Radiomic-Based Pathological Response Prediction from Primary Tumors and Lymph Nodes in NSCLC.
发表日期： 2017.03.01 来源：J Thorac Oncol. 2017 Mar;12(3):467-476.
Coroller TP1, Agrawal V1, Huynh E1, Narayan V1, Lee SW1, Mak RH#1, Aerts HJWL#1,2.
1. Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
2. Department of Radiology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
# Contributed equally
Noninvasive biomarkers that capture the total tumor burden could provide important complementary information for precision medicine to aid clinical decision making. We investigated the value of radiomic data extracted from pretreatment computed tomography images of the primary tumor and lymph nodes in predicting pathological response after neoadjuvant chemoradiation before surgery.
A total of 85 patients with resectable locally advanced (stage II-III) NSCLC (median age 60.3 years, 65% female) treated from 2003 to 2013 were included in this institutional review board-approved study. Radiomics analysis was performed on 85 primary tumors and 178 lymph nodes to discriminate between pathological complete response (pCR) and gross residual disease (GRD). Twenty nonredundant and stable features (10 from each site) were evaluated by using the area under the curve (AUC) (all p values were corrected for multiple hypothesis testing). Classification performance of each feature set was evaluated by random forest and nested cross validation.
三个基本特征（描述原发性肿瘤球形度和淋巴结同质性）对pCR预测具有相似的显著性表现（所有的AUC = 0.67，p < 0.05）。两个特征（定量淋巴结同质性）预测GRD（AUC范围0.72-0.75，p < 0.05），并且显著优于主要特征（AUC = 0.62）。多变量分析显示，对于pCR，单独设置的影像组学特征具有最好的分类能力（中值AUC = 0.68）。此外，对于GRD分类，影像组学和临床数据的组合显著优于其他所有特征组（中值AUC = 0.73）。
Three radiomic features (describing primary tumor sphericity and lymph node homogeneity) were significantly predictive of pCR with similar performances (all AUC = 0.67, p < 0.05). Two features (quantifying lymph node homogeneity) were predictive of GRD (AUC range 0.72-0.75, p < 0.05) and performed significantly better than the primary features (AUC = 0.62). Multivariate analysis showed that for pCR, the radiomic features set alone had the best-performing classification (median AUC = 0.68). Furthermore, for GRD classification, the combination of radiomic and clinical data significantly outperformed all other feature sets (median AUC = 0.73).
Lymph node phenotypic information was significantly predictive for pathological response and showed higher classification performance than radiomic features obtained from the primary tumor.
Biostatistics; Lymph nodes; NSCLC; Pathological response; Quantitative imaging; Radiomics