Department of Data Science and Machine Learning, EXINI Diagnostics AB, Lund, Sweden.
Radiation Oncology Service, VA Greater Los Angeles Healthcare System, Los Angeles, CA, USA.
Eur J Nucl Med Mol Imaging. 2022 Feb;49(3):1041-1051. doi: 10.1007/s00259-021-05497-8. Epub 2021 Aug 31.
The application of automated image analyses could improve and facilitate standardization and consistency of quantification in [F]DCFPyL (PSMA) PET/CT scans. In the current study, we analytically validated aPROMISE, a software as a medical device that segments organs in low-dose CT images with deep learning, and subsequently detects and quantifies potential pathological lesions in PSMA PET/CT.
To evaluate the deep learning algorithm, the automated segmentations of the low-dose CT component of PSMA PET/CT scans from 20 patients were compared to manual segmentations. Dice scores were used to quantify the similarities between the automated and manual segmentations. Next, the automated quantification of tracer uptake in the reference organs and detection and pre-segmentation of potential lesions were evaluated in 339 patients with prostate cancer, who were all enrolled in the phase II/III OSPREY study. Three nuclear medicine physicians performed the retrospective independent reads of OSPREY images with aPROMISE. Quantitative consistency was assessed by the pairwise Pearson correlations and standard deviation between the readers and aPROMISE. The sensitivity of detection and pre-segmentation of potential lesions was evaluated by determining the percent of manually selected abnormal lesions that were automatically detected by aPROMISE.
The Dice scores for bone segmentations ranged from 0.88 to 0.95. The Dice scores of the PSMA PET/CT reference organs, thoracic aorta and liver, were 0.89 and 0.97, respectively. Dice scores of other visceral organs, including prostate, were observed to be above 0.79. The Pearson correlation for blood pool reference was higher between any manual reader and aPROMISE, than between any pair of manual readers. The standard deviations of reference organ uptake across all patients as determined by aPROMISE (SD = 0.21 blood pool and SD = 1.16 liver) were lower compared to those of the manual readers. Finally, the sensitivity of aPROMISE detection and pre-segmentation was 91.5% for regional lymph nodes, 90.6% for all lymph nodes, and 86.7% for bone in metastatic patients.
In this analytical study, we demonstrated the segmentation accuracy of the deep learning algorithm, the consistency in quantitative assessment across multiple readers, and the high sensitivity in detecting potential lesions. The study provides a foundational framework for clinical evaluation of aPROMISE in standardized reporting of PSMA PET/CT.
自动化图像分析的应用可以提高和促进 [F]DCFPyL（PSMA）PET/CT 扫描中定量的标准化和一致性。在本研究中，我们对 aPROMISE 进行了分析验证，aPROMISE 是一种软件即医疗器械，它使用深度学习对低剂量 CT 图像进行器官分割，然后检测和量化 PSMA PET/CT 中的潜在病理病变。
为了评估深度学习算法，将 20 名患者的 PSMA PET/CT 扫描的低剂量 CT 成分的自动分割与手动分割进行了比较。使用 Dice 分数来量化自动分割和手动分割之间的相似性。接下来，在 339 名前列腺癌患者中评估了参考器官示踪剂摄取的自动定量和潜在病变的检测和预分割，这些患者均纳入了 OSPREY 研究的 II/III 期。三位核医学医师使用 aPROMISE 对 OSPREY 图像进行了回顾性独立阅读。通过读者和 aPROMISE 之间的成对 Pearson 相关系数和标准差评估定量一致性。通过确定手动选择的异常病变中由 aPROMISE 自动检测到的百分比来评估潜在病变检测和预分割的灵敏度。
骨分割的 Dice 分数范围为 0.88 至 0.95。PSMA PET/CT 参考器官，胸主动脉和肝脏的 Dice 分数分别为 0.89 和 0.97。其他内脏器官（包括前列腺）的 Dice 分数均高于 0.79。任何手动读者与 aPROMISE 之间的血池参考 Pearson 相关系数均高于任何一对手动读者之间的相关系数。通过 aPROMISE 确定的所有患者的参考器官摄取的标准差（SD=0.21 血池和 SD=1.16 肝脏）均低于手动读者的标准差。最后，aPROMISE 检测和预分割的灵敏度在转移性患者中分别为区域淋巴结 91.5%、所有淋巴结 90.6%和骨骼 86.7%。
在这项分析研究中，我们展示了深度学习算法的分割准确性、多个读者之间定量评估的一致性以及检测潜在病变的高灵敏度。该研究为 aPROMISE 在 PSMA PET/CT 标准化报告中的临床评估提供了基础框架。
