Wu Jia, Li Chao, Gensheimer Michael, Padda Sukhmani, Kato Fumi, Shirato Hiroki, Wei Yiran, Schönlieb Carola-Bibiane, Price Stephen John, Jaffray David, Heymach John, Neal Joel W, Loo Billy W, Wakelee Heather, Diehn Maximilian, Li Ruijiang
Department of Radiation Oncology, Stanford University School of Medicine, Palo Alto, CA, USA.
Department of Imaging Physics, MD Anderson Cancer Center, Houston, TX, USA.
Nat Mach Intell. 2021 Sep;3:787-798. doi: 10.1038/s42256-021-00377-0. Epub 2021 Aug 9.
Radiomics refers to the high-throughput extraction of quantitative features from radiological scans and is widely used to search for imaging biomarkers for prediction of clinical outcomes. Current radiomic signatures suffer from limited reproducibility and generalizability, because most features are dependent on imaging modality and tumor histology, making them sensitive to variations in scan protocol. Here, we propose novel radiological features that are specially designed to ensure compatibility across diverse tissues and imaging contrast. These features provide systematic characterization of tumor morphology and spatial heterogeneity. In an international multi-institution study of 1,682 patients, we discover and validate four unifying imaging subtypes across three malignancies and two major imaging modalities. These tumor subtypes demonstrate distinct molecular characteristics and prognoses after conventional therapies. In advanced lung cancer treated with immunotherapy, one subtype is associated with improved survival and increased tumor-infiltrating lymphocytes compared with the others. Deep learning enables automatic tumor segmentation and reproducible subtype identification, which can facilitate practical implementation. The unifying radiological tumor classification may inform prognosis and treatment response for precision medicine.
放射组学是指从放射影像扫描中高通量提取定量特征，并广泛用于寻找预测临床结果的影像生物标志物。目前的放射组学特征存在可重复性和可推广性有限的问题，因为大多数特征依赖于成像模式和肿瘤组织学，这使得它们对扫描协议的变化很敏感。在此，我们提出了专门设计的新型放射学特征，以确保在不同组织和成像对比度之间的兼容性。这些特征提供了肿瘤形态和空间异质性的系统表征。在一项对1682名患者的国际多机构研究中，我们在三种恶性肿瘤和两种主要成像模式中发现并验证了四种统一的影像亚型。这些肿瘤亚型在传统治疗后表现出不同的分子特征和预后。在接受免疫治疗的晚期肺癌中，与其他亚型相比，一种亚型与生存率提高和肿瘤浸润淋巴细胞增加相关。深度学习能够实现自动肿瘤分割和可重复的亚型识别，这有助于实际应用。统一的放射学肿瘤分类可为精准医学的预后和治疗反应提供参考。
