skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: SU-F-R-53: CT-Based Radiomics Analysis of Non-Small Cell Lung Cancer Patients Treated with Stereotactic Body Radiation Therapy

Abstract

Purpose: Stereotactic body radiation therapy (SBRT) is the standard of care for medically inoperable non-small cell lung cancer (NSCLC) patients and has demonstrated excellent local control and survival. However, some patients still develop distant metastases and local recurrence, and therefore, there is a clinical need to identify patients at high-risk of disease recurrence. The aim of the current study is to use a radiomics approach to identify imaging biomarkers, based on tumor phenotype, for clinical outcomes in SBRT patients. Methods: Radiomic features were extracted from free breathing computed tomography (CT) images of 113 Stage I-II NSCLC patients treated with SBRT. Their association to and prognostic performance for distant metastasis (DM), locoregional recurrence (LRR) and survival was assessed and compared with conventional features (tumor volume and diameter) and clinical parameters (e.g. performance status, overall stage). The prognostic performance was evaluated using the concordance index (CI). Multivariate model performance was evaluated using cross validation. All p-values were corrected for multiple testing using the false discovery rate. Results: Radiomic features were associated with DM (one feature), LRR (one feature) and survival (four features). Conventional features were only associated with survival and one clinical parameter was associated with LRR and survival. One radiomic featuremore » was significantly prognostic for DM (CI=0.670, p<0.1 from random), while none of the conventional and clinical parameters were significant for DM. The multivariate radiomic model had a higher median CI (0.671) for DM than the conventional (0.618) and clinical models (0.617). Conclusion: Radiomic features have potential to be imaging biomarkers for clinical outcomes that conventional imaging metrics and clinical parameters cannot predict in SBRT patients, such as distant metastasis. Development of a radiomics biomarker that can identify patients at high-risk of recurrence could facilitate personalization of their treatment regimen for an optimized clinical outcome. R.M. had consulting interest with Amgen (ended in 2015).« less

Authors:
; ; ; ; ; ; ; ;  [1]
  1. Brigham Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA (United States)
Publication Date:
OSTI Identifier:
22626771
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 43; Journal Issue: 6; Other Information: (c) 2016 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; 61 RADIATION PROTECTION AND DOSIMETRY; BIOLOGICAL MARKERS; BIOMEDICAL RADIOGRAPHY; COMPUTERIZED TOMOGRAPHY; HAZARDS; IMAGE PROCESSING; LUNGS; METASTASES; MULTIVARIATE ANALYSIS; NEOPLASMS; PATIENTS; PHENOTYPE; RADIOTHERAPY; VALIDATION

Citation Formats

Huynh, E, Coroller, T, Narayan, V, Agrawal, V, Hou, Y, Romano, J, Franco, I, Mak, R, and Aerts, H. SU-F-R-53: CT-Based Radiomics Analysis of Non-Small Cell Lung Cancer Patients Treated with Stereotactic Body Radiation Therapy. United States: N. p., 2016. Web. doi:10.1118/1.4955824.
Huynh, E, Coroller, T, Narayan, V, Agrawal, V, Hou, Y, Romano, J, Franco, I, Mak, R, & Aerts, H. SU-F-R-53: CT-Based Radiomics Analysis of Non-Small Cell Lung Cancer Patients Treated with Stereotactic Body Radiation Therapy. United States. doi:10.1118/1.4955824.
Huynh, E, Coroller, T, Narayan, V, Agrawal, V, Hou, Y, Romano, J, Franco, I, Mak, R, and Aerts, H. 2016. "SU-F-R-53: CT-Based Radiomics Analysis of Non-Small Cell Lung Cancer Patients Treated with Stereotactic Body Radiation Therapy". United States. doi:10.1118/1.4955824.
@article{osti_22626771,
title = {SU-F-R-53: CT-Based Radiomics Analysis of Non-Small Cell Lung Cancer Patients Treated with Stereotactic Body Radiation Therapy},
author = {Huynh, E and Coroller, T and Narayan, V and Agrawal, V and Hou, Y and Romano, J and Franco, I and Mak, R and Aerts, H},
abstractNote = {Purpose: Stereotactic body radiation therapy (SBRT) is the standard of care for medically inoperable non-small cell lung cancer (NSCLC) patients and has demonstrated excellent local control and survival. However, some patients still develop distant metastases and local recurrence, and therefore, there is a clinical need to identify patients at high-risk of disease recurrence. The aim of the current study is to use a radiomics approach to identify imaging biomarkers, based on tumor phenotype, for clinical outcomes in SBRT patients. Methods: Radiomic features were extracted from free breathing computed tomography (CT) images of 113 Stage I-II NSCLC patients treated with SBRT. Their association to and prognostic performance for distant metastasis (DM), locoregional recurrence (LRR) and survival was assessed and compared with conventional features (tumor volume and diameter) and clinical parameters (e.g. performance status, overall stage). The prognostic performance was evaluated using the concordance index (CI). Multivariate model performance was evaluated using cross validation. All p-values were corrected for multiple testing using the false discovery rate. Results: Radiomic features were associated with DM (one feature), LRR (one feature) and survival (four features). Conventional features were only associated with survival and one clinical parameter was associated with LRR and survival. One radiomic feature was significantly prognostic for DM (CI=0.670, p<0.1 from random), while none of the conventional and clinical parameters were significant for DM. The multivariate radiomic model had a higher median CI (0.671) for DM than the conventional (0.618) and clinical models (0.617). Conclusion: Radiomic features have potential to be imaging biomarkers for clinical outcomes that conventional imaging metrics and clinical parameters cannot predict in SBRT patients, such as distant metastasis. Development of a radiomics biomarker that can identify patients at high-risk of recurrence could facilitate personalization of their treatment regimen for an optimized clinical outcome. R.M. had consulting interest with Amgen (ended in 2015).},
doi = {10.1118/1.4955824},
journal = {Medical Physics},
number = 6,
volume = 43,
place = {United States},
year = 2016,
month = 6
}
  • Purpose: To examine the rates and risk factors of radiation pneumonitis (RP) in non-small cell lung cancer (NSCLC) patients treated with stereotactic body radiotherapy (SBRT). Methods and Materials: Dosimetry records for 251 patients with lymph node-negative Stage I-IIB NSCLC and no prior chest radiation therapy (RT) treated with SBRT were reviewed. Patients were coded on the basis of the presence of at least Grade (G) 2 RP using the Common Toxicity Criteria version 2 criteria. Radiation doses, V5, V10, V20, and mean lung dose (MLD) data points were extracted from the dose-volume histogram (DVH). Results: Median PTV volume was 48more » cc. Median prescribed radiation dose was 60 Gy delivered in three fractions to the 80% isodose line. Median age at treatment was 74 years. Median follow-up was 17 months. RP was reported after treatment of 42 lesions: G1 in 19 (8%), G2 in 17 (7%), G3 in 5 (2%), and G4 in 1 (0.4%). Total lung DVHs were available for 143 patients. For evaluable patients, median MLD, V5, V10, and V20 were 4.1 Gy, 20%, 12%, and 4%, respectively. Median MLDs were 4 Gy and 5 Gy for G0-1 and G2-4 groups, respectively (p = 0.14); median V5 was 20% for G0-1 and 24% for G2-4 (p = 0.70); median V10 was 12% in G0-1 and 16% in G2-4 (p = 0.08), and median V20 was 4% in G0-1 and 6.6% in G2-4 (p = 0.05). G2-4 RP was noted in 4.3% of patients with MLD {<=}4 Gy compared with 17.6% of patients with MLD >4 Gy (p = 0.02), and in 4.3% of patients with V20 {<=}4% compared with 16.4% of patients with V20 >4% (p = 0.03). Conclusion: Overall rate of G2-4 RP in our population treated with SBRT was 9.4%. Development of symptomatic RP in this series correlated with MLD and V20.« less
  • Purpose: To determine the effect of biologically effective dose (BED{sub 10}) and radiation treatment schedule on overall survival (OS) in patients with early-stage non-small cell lung cancer (NSCLC) undergoing stereotactic body radiation therapy (SBRT). Methods and Materials: Using data from 65 treatment centers in the United States, we retrospectively reviewed the records of T1-2 N0 NSCLC patients undergoing SBRT alone from 2006 to 2014. Biologically relevant covariates, including dose per fraction, number of fractions, and time between fractions, were used to quantify BED{sub 10} and radiation treatment schedule. The linear-quadratic equation was used to calculate BED{sub 10} and to generatemore » a dichotomous dose variable of <105 Gy versus ≥105 Gy BED{sub 10}. The primary outcome was OS. We used the Kaplan-Meier method, the log–rank test, and Cox proportional hazards regression with propensity score matching to determine whether prescription BED{sub 10} was associated with OS. Results: We identified 747 patients who met inclusion criteria. The median BED{sub 10} was 132 Gy, and 59 (7.7%) had consecutive-day fractions. Median follow-up was 41 months, and 452 patients (60.5%) had died by the conclusion of the study. The 581 patients receiving ≥105 Gy BED{sub 10} had a median survival of 28 months, whereas the 166 patients receiving <105 Gy BED{sub 10} had a median survival of 22 months (log–rank, P=.01). Radiation treatment schedule was not a significant predictor of OS on univariable analysis. After adjusting for T stage, sex, tumor histology, and Eastern Cooperative Oncology Group performance status, BED{sub 10} ≥105 Gy versus <105 Gy remained significantly associated with improved OS (hazard ratio 0.78, 95% confidence interval 0.62-0.98, P=.03). Propensity score matching on imbalanced variables within high- and low-dose cohorts confirmed a survival benefit with higher prescription dose. Conclusions: We found that dose escalation to 105 Gy BED{sub 10} and beyond may improve survival in NSCLC patients treated with SBRT.« less
  • Purpose: Quantification of volume changes on CBCT during SBRT for NSCLC may provide a useful radiological marker for radiation response and adaptive treatment planning, but the reproducibility of CBCT volume delineation is a concern. This study is to quantify inter-scan/inter-observer variability in tumor volume delineation on CBCT. Methods: Twenty earlystage (stage I and II) NSCLC patients were included in this analysis. All patients were treated with SBRT with a median dose of 54 Gy in 3 to 5 fractions. Two physicians independently manually contoured the primary gross tumor volume on CBCTs taken immediately before SBRT treatment (Pre) and after themore » same SBRT treatment (Post). Absolute volume differences (AVD) were calculated between the Pre and Post CBCTs for a given treatment to quantify inter-scan variability, and then between the two observers for a given CBCT to quantify inter-observer variability. AVD was also normalized with respect to average volume to obtain relative volume differences (RVD). Bland-Altman approach was used to evaluate variability. All statistics were calculated with SAS version 9.4. Results: The 95% limit of agreement (mean ± 2SD) on AVD and RVD measurements between Pre and Post scans were −0.32cc to 0.32cc and −0.5% to 0.5% versus −1.9 cc to 1.8 cc and −15.9% to 15.3% for the two observers respectively. The 95% limit of agreement of AVD and RVD between the two observers were −3.3 cc to 2.3 cc and −42.4% to 28.2% respectively. The greatest variability in inter-scan RVD was observed with very small tumors (< 5 cc). Conclusion: Inter-scan variability in RVD is greatest with small tumors. Inter-observer variability was larger than inter-scan variability. The 95% limit of agreement for inter-observer and inter-scan variability (∼15–30%) helps define a threshold for clinically meaningful change in tumor volume to assess SBRT response, with larger thresholds needed for very small tumors. Part of the work was funded by a Kaye award; Disclosure/Conflict of interest: Raymond H. Mak: Stock ownership: Celgene, Inc. Consulting: Boehringer-Ingelheim, Inc.« less
  • Purpose: To compare, using the National Cancer Database, survival, pathologic, and surgical outcomes in patients with stage IIIA non-small cell lung cancer treated with differential doses of neoadjuvant chemoradiation therapy, with the aim to discern whether radiation dose escalation was associated with a comparative effectiveness benefit and/or toxicity risk. Methods and Materials: Patients in the National Cancer Database with stage IIIA non-small cell lung cancer treated with neoadjuvant chemoradiation therapy and surgery between 1998 and 2005 were analyzed. Dose strata were divided between 36 to 45 Gy (low-dose radiation therapy, LD-RT), 45 to 54 Gy (inclusive, standard-dose, SD-RT), and 54 to 74 Gymore » (high-dose, HD-RT). Outcomes included overall survival, residual nodal disease, positive surgical margin status, hospital length of stay, and adverse surgical outcomes (30-day mortality or readmission). Results: The cohort consisted of 1041 patients: 233 (22%) LD-RT, 584 (56%) SD-RT, and 230 (22%) HD-RT. The median, 3-year, and 5-year overall survival outcomes were 34.9 months, 48%, and 37%, respectively. On univariable analysis, patients treated with SD-RT experienced prolonged overall survival (median 38.3 vs 31.8 vs 29.0 months for SD-RT, LD-RT, and HD-RT, respectively, P=.0089), which was confirmed on multivariable analysis (hazard ratios 0.77 and 0.81 vs LD and HD, respectively). Residual nodal disease was seen less often after HD-RT (25.5% vs 31.8% and 37.5% for HD-RT, LD-RT, and SD-RT, respectively, P=.0038). Patients treated with SD-RT had fewer prolonged hospital stays. There were no differences in positive surgical margin status or adverse surgical outcomes between the cohorts. Conclusions: Neoadjuvant chemoradiation therapy between 45 and 54 Gy was associated with superior survival in comparison with doses above and below this threshold. Although this conclusion is limited by selection bias, clear candidates for trimodality therapy do not seem to achieve additional benefit with dose escalation.« less
  • Purpose: To determine the comparative effectiveness of different stereotactic body radiation therapy (SBRT) dosing regimens for early-stage non–small-cell lung cancer, using a large national database, focusing on the relative impact of dose as a function of tumor stage. Methods and Materials: The study included patients in the National Cancer Database from 2003 to 2006 with T1-T2N0M0 inoperable lung cancer (n=498). The biologically effective dose (BED) was calculated according to the linear quadratic formula using an α/β ratio of 10. High versus lower-dose (HD vs LD) SBRT was defined as a calculated BED above or below 150 Gy. Overall survival was estimated using Kaplan-Meiermore » methods and Cox proportional hazard regression. Results: The 5 most common dose fractionation schemes (percentage of cohort) used were 20 Gy × 3 (34%), 12 Gy × 4 (16%), 18 Gy × 3 (10%), 15 Gy × 3 (10%), and 16 Gy × 3 (4%). The median calculated BED was 150 Gy (interquartile range 106-166 Gy). The 3-year overall survival (OS) for patients who received HD versus LD was 55% versus 46% (log–rank P=.03). On subset analysis of the T1 cohort there was no association between calculated BED and 3-year OS (61% vs 60% with HD vs LD, P=.9). Among the T2 cohort, patients receiving HD experienced superior 3-year OS (37% vs 24%, P=.01). On multivariable analysis, factors independently prognostic for mortality were female gender (hazard ratio [HR] 0.76, P=.01), T2 tumor (HR 1.99, P=.0001), and HD (HR 0.68, P=.001). Conclusions: This comparative effectiveness analysis of SBRT dose for patients with stage I non–small-cell lung cancer suggests that higher doses (>150 Gy BED) are associated with a significant survival benefit in patients with T2 tumors.« less