doi:10.1007/s00259-022-06003-4
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。