David V Fried1, Susan L Tucker2, Shouhao Zhou3, Zhongxing Liao4, Osama Mawlawi5, Geoffrey Ibbott1, Laurence E Court6. 1. Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas; Graduate School of Biomedical Sciences, The University of Texas Health Science Center at Houston, Houston, Texas. 2. Department of Bioinformatics and Computational Biology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 3. Division of Quantitative Sciences, Department of Bioinformatics and Computational Biology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 4. Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, Texas. 5. Graduate School of Biomedical Sciences, The University of Texas Health Science Center at Houston, Houston, Texas. 6. Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, Texas; Graduate School of Biomedical Sciences, The University of Texas Health Science Center at Houston, Houston, Texas. Electronic address: LECourt@mdanderson.org.
Abstract
PURPOSE: To determine whether pretreatment CT texture features can improve patient risk stratification beyond conventional prognostic factors (CPFs) in stage III non-small cell lung cancer (NSCLC). METHODS AND MATERIALS: We retrospectively reviewed 91 cases with stage III NSCLC treated with definitive chemoradiation therapy. All patients underwent pretreatment diagnostic contrast enhanced computed tomography (CE-CT) followed by 4-dimensional CT (4D-CT) for treatment simulation. We used the average-CT and expiratory (T50-CT) images from the 4D-CT along with the CE-CT for texture extraction. Histogram, gradient, co-occurrence, gray tone difference, and filtration-based techniques were used for texture feature extraction. Penalized Cox regression implementing cross-validation was used for covariate selection and modeling. Models incorporating texture features from the 33 image types and CPFs were compared to those with models incorporating CPFs alone for overall survival (OS), local-regional control (LRC), and freedom from distant metastases (FFDM). Predictive Kaplan-Meier curves were generated using leave-one-out cross-validation. Patients were stratified based on whether their predicted outcome was above or below the median. Reproducibility of texture features was evaluated using test-retest scans from independent patients and quantified using concordance correlation coefficients (CCC). We compared models incorporating the reproducibility seen on test-retest scans to our original models and determined the classification reproducibility. RESULTS: Models incorporating both texture features and CPFs demonstrated a significant improvement in risk stratification compared to models using CPFs alone for OS (P=.046), LRC (P=.01), and FFDM (P=.005). The average CCCs were 0.89, 0.91, and 0.67 for texture features extracted from the average-CT, T50-CT, and CE-CT, respectively. Incorporating reproducibility within our models yielded 80.4% (±3.7% SD), 78.3% (±4.0% SD), and 78.8% (±3.9% SD) classification reproducibility in terms of OS, LRC, and FFDM, respectively. CONCLUSIONS: Pretreatment tumor texture may provide prognostic information beyond that obtained from CPFs. Models incorporating feature reproducibility achieved classification rates of ∼80%. External validation would be required to establish texture as a prognostic factor.
PURPOSE: To determine whether pretreatment CT texture features can improve patient risk stratification beyond conventional prognostic factors (CPFs) in stage III non-small cell lung cancer (NSCLC). METHODS AND MATERIALS: We retrospectively reviewed 91 cases with stage III NSCLC treated with definitive chemoradiation therapy. All patients underwent pretreatment diagnostic contrast enhanced computed tomography (CE-CT) followed by 4-dimensional CT (4D-CT) for treatment simulation. We used the average-CT and expiratory (T50-CT) images from the 4D-CT along with the CE-CT for texture extraction. Histogram, gradient, co-occurrence, gray tone difference, and filtration-based techniques were used for texture feature extraction. Penalized Cox regression implementing cross-validation was used for covariate selection and modeling. Models incorporating texture features from the 33 image types and CPFs were compared to those with models incorporating CPFs alone for overall survival (OS), local-regional control (LRC), and freedom from distant metastases (FFDM). Predictive Kaplan-Meier curves were generated using leave-one-out cross-validation. Patients were stratified based on whether their predicted outcome was above or below the median. Reproducibility of texture features was evaluated using test-retest scans from independent patients and quantified using concordance correlation coefficients (CCC). We compared models incorporating the reproducibility seen on test-retest scans to our original models and determined the classification reproducibility. RESULTS: Models incorporating both texture features and CPFs demonstrated a significant improvement in risk stratification compared to models using CPFs alone for OS (P=.046), LRC (P=.01), and FFDM (P=.005). The average CCCs were 0.89, 0.91, and 0.67 for texture features extracted from the average-CT, T50-CT, and CE-CT, respectively. Incorporating reproducibility within our models yielded 80.4% (±3.7% SD), 78.3% (±4.0% SD), and 78.8% (±3.9% SD) classification reproducibility in terms of OS, LRC, and FFDM, respectively. CONCLUSIONS: Pretreatment tumor texture may provide prognostic information beyond that obtained from CPFs. Models incorporating feature reproducibility achieved classification rates of ∼80%. External validation would be required to establish texture as a prognostic factor.
Authors: Balaji Ganeshan; Vicky Goh; Henry C Mandeville; Quan Sing Ng; Peter J Hoskin; Kenneth A Miles Journal: Radiology Date: 2012-11-20 Impact factor: 11.105
Authors: Dan J Raz; M Roshni Ray; Jae Y Kim; Biao He; Miquel Taron; Marcin Skrzypski; Mark Segal; David R Gandara; Rafael Rosell; David M Jablons Journal: Clin Cancer Res Date: 2008-09-01 Impact factor: 12.531
Authors: Gary J R Cook; Connie Yip; Muhammad Siddique; Vicky Goh; Sugama Chicklore; Arunabha Roy; Paul Marsden; Shahreen Ahmad; David Landau Journal: J Nucl Med Date: 2012-11-30 Impact factor: 10.057
Authors: Haiden A Huskamp; Nancy L Keating; Jennifer L Malin; Alan M Zaslavsky; Jane C Weeks; Craig C Earle; Joan M Teno; Beth A Virnig; Katherine L Kahn; Yulei He; John Z Ayanian Journal: Arch Intern Med Date: 2009-05-25
Authors: Bruno Hochhegger; Matheus Zanon; Stephan Altmayer; Gabriel S Pacini; Fernanda Balbinot; Martina Z Francisco; Ruhana Dalla Costa; Guilherme Watte; Marcel Koenigkam Santos; Marcelo C Barros; Diana Penha; Klaus Irion; Edson Marchiori Journal: Lung Date: 2018-10-09 Impact factor: 2.584
Authors: Zijian Zhang; Jinzhong Yang; Angela Ho; Wen Jiang; Jennifer Logan; Xin Wang; Paul D Brown; Susan L McGovern; Nandita Guha-Thakurta; Sherise D Ferguson; Xenia Fave; Lifei Zhang; Dennis Mackin; Laurence E Court; Jing Li Journal: Eur Radiol Date: 2017-11-24 Impact factor: 5.315
Authors: Emmanuel Rios Velazquez; Chintan Parmar; Ying Liu; Thibaud P Coroller; Gisele Cruz; Olya Stringfield; Zhaoxiang Ye; Mike Makrigiorgos; Fiona Fennessy; Raymond H Mak; Robert Gillies; John Quackenbush; Hugo J W L Aerts Journal: Cancer Res Date: 2017-05-31 Impact factor: 12.701