Smith David S, Lippenszky Levente, LeNoue-Newton Michele L, Jain Neha M, Mittendorf Kathleen F, Micheel Christine M, Cella Patrick A, Wolber Jan, Osterman Travis J
Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, TN.
Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN.
JCO Clin Cancer Inform. 2025 Feb;9:e2400198. doi: 10.1200/CCI-24-00198. Epub 2025 Feb 20.
Primary barriers to application of immune checkpoint inhibitor (ICI) therapy for cancer include severe side effects (such as potentially life threatening pneumonitis [PN]), which can cause the discontinuation of treatment. Predicting which patients may develop PN while on ICI would improve both safety and potential efficacy because treatments could be safely administered for longer or discontinued before severe toxicity.
Starting from a cohort of 3,351 patients with cancer who received previous ICI therapy at the Vanderbilt University Medical Center, we curated 2,700 contrast chest computed tomography (CT) volumes for 671 patients. Three different pure imaging models predicted the potential for PN using only a single time point before the first ICI dose.
The first model used 109 radiomics features only and achieved an AUC of 0.747 (CI, 0.705 to 0.789) with a positive predictive value (PPV) of 0.244 (CI, 0.211 to 0.276) at a sensitivity of 0.553 (CI, 0.485 to 0.621) using mainly features describing the global lung properties. The second model used a convolutional neural network (CNN) on the raw CTs to improve to an AUC of 0.819 (CI, 0.781 to 0.857) with a PPV of 0.244 (CI, 0.203 to 0.284) at a sensitivity of 0.743 (CI, 0.681 to 0.806). The third model combined both radiomics and deep learning but, with an AUC of 0.829 (CI, 0.797 to 0.862) and a PPV of 0.254 (CI, 0.228 to 0.281) at a sensitivity of 0.780 (CI, 0.721 to 0.840), did not show a significant improvement on the CNN-only model.
This new model suggests the utility of deep learning in PN prediction over traditional pure radiomics and promises better management for patients receiving ICI and the ability to better stratify patients in immunotherapy drug trials.
免疫检查点抑制剂（ICI）疗法应用于癌症的主要障碍包括严重的副作用（如可能危及生命的肺炎[PN]），这可能导致治疗中断。预测哪些患者在接受ICI治疗时可能发生PN，将提高安全性和潜在疗效，因为治疗可以更安全地延长使用时间，或在出现严重毒性之前停药。
从范德比尔特大学医学中心接受过ICI治疗的3351例癌症患者队列开始，我们为671例患者整理了2700份胸部对比计算机断层扫描（CT）图像。三种不同的纯影像模型仅使用首次ICI给药前的单个时间点来预测PN的可能性。
第一个模型仅使用109个放射组学特征，AUC为0.747（95%CI，0.705至0.789），阳性预测值（PPV）为0.244（95%CI，0.211至0.276），敏感性为0.553（95%CI，0.485至0.621），主要使用描述全肺特征的特征。第二个模型在原始CT图像上使用卷积神经网络（CNN），将AUC提高到0.819（95%CI，0.781至0.857），PPV为0.244（95%CI，0.203至0.284），敏感性为0.743（95%CI，0.681至0.806）。第三个模型结合了放射组学和深度学习，但AUC为0.829（95%CI，0.797至0.862），PPV为0.254（95%CI，0.228至0.281），敏感性为0.780（95%CI，0.721至0.840），与仅使用CNN的模型相比没有显著改善。
这种新模型表明深度学习在PN预测方面优于传统的纯放射组学，有望为接受ICI治疗的患者提供更好的管理，并能够在免疫治疗药物试验中更好地对患者进行分层。
