Silosky Michael, Xing Fuyong, Wehrend John, Litwiller Daniel V, Metzler Scott D, Chin Bennett B
Department of Radiology, University of Colorado School of Medicine, Anschutz Medical Campus Aurora, CO, USA.
Department of Biostatistics and Informatics, University of Colorado School of Medicine, Anschutz Medical Campus Aurora, CO, USA.
Am J Nucl Med Mol Imaging. 2023 Feb 15;13(1):33-42. eCollection 2023.
Deep learning (DL) algorithms have shown promise in identifying and quantifying lesions in PET/CT. However, the accuracy and generalizability of these algorithms relies on large, diverse datasets which are time and labor intensive to curate. Modern PET/CT scanners may acquire data in list mode, allowing for multiple reconstructions of the same datasets with different parameters and imaging times. These reconstructions may provide a wide range of image characteristics to increase the size and diversity of datasets. Training algorithms with shorter imaging times and higher noise properties requires that lesions remain detectable. The purpose of this study is to model and predict the contrast-to-noise ratio (CNR) for shorter imaging times based on CNR from longer duration, lower noise images for Ga DOTATATE PET hepatic lesions and identify a threshold above which lesions remain detectable.
Ga DOTATATE subjects (n=20) with hepatic lesions were divided into two subgroups. The "Model" group (n=4 subjects; n=9 lesions; n=36 datapoints) was used to identify the relationship between CNR and imaging time. The "Test" group (n=16 subjects; n=44 lesions; n=176 datapoints) was used to evaluate the prediction provided by the model.
CNR plotted as a function of imaging time for a subset of identified subjects was very well fit with a quadratic model. For the remaining subjects, the measured CNR showed a very high linear correlation with the predicted CNR for these lesions (R > 0.97) for all imaging durations. From the model, a threshold CNR=6.9 at 5-minutes predicted CNR > 5 at 2-minutes. Visual inspection of lesions in 2-minute images with CNR above the threshold in 5-minute images were assessed and rated as a 4 or 5 (probably positive or definitely positive) confirming 100% lesion detectability on the shorter 2-minute PET images.
CNR for shorter DOTATATE PET imaging times may be accurately predicted using list mode reconstructions of longer acquisitions. A threshold CNR may be applied to longer duration images to ensure lesion detectability of shorter duration reconstructions. This method can aid in the selection of lesions to include in novel data augmentation techniques for deep learning.
深度学习（DL）算法在正电子发射断层扫描/计算机断层扫描（PET/CT）中识别和量化病变方面显示出前景。然而，这些算法的准确性和通用性依赖于大量多样的数据集，而精心整理这些数据集既耗时又费力。现代PET/CT扫描仪可以以列表模式采集数据，从而允许对同一数据集使用不同参数和成像时间进行多次重建。这些重建可能会提供广泛的图像特征，以增加数据集的规模和多样性。使用更短成像时间和更高噪声特性训练算法要求病变仍然可检测。本研究的目的是基于更长持续时间、更低噪声的镓 DOTATATE PET肝脏病变图像的对比噪声比（CNR），对更短成像时间的CNR进行建模和预测，并确定一个阈值，高于该阈值病变仍然可检测。
患有肝脏病变的镓 DOTATATE受试者（n = 20）被分为两个亚组。“模型”组（n = 4名受试者；n = 9个病变；n = 36个数据点）用于确定CNR与成像时间之间的关系。“测试”组（n = 16名受试者；n = 44个病变；n = 176个数据点）用于评估模型提供的预测。
对于一部分已识别受试者，将CNR绘制为成像时间的函数，与二次模型拟合得非常好。对于其余受试者，在所有成像持续时间内，测量的CNR与这些病变的预测CNR显示出非常高的线性相关性（R > 0.97）。根据该模型，5分钟时预测CNR > 5时的阈值CNR = 6.9，对应2分钟时的情况。对5分钟图像中CNR高于阈值的2分钟图像中的病变进行视觉检查，并评为4或5级（可能为阳性或肯定为阳性），证实较短的2分钟PET图像上病变可检测率为100%。
使用更长采集时间的列表模式重建可以准确预测更短的镓 DOTATATE PET成像时间的CNR。可以将阈值CNR应用于更长持续时间的图像，以确保更短持续时间重建中病变的可检测性。该方法有助于选择病变纳入深度学习的新型数据增强技术中。
