Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Apr;9(4):e001752.
doi: 10.1136/jitc-2020-001752.

Radiomics analysis for predicting pembrolizumab response in patients with advanced rare cancers

Rivka R Colen  1   2 , Christian Rolfo  3 , Murat Ak  4   2 , Mira Ayoub  4   2 , Sara Ahmed  5 , Nabil Elshafeey  6 , Priyadarshini Mamindla  2 , Pascal O Zinn  7 , Chaan Ng  8 , Raghu Vikram  8 , Spyridon Bakas  9 , Christine B Peterson  10 , Jordi Rodon Ahnert  11 , Vivek Subbiah  11 , Daniel D Karp  11 , Bettzy Stephen  11 , Joud Hajjar  12   13 , Aung Naing  14
Affiliations

Radiomics analysis for predicting pembrolizumab response in patients with advanced rare cancers

Rivka R Colen et al. J Immunother Cancer. 2021 Apr.

Abstract

Background: We present a radiomics-based model for predicting response to pembrolizumab in patients with advanced rare cancers.

Methods: The study included 57 patients with advanced rare cancers who were enrolled in our phase II clinical trial of pembrolizumab. Tumor response was evaluated using Response Evaluation Criteria in Solid Tumors (RECIST) 1.1 and immune-related RECIST (irRECIST). Patients were categorized as 20 "controlled disease" (stable disease, partial response, or complete response) or 37 progressive disease). We used 3D-slicer to segment target lesions on standard-of-care, pretreatment contrast enhanced CT scans. We extracted 610 features (10 histogram-based features and 600 second-order texture features) from each volume of interest. Least absolute shrinkage and selection operator logistic regression was used to detect the most discriminatory features. Selected features were used to create a classification model, using XGBoost, for the prediction of tumor response to pembrolizumab. Leave-one-out cross-validation was performed to assess model performance.

Findings: The 10 most relevant radiomics features were selected; XGBoost-based classification successfully differentiated between controlled disease (complete response, partial response, stable disease) and progressive disease with high accuracy, sensitivity, and specificity in patients assessed by RECIST (94.7%, 97.3%, and 90%, respectively; p<0.001) and in patients assessed by irRECIST (94.7%, 93.9%, and 95.8%, respectively; p<0.001). Additionally, the common features of the RECIST and irRECIST groups also highly predicted pembrolizumab response with accuracy, sensitivity, specificity, and p value of 94.7%, 97%, 90%, p<0.001% and 96%, 96%, 95%, p<0.001, respectively.

Conclusion: Our radiomics-based signature identified imaging differences that predicted pembrolizumab response in patients with advanced rare cancer.

Interpretation: Our radiomics-based signature identified imaging differences that predicted pembrolizumab response in patients with advanced rare cancer.

Keywords: immunotherapy.

PubMed Disclaimer

Conflict of interest statement

Competing interests: CN reports grant support and personal fees from General Electric Healthcare, outside the submitted work. SB reports grant support from National Institutes of Health, outside the submitted work. JRA reports personal fees from Novartis, Eli Lilly, Orion Pharmaceuticals, Servier Pharma, Peptomyc, and Merck Sharpe, on the advisory board for Novartis, Eli Lilly, Orion Pharmaceuticals, Servier Pharma, Peptomyc, Merck Sharpe & Dome, Kelun Pharma/Klus Pharma, Pfizer, Roche Pharma, and Elipses Pharma, research funding from Bayer, Novartis, Spectrum Pharmaceuticals, Tocagen, Symphogen, BioAtla, Pfizer, GenMab, CytomX, KELUN-BIOTECH, Takeda-Millenium, GLAXOSMITHKLINE, Ipsen, from null, outside the submitted work. VS reports clinical trial research funding from Novartis, Bayer, GlaxoSmithKline, Nanocarrier, Vegenics, Celgene, Northwest Biotherapeutics, Berghealth, Incyte, Fujifilm, Pharmamar, D3, Pfizer, Multivir, Amgen, Abbvie, Alfa-sigma, Agensys, Boston Biomedical, Idera Pharma, Inhibrx, Exelixis, Blueprint medicines, Loxo oncology, Takeda and Roche/ Genentech, National Comprehensive Cancer Network, NCI-CTEP and UT MD Anderson Cancer Center, outside the submitted work. JH reports grants from Immune Deficiency Foundation, Jeffery Modell Foundatoin and Chao Physician-Scientist, and Baxalta, and has served as an advisory board member for Takeda, CSL Behring, and Horizn Pharma outside the submitted work. AN reports research support and non-financial support from Merck Sharp & Dohme Corp., grants from NCI/NIH, research support from The University of Texas MD Anderson Cancer Center, during the conduct of the study; grants from NCI, research support from EMD Serono, MedImmune, Healios Onc. Nutrition, Atterocor, Amplimmune, ARMO BioSciences, Karyopharm Therapeutics, Incyte, Novartis, Regeneron, Merck, Bristol Myers Squibb, Pfizer, CytomX Therapeutics, Neon Therapeutics, Calithera BioSciences, TopAlliance BioSciences, Eli Lilly, Kymab, PsiOxus, Arcus Biosciences, NeoImmuneTech, ImmuneOncia, and Surface Oncology, non-financial support for travel and accommodation from ARMO BioSciences, and has served as an advisory board member for Novartis, CytomX Therapeutics, Genome and Company, STCube Pharmaceuticals, OncoSec KEYNOTE-695, and Kymab outside the submitted work. RRC, CR, MAk, MAyoub, SA, NE, PM, POZ, RV, CP, BS, DDK declare no competing interests.

Figures

Figure 1
Figure 1
Radiomic pipeline for advanced rare tumor.
Figure 2
Figure 2
(A) Receiver operating characteristic (ROC) curve representing the performance of the predictive model when using the top 10 least absolute shrinkage and selection operator (LASSO) features in the Response Evaluation Criteria in Solid Tumors (RECIST) group. (B) ROC curve representing the performance of the predictive model when using the top 10 LASSO features in the immune-related RECIST group.
Figure 3
Figure 3
(A) Receiver operating characteristic (ROC) curve representing the performance of the predictive model when using the common 15 least absolute shrinkage and selection operator (LASSO) features in the Response Evaluation Criteria in Solid Tumors (RECIST) group. (B) Fifteen common LASSO features between 44 features and 56 features obtained from 57 patients assessed by RECIST and immune-related RECIST (irRECIST), respectively. (C) ROC curve representing the performance of the predictive model when using the common 15 LASSO features in the irRECIST group.
Figure 4
Figure 4
(A) The Kaplan-Meier curves for overall survival (OS) with radiomic texture features from Response Evaluation Criteria in Solid Tumors (RECIST) model. (B) The Kaplan-Meier curves for OS with radiomic texture features from immune-related RECIST model.
See this image and copyright information in PMC

Comment in

References

    1. Bogaerts J, Sydes MR, Keat N, et al. . Clinical trial designs for rare diseases: studies developed and discussed by the International rare cancers initiative. Eur J Cancer 2015;51:271–81. 10.1016/j.ejca.2014.10.027 - DOI - PMC - PubMed
    1. Greenlee RT, Goodman MT, Lynch CF, et al. . The occurrence of rare cancers in U.S. adults, 1995-2004. Public Health Rep 2010;125:28–43. 10.1177/003335491012500106 - DOI - PMC - PubMed
    1. Institute NC . Cancer STAT facts. Surveilance, epidemiology, and end results program, 2020. Available: https://seercancergov/statfacts/
    1. Komatsubara KM, Carvajal RD. The promise and challenges of rare cancer research. Lancet Oncol 2016;17:136–8. 10.1016/S1470-2045(15)00485-4 - DOI - PubMed
    1. Ansell SM, Lesokhin AM, Borrello I, et al. . PD-1 blockade with nivolumab in relapsed or refractory Hodgkin's lymphoma. N Engl J Med 2015;372:311–9. 10.1056/NEJMoa1411087 - DOI - PMC - PubMed

Publication types

MeSH terms

Substances