Predicting survival time of lung cancer patients using radiomic analysis

被引:60
作者
Chaddad, Ahmad [1 ,2 ]
Desrosiers, Christian [2 ]
Toews, Matthew [2 ]
Abdulkarim, Bassam [1 ]
机构
[1] McGill Univ, Div Radiat Oncol, Montreal, PQ, Canada
[2] Econ Technol Super, Lab Imagery Vis & Artificial Intelligence, Montreal, PQ, Canada
关键词
lung cancer; NSCLC; cancer staging; radiomics; texture features; POTENTIAL MARKER; TEXTURE ANALYSIS; PROGNOSTIC VALUE; CT IMAGES; CELL; FEATURES; NODULE; HETEROGENEITY; PRETREATMENT; REPRODUCIBILITY;
D O I
10.18632/oncotarget.22251
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Objectives: This study investigates the prediction of Non-small cell lung cancer (NSCLC) patient survival outcomes based on radiomic texture and shape features automatically extracted from tumor image data. Materials and Methods: Retrospective analysis involves CT scans of 315 NSCLC patients from The Cancer Imaging Archive (TCIA). A total of 24 image features are computed from labeled tumor volumes of patients within groups defined using NSCLC subtype and TNM staging information. Spearman's rank correlation, Kaplan-Meier estimation and log-rank tests were used to identify features related to long/short NSCLC patient survival groups. Automatic random forest classification was used to predict patient survival group from multivariate feature data. Significance is assessed at P < 0.05 following Holm-Bonferroni correction for multiple comparisons. Results: Significant correlations between radiomic features and survival were observed for four clinical groups: (group, [absolute correlation range]): (large cell carcinoma (LCC) [0.35, 0.43]), (tumor size T2, [0.31, 0.39]), (non lymph node metastasis N0, [0.3, 0.33]), (TNM stage I, [0.39, 0.48]). Significant log-rank relationships between features and survival time were observed for three clinical groups: (group, hazard ratio): (LCC, 3.0), (LCC, 3.9), (T2, 2.5) and (stage I, 2.9). Automatic survival prediction performance (i.e. below/above median) is superior for combined radiomic features with age-TNM in comparison to standard TNM clinical staging information (clinical group, mean area-under-the-ROC-curve (AUC)): (LCC, 75.73%), (N0, 70.33%), (T2, 70.28%) and (TNM-I, 76.17%). Conclusion: Quantitative lung CT imaging features can be used as indicators of survival, in particular for patients with large-cell-carcinoma (LCC), primary-tumor-sizes (T2) and no lymph-node-metastasis (N0).
引用
收藏
页码:104393 / 104407
页数:15
相关论文
共 48 条
[1]   Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J].
Aerts, Hugo J. W. L. ;
Velazquez, Emmanuel Rios ;
Leijenaar, Ralph T. H. ;
Parmar, Chintan ;
Grossmann, Patrick ;
Cavalho, Sara ;
Bussink, Johan ;
Monshouwer, Rene ;
Haibe-Kains, Benjamin ;
Rietveld, Derek ;
Hoebers, Frank ;
Rietbergen, Michelle M. ;
Leemans, C. Rene ;
Dekker, Andre ;
Quackenbush, John ;
Gillies, Robert J. ;
Lambin, Philippe .
NATURE COMMUNICATIONS, 2014, 5
[2]   Molecular classification of nonsmall cell lung cancer using a 4-protein quantitative assay [J].
Anagnostou, Valsamo K. ;
Dimou, Anastasios T. ;
Botsis, Taxiarchis ;
Killiam, Elizabeth J. ;
Gustavson, Mark D. ;
Homer, Robert J. ;
Boffa, Daniel ;
Zolota, Vassiliki ;
Dougenis, Dimitrios ;
Tanoue, Lynn ;
Gettinger, Scott N. ;
Detterbeck, Frank C. ;
Syrigos, Konstantinos N. ;
Bepler, Gerold ;
Rimm, David L. .
CANCER, 2012, 118 (06) :1607-1618
[3]  
[Anonymous], ONCOTARGET
[4]   Empirical characterization of random forest variable importance measures [J].
Archer, Kelfie J. ;
Kirnes, Ryan V. .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2008, 52 (04) :2249-2260
[5]   Lung cancer: Performance of automated lung nodule detection applied to cancers missed in a CT screening program [J].
Armato, SG ;
Li, F ;
Giger, ML ;
MacMahon, H ;
Sone, S ;
Doi, K .
RADIOLOGY, 2002, 225 (03) :685-692
[6]   The tumour shape of lung adenocarcinoma is related to the postoperative prognosis [J].
Baba, Tetsuro ;
Uramoto, Hidetaka ;
Takenaka, Masaru ;
Oka, Souichi ;
Shigematsu, Yoshiki ;
Shimokawa, Hidehiko ;
Hanagiri, Takeshi ;
Tanaka, Fumihiro .
INTERACTIVE CARDIOVASCULAR AND THORACIC SURGERY, 2012, 15 (01) :73-76
[7]   Pathologic stratification of operable lung adenocarcinoma using radiomics features extracted from dual energy ct images [J].
Bae, Jung Min ;
Jeong, Ji Yun ;
Lee, Ho Yun ;
Sohn, Insuk ;
Kim, Hye Seung ;
Son, Ji Ye ;
Kwon, O. Jung ;
Choi, Joon Young ;
Lee, Kyung Soo ;
Shim, Young Mog .
ONCOTARGET, 2017, 8 (01) :523-535
[8]   Reproducibility and Prognosis of Quantitative Features Extracted from CT Images [J].
Balagurunathan, Yoganand ;
Gu, Yuhua ;
Wang, Hua ;
Kumar, Virendra ;
Grove, Olya ;
Hawkins, Sam ;
Kim, Jongphil ;
Goldgof, Dmitry B. ;
Hall, Lawrence O. ;
Gatenby, Robert A. ;
Gillies, Robert J. .
TRANSLATIONAL ONCOLOGY, 2014, 7 (01) :72-87
[9]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[10]   A quantitative study of shape descriptors from glioblastoma multiforme phenotypes for predicting survival outcome [J].
Chaddad, Ahmad ;
Desrosiers, Christian ;
Hassan, Lama ;
Tanougast, Camel .
BRITISH JOURNAL OF RADIOLOGY, 2016, 89 (1068)