Monica Khunger
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Monica Khunger has a total of 97 co-authors. Here are the top co-authors by number of shared publications:
Vamsidhar Velcheti
NYU Langone, Perlmutter Cancer Center, New York, NY
11 shared publications- Vamsidhar Velcheti
Department of Hematology and Oncology, Cleveland Clinic, Cleveland, OH
9 shared publications Sagar Rakshit
Department of Internal Medicine, Cleveland Clinic, Cleveland, Ohio, United States of America
8 shared publicationsAnant Madabhushi
Case Western Reserve University, Department of Biomedical Engineering, Cleveland, OH
6 shared publicationsArjun Khunger
Department of Hematology and Oncology, Taussig Cancer Institute, Cleveland Clinic, Cleveland, Ohio, United States of America
6 shared publicationsJames Stevenson
Cleveland Clinic, Cleveland, OH
6 shared publications
Latest Publications
- 1 August 2020
- Published by Elsevier in Seminars in Oncology
- Vol. 47 (4) , 229-237
The evolving management of metastatic triple negative breast cancer
- 1 August 2020
- Published by Elsevier in Seminars in Oncology
- Vol. 47 (4) , 229-237
The evolving management of metastatic triple negative breast cancer
- 20 May 2019
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 37 (15_suppl) , 2588
Intra and perinodular CT delta radiomic features associated with early response to predict overall survival (OS) in immunotherapy-treated non-small cell lung cancer (NSCLC): A multisite multi-agent study.
2588 Background: None of the current biomarkers for predicting response to checkpoint inhibitors (ICIT) for advanced NSCLC are associated with long-term benefits, such as improved OS. In this multi-agent (nivolumab, pembrolizumab, or atezolizumab) multi-site study (Cleveland Clinic, Univ. of Pennsylvania), we demonstrate that changes in computer-extracted textural patterns, from within and 30mm outside the nodules, between baseline and post-treatment CT following ICIT correlate with RECIST-derived responses, and are prognostic of OS. Methods: CT scans from 139 NSCLC patients both pre-, and post 2-3 cycles of ICIT were acquired from 2 sites. Patients with objective response/stable disease per RECIST v1.1 were defined as ‘responders’, and those with progressive disease were ‘non-responders’. The cohort was divided into a discovery (D1 = 50) and two validation sets (D2 = 62, D3 = 27). 454 intranodular texture (IT) features, and 7426 perinodular features (PT) were extracted from the temporalscans, Relative differences were computed to yield a set of ‘delta-radiomic’ descriptors. In D1, 8 features that evolved the most between baseline and post-treatment CT, and performed the best in identifying responders, were determined. These were then used with a Linear Discriminant Analysis classifier to identify the responders from the non-responders. We then computed a radiomic risk score (RRS) system and tested its prognostic ability in assessing differences in OS. Results: A combination of 5 IT, 3 PT delta radiomic features yielded an AUC of 0.88 ± 0.08 in D1 and a corresponding AUC = 0.85 and 0.81 in D2 and D3, respectively. Multivariate survival metrics are shown in Table. Conclusions: Delta-radiomic features, both from inside and outside the nodules, could be used to identify patients likely to derive clinical benefit from ICIT (eg: OS) beyond anatomic response. [Table: see text]
- 20 May 2019
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 37 (15_suppl) , 2588
Intra and perinodular CT delta radiomic features associated with early response to predict overall survival (OS) in immunotherapy-treated non-small cell lung cancer (NSCLC): A multisite multi-agent study.
2588 Background: None of the current biomarkers for predicting response to checkpoint inhibitors (ICIT) for advanced NSCLC are associated with long-term benefits, such as improved OS. In this multi-agent (nivolumab, pembrolizumab, or atezolizumab) multi-site study (Cleveland Clinic, Univ. of Pennsylvania), we demonstrate that changes in computer-extracted textural patterns, from within and 30mm outside the nodules, between baseline and post-treatment CT following ICIT correlate with RECIST-derived responses, and are prognostic of OS. Methods: CT scans from 139 NSCLC patients both pre-, and post 2-3 cycles of ICIT were acquired from 2 sites. Patients with objective response/stable disease per RECIST v1.1 were defined as ‘responders’, and those with progressive disease were ‘non-responders’. The cohort was divided into a discovery (D1 = 50) and two validation sets (D2 = 62, D3 = 27). 454 intranodular texture (IT) features, and 7426 perinodular features (PT) were extracted from the temporalscans, Relative differences were computed to yield a set of ‘delta-radiomic’ descriptors. In D1, 8 features that evolved the most between baseline and post-treatment CT, and performed the best in identifying responders, were determined. These were then used with a Linear Discriminant Analysis classifier to identify the responders from the non-responders. We then computed a radiomic risk score (RRS) system and tested its prognostic ability in assessing differences in OS. Results: A combination of 5 IT, 3 PT delta radiomic features yielded an AUC of 0.88 ± 0.08 in D1 and a corresponding AUC = 0.85 and 0.81 in D2 and D3, respectively. Multivariate survival metrics are shown in Table. Conclusions: Delta-radiomic features, both from inside and outside the nodules, could be used to identify patients likely to derive clinical benefit from ICIT (eg: OS) beyond anatomic response. [Table: see text]
- 1 March 2019
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 1 (2) , e180012
Combination of Peri- and Intratumoral Radiomic Features on Baseline CT Scans Predicts Response to Chemotherapy in Lung Adenocarcinoma
PurposeTo identify the role of radiomics texture features both within and outside the nodule in predicting (a) time to progression (TTP) and overall survival (OS) as well as (b) response to chemotherapy in patients with non–small cell lung cancer (NSCLC).Materials and MethodsData in a total of 125 patients who had been treated with pemetrexed-based platinum doublet chemotherapy at Cleveland Clinic were retrospectively analyzed. The patients were divided randomly into two sets with the constraint that there were an equal number of responders and nonresponders in the training set. The training set comprised 53 patients with NSCLC, and the validation set comprised 72 patients. A machine learning classifier trained with radiomic texture features extracted from intra- and peritumoral regions of non–contrast-enhanced CT images was used to predict response to chemotherapy. The radiomic risk-score signature was generated by using least absolute shrinkage and selection operator with the Cox regression model; assoc...
- 1 March 2019
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 1 (2) , e180012
Combination of Peri- and Intratumoral Radiomic Features on Baseline CT Scans Predicts Response to Chemotherapy in Lung Adenocarcinoma
PurposeTo identify the role of radiomics texture features both within and outside the nodule in predicting (a) time to progression (TTP) and overall survival (OS) as well as (b) response to chemotherapy in patients with non–small cell lung cancer (NSCLC).Materials and MethodsData in a total of 125 patients who had been treated with pemetrexed-based platinum doublet chemotherapy at Cleveland Clinic were retrospectively analyzed. The patients were divided randomly into two sets with the constraint that there were an equal number of responders and nonresponders in the training set. The training set comprised 53 patients with NSCLC, and the validation set comprised 72 patients. A machine learning classifier trained with radiomic texture features extracted from intra- and peritumoral regions of non–contrast-enhanced CT images was used to predict response to chemotherapy. The radiomic risk-score signature was generated by using least absolute shrinkage and selection operator with the Cox regression model; assoc...
- Open Access
- 25 October 2018
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 13 (10) , e0197743
Post-treatment changes in hematological parameters predict response to nivolumab monotherapy in non-small cell lung cancer patients
The absolute neutrophil count (ANC), absolute lymphocyte count (ALC), absolute monocyte count (AMC) and neutrophil to lymphocyte ratio (NLR) are known markers of inflammation. We evaluated whether ANC, ALC, AMC and NLR, both before and after treatment with nivolumab, are indicative markers of overall survival (OS) and evaluated change in NLR as a predictive marker of response in non -small cell lung cancer (NSCLC) patients treated with nivolumab. A total of 109 patients with advanced NSCLC treated with nivolumab were included. ANC, ALC, AMC and NLR were examined at initiation of nivolumab therapy and after two cycles. The prognostic role of ANC, ALC, AMC and NLR with OS and changes in NLR ratio were examined with Kaplan-Meier curves and proportional hazard model. Post-treatment NLR ≥5 after two cycles of nivolumab was associated with poor OS (median OS in NLR = <5 vs NLR = ≥5 was 29.1 (16.2–40.9) vs 24.2(16.1–36.2) months respectively, p<0.001). In addition NLR increased in non-responders after two cycles of nivolumab by 6.6±21.8 as compared to responders (p = 0.027). Post-treatment ANC, ALC and NLR are independent prognostic factors in NSCLC patients treated with nivolumab. Changes in NLR can be an early biomarker for response in NSCLC patients treated with nivolumab.
- 25 October 2018
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 13 (10) , e0197743
Open AccessPost-treatment changes in hematological parameters predict response to nivolumab monotherapy in non-small cell lung cancer patients
The absolute neutrophil count (ANC), absolute lymphocyte count (ALC), absolute monocyte count (AMC) and neutrophil to lymphocyte ratio (NLR) are known markers of inflammation. We evaluated whether ANC, ALC, AMC and NLR, both before and after treatment with nivolumab, are indicative markers of overall survival (OS) and evaluated change in NLR as a predictive marker of response in non -small cell lung cancer (NSCLC) patients treated with nivolumab. A total of 109 patients with advanced NSCLC treated with nivolumab were included. ANC, ALC, AMC and NLR were examined at initiation of nivolumab therapy and after two cycles. The prognostic role of ANC, ALC, AMC and NLR with OS and changes in NLR ratio were examined with Kaplan-Meier curves and proportional hazard model. Post-treatment NLR ≥5 after two cycles of nivolumab was associated with poor OS (median OS in NLR = <5 vs NLR = ≥5 was 29.1 (16.2–40.9) vs 24.2(16.1–36.2) months respectively, p<0.001). In addition NLR increased in non-responders after two cycles of nivolumab by 6.6±21.8 as compared to responders (p = 0.027). Post-treatment ANC, ALC and NLR are independent prognostic factors in NSCLC patients treated with nivolumab. Changes in NLR can be an early biomarker for response in NSCLC patients treated with nivolumab.
- Open Access
- 1 August 2018
- Published by Oxford University Press (OUP) in The Oncologist
- Vol. 23 (12) , 1494-1499
Premature Clinical Trial Discontinuation in the Era of Immune Checkpoint Inhibitors
Background: Clinical trial completion is critical for new cancer therapies. Premature trial termination or withdrawal is common and impairs progress. We assessed factors of early terminated/withdrawn oncology trials focusing on trials with immune checkpoint inhibitors (ICI), hypothesizing that the latter may be associated with lower rates of premature discontinuation. Materials and Methods: We reviewed all adult, intervention, oncology trials registered in ClinicalTrials.gov (November 16, 2011, to April 16, 2015) to identify all terminated/withdrawn trials and reasons for termination. Logistics regression model was used to identify factors associated with early termination/withdrawal. Discontinuation rate was compared in trials with and without ICI. Results: We identified 12,875 trials (35% industry funded, 12% federal funded), of which 8.5% were prematurely terminated (5%) or withdrawn (3.5%); the main reasons were poor accrual (33%) and logistical (24%). ICI trials (n = 350) had a nonsignificant lower rate of termination or withdrawal compared with all other oncology trials (5.4% vs. 8.5%; p = .9) and were less likely to discontinue due to poor accrual (nonsignificant difference: 21% vs. 33%; p = .4). ICI trials were also less likely to discontinue compared with all other oncology drug trials (e.g., chemotherapy, targeted inhibitors, antiangiogenesis, biologics; 5.4% vs. 7.9%, respectively, nonsignificant difference). The 4-year cumulative incidence of failing to complete for reasons unrelated to toxicity or efficacy was 18% (95% confidence interval 16%–20%). There was no association between annual incidence across different tumor types or accrual goal and rate of trial termination. Conclusion: Poor accrual represents the main cause of early cancer trial termination. Premature termination/withdrawal rate was not significantly lower in ICI compared with other trials. Clinical trial completion remains a high priority and can be influenced by provider and patient factors. Implications for Practice: Clinical trial completion is critical for new cancer therapies. Premature trial termination or withdrawal is common and impairs progress. This study assessed factors of early terminated/withdrawn oncology trials, focusing on trials with immune checkpoint inhibitors (ICI), and found that poor accrual represents the main cause of early cancer trial termination. Premature termination/withdrawal rate was not significantly lower in immune checkpoint inhibitor trials compared to other trials. The discussion herein is focused on measures taken by the National Cancer Institute and other institutions to improve clinical trial accrual and prevent premature clinical trial discontinuation.
- 1 August 2018
- Published by Oxford University Press (OUP) in The Oncologist
- Vol. 23 (12) , 1494-1499
Open AccessPremature Clinical Trial Discontinuation in the Era of Immune Checkpoint Inhibitors
Background: Clinical trial completion is critical for new cancer therapies. Premature trial termination or withdrawal is common and impairs progress. We assessed factors of early terminated/withdrawn oncology trials focusing on trials with immune checkpoint inhibitors (ICI), hypothesizing that the latter may be associated with lower rates of premature discontinuation. Materials and Methods: We reviewed all adult, intervention, oncology trials registered in ClinicalTrials.gov (November 16, 2011, to April 16, 2015) to identify all terminated/withdrawn trials and reasons for termination. Logistics regression model was used to identify factors associated with early termination/withdrawal. Discontinuation rate was compared in trials with and without ICI. Results: We identified 12,875 trials (35% industry funded, 12% federal funded), of which 8.5% were prematurely terminated (5%) or withdrawn (3.5%); the main reasons were poor accrual (33%) and logistical (24%). ICI trials (n = 350) had a nonsignificant lower rate of termination or withdrawal compared with all other oncology trials (5.4% vs. 8.5%; p = .9) and were less likely to discontinue due to poor accrual (nonsignificant difference: 21% vs. 33%; p = .4). ICI trials were also less likely to discontinue compared with all other oncology drug trials (e.g., chemotherapy, targeted inhibitors, antiangiogenesis, biologics; 5.4% vs. 7.9%, respectively, nonsignificant difference). The 4-year cumulative incidence of failing to complete for reasons unrelated to toxicity or efficacy was 18% (95% confidence interval 16%–20%). There was no association between annual incidence across different tumor types or accrual goal and rate of trial termination. Conclusion: Poor accrual represents the main cause of early cancer trial termination. Premature termination/withdrawal rate was not significantly lower in ICI compared with other trials. Clinical trial completion remains a high priority and can be influenced by provider and patient factors. Implications for Practice: Clinical trial completion is critical for new cancer therapies. Premature trial termination or withdrawal is common and impairs progress. This study assessed factors of early terminated/withdrawn oncology trials, focusing on trials with immune checkpoint inhibitors (ICI), and found that poor accrual represents the main cause of early cancer trial termination. Premature termination/withdrawal rate was not significantly lower in immune checkpoint inhibitor trials compared to other trials. The discussion herein is focused on measures taken by the National Cancer Institute and other institutions to improve clinical trial accrual and prevent premature clinical trial discontinuation.
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15_suppl) , 12058
Tumor PD-L1 heterogeneity in non-small cell lung cancer: Does biopsy size and volume matter?
12058Background: Although patients with high tumor programmed death ligand-1(PD-L1) expression benefit from PD-1/PD-L1 axis inhibitors, many studies have highlighted that a fraction of patients respond to these agents despite lacking detectable PD-L1 expression. Heterogeneity of tumor PD-L1 expression within the tumor has been postulated to be contributing to the limited performance of PD-L1 as a predictive biomarker. We evaluated the PD-L1 expression heterogeneity by comparing the percentage of PD-L1 positive tumor cells as a measure of tumor PD-L1 proportion scores (TPS) using fluorescence immunohistochemistry in paired whole tissue sections (WTS) and tissue microarray (TMA) cores from surgical non-small cell lung cancer (NSCLC) specimens. Methods: WTS and two 0.6mm TMA cores localized at least 3mm apart from each other were prepared from each formalin-fixed, paraffin-embedded surgically resected tumor specimens of 451 patients with stage I-III NSCLC. Using quantitative immunofluorescence with the E1L3N...
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15_suppl) , 12058
Tumor PD-L1 heterogeneity in non-small cell lung cancer: Does biopsy size and volume matter?
12058Background: Although patients with high tumor programmed death ligand-1(PD-L1) expression benefit from PD-1/PD-L1 axis inhibitors, many studies have highlighted that a fraction of patients respond to these agents despite lacking detectable PD-L1 expression. Heterogeneity of tumor PD-L1 expression within the tumor has been postulated to be contributing to the limited performance of PD-L1 as a predictive biomarker. We evaluated the PD-L1 expression heterogeneity by comparing the percentage of PD-L1 positive tumor cells as a measure of tumor PD-L1 proportion scores (TPS) using fluorescence immunohistochemistry in paired whole tissue sections (WTS) and tissue microarray (TMA) cores from surgical non-small cell lung cancer (NSCLC) specimens. Methods: WTS and two 0.6mm TMA cores localized at least 3mm apart from each other were prepared from each formalin-fixed, paraffin-embedded surgically resected tumor specimens of 451 patients with stage I-III NSCLC. Using quantitative immunofluorescence with the E1L3N...
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15_suppl) , 12115
Computer-extracted features relating to spatial arrangement of tumor infiltrating lymphocytes to predict response to nivolumab in non-small cell lung cancer (NSCLC).
12115Background: Immune checkpoint inhibitors are now approved for use as therapy in advanced stage NSCLC. These drugs can decrease risk of progression by up to 60% when compared to standard chemotherapeutic regimens, but only about 20% of treated patients show significant benefit. The current gold standard for predicting response is increased tissue expression of PD-L1, but recent studies have shown this measure to be inadequate. TILs are correlated with PD-L1 levels and with antigen-induced anti-tumor immune pressure, with increased TILs associated with treatment response and longer survival. Recent work suggests that the spatial arrangement of TILs may be prognostic of outcome in several different cancer types. Here we evaluate whether computer-extracted features relating to spatial arrangement of TILs on digitized H&E images could predict response to Nivolumab in NSCLC. Methods: The study included fifty-six NSCLC patients with diagnostic tumor biopsies who were treated with Nivolumab. Responders and n...
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15_suppl) , 12115
Computer-extracted features relating to spatial arrangement of tumor infiltrating lymphocytes to predict response to nivolumab in non-small cell lung cancer (NSCLC).
12115Background: Immune checkpoint inhibitors are now approved for use as therapy in advanced stage NSCLC. These drugs can decrease risk of progression by up to 60% when compared to standard chemotherapeutic regimens, but only about 20% of treated patients show significant benefit. The current gold standard for predicting response is increased tissue expression of PD-L1, but recent studies have shown this measure to be inadequate. TILs are correlated with PD-L1 levels and with antigen-induced anti-tumor immune pressure, with increased TILs associated with treatment response and longer survival. Recent work suggests that the spatial arrangement of TILs may be prognostic of outcome in several different cancer types. Here we evaluate whether computer-extracted features relating to spatial arrangement of TILs on digitized H&E images could predict response to Nivolumab in NSCLC. Methods: The study included fifty-six NSCLC patients with diagnostic tumor biopsies who were treated with Nivolumab. Responders and n...
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15) , 12059
PD-1/PD-L1 interaction and CD25/FOXP3+t cells to predict survival benefit from adjuvant chemotherapy in early stage non-small-cell lung cancer (ES-NSCLC).
12059 Background: Adjuvant chemotherapy (ACT) for ES-NSCLC provides only a modest improvement in survival and is associated with serious adverse effects. Thus, identifying subgroups of ES-NSCLC patients who will benefit from ACT is of high clinical relevance. Utilizing novel digital pathology algorithms, we evaluated relationship between pre-treatment tumor immune microenvironment and survival benefit from ACT in ES-NSCLC patients. Methods: 451 tissue sections of formalin-fixed, paraffin embedded surgical resection specimens from ES-NSCLC patients with/without ACT were tested with multiplexed fluorescence immunohistochemistry assays designed to detect key immune cell markers such as PD-1, PD-L1, CD4, CD8, CD25, FOXP3 and Ki67. Fluorescence Images were acquired on the Vectra platform (Perkin Elmer) and analyzed with novel AQUA algorithms designed to accurately measure the co-localization of PD-1 and PD-L1 (the Interaction Score), regulatory (CD25+/FOXP3+) and activated (Ki67+) T cell subsets. Results: High PD-1/PD-L1 Interaction Scores (≥ 643) and regulatory T cell burden (≥ 1%) in pre-treatment tumors exhibited significant correlations with improved recurrence free (p = 0.003) and overall survival (p = 0.004) in patients receiving ACT after surgery, whereas no difference in survival was observed for patients who received surgery alone (p > 0.5). Median RFS was not reached in signature positive patients vs 93.2 months in signature negative patients. Interestingly, the levels of PD-1 or PD-L1 alone did not predict survival for surgery + ACT or surgery alone patient populations. Conclusions: PD-1/PD-L1 Interaction Score and CD25/FOXP3 positive T cells are predictive of benefit from ACT in patients with ES-NSCLC. Future studies will determine if these biomarker signatures can be used to select patients that may be spared chemotherapy without compromising outcome.
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15) , 12059
PD-1/PD-L1 interaction and CD25/FOXP3+t cells to predict survival benefit from adjuvant chemotherapy in early stage non-small-cell lung cancer (ES-NSCLC).
12059 Background: Adjuvant chemotherapy (ACT) for ES-NSCLC provides only a modest improvement in survival and is associated with serious adverse effects. Thus, identifying subgroups of ES-NSCLC patients who will benefit from ACT is of high clinical relevance. Utilizing novel digital pathology algorithms, we evaluated relationship between pre-treatment tumor immune microenvironment and survival benefit from ACT in ES-NSCLC patients. Methods: 451 tissue sections of formalin-fixed, paraffin embedded surgical resection specimens from ES-NSCLC patients with/without ACT were tested with multiplexed fluorescence immunohistochemistry assays designed to detect key immune cell markers such as PD-1, PD-L1, CD4, CD8, CD25, FOXP3 and Ki67. Fluorescence Images were acquired on the Vectra platform (Perkin Elmer) and analyzed with novel AQUA algorithms designed to accurately measure the co-localization of PD-1 and PD-L1 (the Interaction Score), regulatory (CD25+/FOXP3+) and activated (Ki67+) T cell subsets. Results: High PD-1/PD-L1 Interaction Scores (≥ 643) and regulatory T cell burden (≥ 1%) in pre-treatment tumors exhibited significant correlations with improved recurrence free (p = 0.003) and overall survival (p = 0.004) in patients receiving ACT after surgery, whereas no difference in survival was observed for patients who received surgery alone (p > 0.5). Median RFS was not reached in signature positive patients vs 93.2 months in signature negative patients. Interestingly, the levels of PD-1 or PD-L1 alone did not predict survival for surgery + ACT or surgery alone patient populations. Conclusions: PD-1/PD-L1 Interaction Score and CD25/FOXP3 positive T cells are predictive of benefit from ACT in patients with ES-NSCLC. Future studies will determine if these biomarker signatures can be used to select patients that may be spared chemotherapy without compromising outcome.
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15) , e24314
Combination of CT derived radiomic features and lymphovascular invasion status to predict disease recurrence following trimodality therapy in non-small cell lung cancer.
E24314 Background: Currently there are no clinically validated biomarkers to identify which locally advanced non-small cell lung cancer (NSCLC) patients (pts) will benefit from trimodality therapy (i.e. neoadjuvant chemoradiation (NAT) followed by surgery, TMT). In this study, we evaluate radiomic (i.e. computer extracted imaging) features of tumor phenotype as potential predictors of disease recurrence following TMT. Methods: 123 pts with stage III NSCLC treated with TMT were included. Of these, 33 pts with either distant metastasis at presentation and/or those without baseline pre-NAT CT scans were excluded. Lung tumors were retrospectively annotated by an expert reader. 1542 radiomic features (textural and shape) were extracted from intra and peritumoral regions. multivariate Cox regression analysis was performed to evaluate radiomic and clinico-pathologic factors predictive of recurrence post-surgery. Results: Pathological response was achieved in 36 (40%) pts and the rest 54 (60%) were labeled non-responders. 90 pts were randomly allocated to equally sized (n = 45) training and validation sets. The recurrence rate after surgery was 42.2% (n = 38) and the mean duration of recurrence was 20.28 ± 16.43 months. Multivariate Cox regression model revealed that a combination of two radiomic features (intratumoral and peritumoral Laplacian Laws features that capture micro-gradients and patterns of heterogeneous enhancement) from a baseline non-contrast CT scan as well as lymphovascular invasion (LVI) signature status was predictive of time to recurrence after TMT (p-value = 0.0283, 0.0129, 0.0454 respectively). Three-fold cross validation was used for training a Support Vector Machine (SVM) classifier with three features on the training set and subsequently evaluated on the validation set. The classifier successfully distinguished pts based on time to recurrence post-TMT, which was statistically significant (log-rank test, p-value < 0.014). Conclusions: Combination of LVI status and texture features extracted from within and around the tumor on baseline CT images was predictive of disease recurrence in NSCLC pts treated with TMT.
- 20 May 2018
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 36 (15) , e24314
Combination of CT derived radiomic features and lymphovascular invasion status to predict disease recurrence following trimodality therapy in non-small cell lung cancer.
E24314 Background: Currently there are no clinically validated biomarkers to identify which locally advanced non-small cell lung cancer (NSCLC) patients (pts) will benefit from trimodality therapy (i.e. neoadjuvant chemoradiation (NAT) followed by surgery, TMT). In this study, we evaluate radiomic (i.e. computer extracted imaging) features of tumor phenotype as potential predictors of disease recurrence following TMT. Methods: 123 pts with stage III NSCLC treated with TMT were included. Of these, 33 pts with either distant metastasis at presentation and/or those without baseline pre-NAT CT scans were excluded. Lung tumors were retrospectively annotated by an expert reader. 1542 radiomic features (textural and shape) were extracted from intra and peritumoral regions. multivariate Cox regression analysis was performed to evaluate radiomic and clinico-pathologic factors predictive of recurrence post-surgery. Results: Pathological response was achieved in 36 (40%) pts and the rest 54 (60%) were labeled non-responders. 90 pts were randomly allocated to equally sized (n = 45) training and validation sets. The recurrence rate after surgery was 42.2% (n = 38) and the mean duration of recurrence was 20.28 ± 16.43 months. Multivariate Cox regression model revealed that a combination of two radiomic features (intratumoral and peritumoral Laplacian Laws features that capture micro-gradients and patterns of heterogeneous enhancement) from a baseline non-contrast CT scan as well as lymphovascular invasion (LVI) signature status was predictive of time to recurrence after TMT (p-value = 0.0283, 0.0129, 0.0454 respectively). Three-fold cross validation was used for training a Support Vector Machine (SVM) classifier with three features on the training set and subsequently evaluated on the validation set. The classifier successfully distinguished pts based on time to recurrence post-TMT, which was statistically significant (log-rank test, p-value < 0.014). Conclusions: Combination of LVI status and texture features extracted from within and around the tumor on baseline CT images was predictive of disease recurrence in NSCLC pts treated with TMT.