Nuclear Medicine Unit, Fondazione Istituto G. Giglio, Contrada Pietrapollastra Pisciotto, 90015, Cefalù, PA, Italy.
Institute of Molecular Bioimaging and Physiology, National Research Council (CNR), Cefalù, PA, Italy.
Eur Radiol. 2021 Jul;31(7):4595-4605. doi: 10.1007/s00330-020-07617-8. Epub 2021 Jan 14.
The aim of this study was (1) to investigate the application of texture analysis of choline PET/CT images in prostate cancer (PCa) patients and (2) to propose a machine-learning radiomics model able to select PET features predictive of disease progression in PCa patients with a same high-risk class at restaging.
Ninety-four high-risk PCa patients who underwent restaging Cho-PET/CT were analyzed. Follow-up data were recorded for a minimum of 13 months after the PET/CT scan. PET images were imported in LIFEx toolbox to extract 51 features from each lesion. A statistical system based on correlation matrix and point-biserial-correlation coefficient has been implemented for features reduction and selection, while Discriminant analysis (DA) was used as a method for features classification in a whole sample and sub-groups for primary tumor or local relapse (T), nodal disease (N), and metastatic disease (M).
In the whole group, 2 feature (HISTO_Entropy_log10; HISTO_Energy_Uniformity) results were able to discriminate the occurrence of disease progression at follow-up, obtaining the best performance in DA classification (sensitivity 47.1%, specificity 76.5%, positive predictive value (PPV) 46.7%, and accuracy 67.6%). In the sub-group analysis, the best performance in DA classification for T was obtained by selecting 3 features (SUVmin; SHAPE_Sphericity; GLCM_Correlation) with a sensitivity of 91.6%, specificity 84.1%, PPV 79.1%, and accuracy 87%; for N by selecting 2 features (HISTO = _Energy Uniformity; GLZLM_SZLGE) with a sensitivity of 68.1%, specificity 91.4%, PPV 83%, and accuracy 82.6%; and for M by selecting 2 features (HISTO_Entropy_log10 - HISTO_Entropy_log2) with a sensitivity 64.4%, specificity 74.6%, PPV 40.6%, and accuracy 72.5%.
This machine learning model demonstrated to be feasible and useful to select Cho-PET features for T, N, and M with valuable association with high-risk PCa patients' outcomes.
• Artificial intelligence applications are feasible and useful to select Cho-PET features. • Our model demonstrated the presence of specific features for T, N, and M with valuable association with high-risk PCa patients' outcomes. • Further prospective studies are necessary to confirm our results and to develop the application of artificial intelligence in PET imaging of PCa.
本研究旨在：(1) 探讨胆碱 PET/CT 图像纹理分析在前列腺癌 (PCa) 患者中的应用；(2) 提出一种机器学习放射组学模型，能够选择 PET 特征，预测在 restaging 时处于同一高危类别的 PCa 患者的疾病进展。
分析了 94 例接受 Cho-PET/CT 复查的高危 PCa 患者。在 PET/CT 扫描后至少随访 13 个月记录随访数据。将 PET 图像导入 LIFEx 工具包，从每个病变中提取 51 个特征。基于相关矩阵和点二项式相关系数的统计系统已用于特征减少和选择，而判别分析 (DA) 则用于对整个样本和亚组的特征进行分类，包括原发性肿瘤或局部复发 (T)、淋巴结疾病 (N) 和转移性疾病 (M)。
在整个组中，有 2 个特征（HISTO_Entropy_log10；HISTO_Energy_Uniformity）能够区分随访时的疾病进展，在 DA 分类中表现最佳（敏感性 47.1%，特异性 76.5%，阳性预测值 (PPV) 46.7%，准确性 67.6%）。在亚组分析中，在 DA 分类中对 T 的最佳性能是通过选择 3 个特征（SUVmin；SHAPE_Sphericity；GLCM_Correlation）获得的，敏感性为 91.6%，特异性为 84.1%，PPV 为 79.1%，准确性为 87%；对于 N，通过选择 2 个特征（HISTO = _Energy Uniformity；GLZLM_SZLGE）获得，敏感性为 68.1%，特异性为 91.4%，PPV 为 83%，准确性为 82.6%；对于 M，通过选择 2 个特征（HISTO_Entropy_log10 - HISTO_Entropy_log2）获得，敏感性为 64.4%，特异性为 74.6%，PPV 为 40.6%，准确性为 72.5%。
该机器学习模型被证明是可行且有用的，可用于选择 T、N 和 M 的 Cho-PET 特征，并与高危 PCa 患者的结局具有有价值的关联。
• 人工智能应用是可行且有用的，可以选择 Cho-PET 特征。• 我们的模型证明了 T、N 和 M 存在特定特征，与高危 PCa 患者的结局具有有价值的关联。• 有必要进行进一步的前瞻性研究来验证我们的结果，并开发人工智能在 PCa 中 PET 成像中的应用。
