基于深度学习在uEXPLORER全身PET/CT系统上生成参数成像
本研究纳入200例患者,在2米全身PET/CT(uEXPLORER)上获取60分钟动态参数PET图像与50-60分钟静态PET图像配对,用深度学习模型从静态图像直接预测参数图像,无需图像衍生输入函数。合成参数图像与参考图像定性和定量一致,全局平均SSIM超过0.9,两名核医学医师主观质量评分为4.00±0.45(满分5)。
要点
- 深度学习模型可从10分钟静态PET图像直接生成参数图像,无需图像衍生输入函数。
- 合成参数图像与参考参数图像全局平均SSIM超过0.9,主观质量评分4.00±0.45(满分5)。
- 该技术有望缩短2米全身动态PET/CT所需扫描时间,临床应用验证和网络可解释性仍需进一步研究。
核心结论
- 研究结果表明所提技术可行,并有望缩短2米全身动态PET/CT系统所需的扫描时间;深度学习技术可输出高质量合成参数图像,但临床应用验证和网络模型可解释性仍需在未来工作中进一步研究。
研究设计与样本
- 采用深度学习模型从静态PET图像预测参数图像,并以10折交叉验证评估,计算峰值信噪比(PSNR)、结构相似性指数(SSIM)和归一化均方误差(NMSE)等指标。
- 图像质量由两名核医学医师从临床阅片角度评估。
主要发现
- 合成参数PET图像与参考图像在定性和定量上一致。
- 所有测试患者的合成与参考参数图像之间全局平均SSIM超过0.9。
- 两名专家核医学医师对合成参数PET图像的整体主观质量评分为4.00±0.45(最高可能评分为5)。
局限性
- 原文指出深度学习技术的临床应用验证和网络模型可解释性仍需在未来工作中进一步研究。
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: Total-body dynamic positron emission tomography/computed tomography (PET/CT) provides much sensitivity for clinical imaging and research, bringing new opportunities and challenges regarding the generation of total-body parametric images. This study investigated parametric [Formula: see text] images directly generated from static PET images without an image-derived input function on a 2-m total-body PET/CT scanner (uEXPLORER) using a deep learning model to significantly reduce the dynamic scanning time and improve patient comfort. METHODS: [Formula: see text]F-Fluorodeoxyglucose ([Formula: see text]F-FDG) 2-m total-body PET/CT image pairs were acquired for 200 patients (scanned once) with two protocols: one parametric PET image (60 min, 0[Formula: see text]60 min) and one static PET image (10 min, range of 50[Formula: see text]60 min). A deep learning model was implemented to predict parametric [Formula: see text] images from the static PET images. Evaluation metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and normalized mean square error (NMSE), were calculated for a 10-fold cross-validation assessment. Moreover, image quality was assessed by two nuclear medicine physicians in terms of clinical readings. RESULTS: The synthetic parametric PET images were qualitatively and quantitatively consistent with the reference images. In particular, the global mean SSIM between the synthetic and reference parametric [Formula: see text] images exceeded 0.9 across all test patients. On the other hand, the overall subjective quality of the synthetic parametric PET images was 4.00 ± 0.45 (the highest possible rating is 5) according to the two expert nuclear medicine physicians. CONCLUSION: The findings illustrated the feasibility of the proposed technique and its potential to reduce the required scanning duration for 2-m total-body dynamic PET/CT systems. Moreover, this study explored the potential of direct parametric image generation with uEXPLORER. Deep learning technologies may output high-quality synthetic parametric images, and the validation of clinical applications and the interpretability of network models still need further research in future works.
引用
- Huang Z, Wu Y, Fu F, et al. Parametric image generation with the uEXPLORER total-body PET/CT system through deep learning. Eur J Nucl Med Mol Imaging. 2022. PMID: 35312030. doi:10.1007/s00259-022-05731-x
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。