MedICAL Laboratory, Polytechnique Montréal, Montréal, H3T 1J4, Canada.
Imaging and Engineering Axis, Centre de recherche du Centre Hospitalier de l'Université de Montréal/Institut du cancer de Montréal, 900 rue Saint-Denis R10.430, Montréal, QC, H2X 0A9, Canada.
J Transl Med. 2023 Jul 27;21(1):507. doi: 10.1186/s12967-023-04175-7.
Finding a noninvasive radiomic surrogate of tumor immune features could help identify patients more likely to respond to novel immune checkpoint inhibitors. Particularly, CD73 is an ectonucleotidase that catalyzes the breakdown of extracellular AMP into immunosuppressive adenosine, which can be blocked by therapeutic antibodies. High CD73 expression in colorectal cancer liver metastasis (CRLM) resected with curative intent is associated with early recurrence and shorter patient survival. The aim of this study was hence to evaluate whether machine learning analysis of preoperative liver CT-scan could estimate high vs low CD73 expression in CRLM and whether such radiomic score would have a prognostic significance.
We trained an Attentive Interpretable Tabular Learning (TabNet) model to predict, from preoperative CT images, stratified expression levels of CD73 (CD73 vs. CD73) assessed by immunofluorescence (IF) on tissue microarrays. Radiomic features were extracted from 160 segmented CRLM of 122 patients with matched IF data, preprocessed and used to train the predictive model. We applied a five-fold cross-validation and validated the performance on a hold-out test set.
TabNet provided areas under the receiver operating characteristic curve of 0.95 (95% CI 0.87 to 1.0) and 0.79 (0.65 to 0.92) on the training and hold-out test sets respectively, and outperformed other machine learning models. The TabNet-derived score, termed rad-CD73, was positively correlated with CD73 histological expression in matched CRLM (Spearman's ρ = 0.6004; P < 0.0001). The median time to recurrence (TTR) and disease-specific survival (DSS) after CRLM resection in rad-CD73 vs rad-CD73 patients was 13.0 vs 23.6 months (P = 0.0098) and 53.4 vs 126.0 months (P = 0.0222), respectively. The prognostic value of rad-CD73 was independent of the standard clinical risk score, for both TTR (HR = 2.11, 95% CI 1.30 to 3.45, P < 0.005) and DSS (HR = 1.88, 95% CI 1.11 to 3.18, P = 0.020).
Our findings reveal promising results for non-invasive CT-scan-based prediction of CD73 expression in CRLM and warrant further validation as to whether rad-CD73 could assist oncologists as a biomarker of prognosis and response to immunotherapies targeting the adenosine pathway.
寻找肿瘤免疫特征的无创放射组学替代物可以帮助识别更有可能对新型免疫检查点抑制剂产生反应的患者。特别是，CD73 是一种外核苷酸酶，可催化细胞外 AMP 分解为免疫抑制腺苷，可被治疗性抗体阻断。高表达 CD73 的结直肠癌肝转移（CRLM）在有治愈意图的情况下切除与早期复发和患者生存时间缩短有关。因此，本研究旨在评估术前肝脏 CT 扫描的机器学习分析是否可以估计 CRLM 中 CD73 的高表达与低表达，并评估这种放射组学评分是否具有预后意义。
我们训练了一个 Attentive Interpretable Tabular Learning (TabNet) 模型，从术前 CT 图像中预测组织微阵列免疫荧光（IF）评估的 CD73 分层表达水平（CD73 与 CD73）。从 122 名患者的 160 个匹配 IF 数据的 CRLM 中提取放射组学特征，对其进行预处理并用于训练预测模型。我们应用了五折交叉验证，并在保留测试集上验证了性能。
TabNet 在训练集和保留测试集上的接收器工作特征曲线下面积分别为 0.95（95%CI 0.87 至 1.0）和 0.79（0.65 至 0.92），优于其他机器学习模型。称为 rad-CD73 的 TabNet 衍生评分与匹配的 CRLM 中 CD73 的组织学表达呈正相关（Spearman's ρ=0.6004；P<0.0001）。与 rad-CD73 患者相比，CRLM 切除后复发时间（TTR）和疾病特异性生存（DSS）的中位时间分别为 13.0 与 23.6 个月（P=0.0098）和 53.4 与 126.0 个月（P=0.0222）。rad-CD73 的预后价值独立于标准临床风险评分，对于 TTR（HR=2.11，95%CI 1.30 至 3.45，P<0.005）和 DSS（HR=1.88，95%CI 1.11 至 3.18，P=0.020）均适用。
我们的研究结果揭示了基于无创 CT 扫描预测 CRLM 中 CD73 表达的有前途的结果，需要进一步验证 rad-CD73 是否可以作为预后和对靶向腺苷途径的免疫治疗反应的生物标志物来帮助肿瘤学家。
