Department of Radiology, New York-Presbyterian Hospital, Columbia University Vagelos College of Physicians and Surgeons, New York, NY, USA.
Department of Molecular Imaging and Therapy, Fred Hutchinson Cancer Center, Seattle, WA, USA.
Eur Radiol. 2024 Sep;34(9):5829-5841. doi: 10.1007/s00330-024-10637-3. Epub 2024 Feb 15.
Immunotherapy has dramatically altered the therapeutic landscape for oncology, but more research is needed to identify patients who are likely to achieve durable clinical benefit and those who may develop unacceptable side effects. We investigated the role of artificial intelligence in PET/SPECT-guided approaches for immunotherapy-treated patients.
We performed a scoping review of MEDLINE, CENTRAL, and Embase databases using key terms related to immunotherapy, PET/SPECT imaging, and AI/radiomics through October 12, 2022.
Of the 217 studies identified in our literature search, 24 relevant articles were selected. The median (interquartile range) sample size of included patient cohorts was 63 (157). Primary tumors of interest were lung (n = 14/24, 58.3%), lymphoma (n = 4/24, 16.7%), or melanoma (n = 4/24, 16.7%). A total of 28 treatment regimens were employed, including anti-PD-(L)1 (n = 13/28, 46.4%) and anti-CTLA-4 (n = 4/28, 14.3%) monoclonal antibodies. Predictive models were built from imaging features using univariate radiomics (n = 7/24, 29.2%), radiomics (n = 12/24, 50.0%), or deep learning (n = 5/24, 20.8%) and were most often used to prognosticate (n = 6/24, 25.0%) or describe tumor phenotype (n = 5/24, 20.8%). Eighteen studies (75.0%) performed AI model validation.
Preliminary results suggest broad potential for the application of AI-guided immunotherapy management after further validation of models on large, prospective, multicenter cohorts.
This scoping review describes how artificial intelligence models are built to make predictions based on medical imaging and explores their application specifically in the PET and SPECT examination of immunotherapy-treated cancers.
• Immunotherapy has drastically altered the cancer treatment landscape but is known to precipitate response patterns that are not accurately accounted for by traditional imaging methods. • There is an unmet need for better tools to not only facilitate in-treatment evaluation but also to predict, a priori, which patients are likely to achieve a good response with a certain treatment as well as those who are likely to develop side effects. • Artificial intelligence applied to PET/SPECT imaging of immunotherapy-treated patients is mainly used to make predictions about prognosis or tumor phenotype and is built from baseline, pre-treatment images. Further testing is required before a true transition to clinical application can be realized.
免疫疗法极大地改变了肿瘤学的治疗格局，但仍需要更多的研究来确定哪些患者可能获得持久的临床获益，以及哪些患者可能出现不可接受的副作用。我们研究了人工智能在正电子发射断层扫描/单光子发射计算机断层扫描（PET/SPECT）引导的免疫治疗患者中的作用。
我们通过使用与免疫疗法、PET/SPECT 成像和 AI/放射组学相关的关键词，在 MEDLINE、CENTRAL 和 Embase 数据库中进行了范围界定的综述，检索时间截至 2022 年 10 月 12 日。
在我们的文献检索中确定了 217 项研究，选择了 24 篇相关文章。纳入的患者队列的中位数（四分位距）样本量为 63（157）。主要关注的原发肿瘤为肺癌（n=14/24，58.3%）、淋巴瘤（n=4/24，16.7%）或黑色素瘤（n=4/24，16.7%）。共采用了 28 种治疗方案，包括抗 PD-(L)1（n=13/28，46.4%）和抗 CTLA-4（n=4/28，14.3%）单克隆抗体。使用单变量放射组学（n=7/24，29.2%）、放射组学（n=12/24，50.0%）或深度学习（n=5/24，20.8%）从成像特征中构建预测模型，并最常用于预后（n=6/24，25.0%）或描述肿瘤表型（n=5/24，20.8%）。18 项研究（75.0%）对人工智能模型进行了验证。
初步结果表明，在对大型、前瞻性、多中心队列进行模型进一步验证后，人工智能指导的免疫治疗管理具有广泛的应用潜力。
本范围综述描述了如何构建人工智能模型来基于医学成像进行预测，并探讨了它们在正电子发射断层扫描和单光子发射计算机断层扫描检查免疫治疗癌症中的具体应用。
免疫疗法极大地改变了癌症治疗格局，但已知它会引发传统成像方法无法准确解释的反应模式。
目前迫切需要更好的工具，不仅要促进治疗中的评估，还要预测哪些患者可能对某种治疗有良好反应，以及哪些患者可能出现副作用。
应用于免疫治疗患者的正电子发射断层扫描/单光子发射计算机断层扫描成像的人工智能主要用于预测预后或肿瘤表型，并基于基线、治疗前的图像构建。在真正过渡到临床应用之前，还需要进一步的测试。
