Abstract 2534
Background
Radiomic signatures offer the potential to enhance clinical decision-making as on-treatment markers of efficacy to assess which patients (pts) should continue treatment. Using treatment-related radiomic signatures via quantitative, artificial intelligence (AI)-based analysis of computed tomography (CT) images, we evaluated early tumor changes in pts with sqNSCLC treated in 2 treatment groups: nivolumab (group A) or docetaxel (group B).
Methods
Data from pts with sqNSCLC were collected prospectively and analyzed retrospectively across 2 multicenter clinical trials (A, n = 92 CheckMate 017 [NCT01642004], CheckMate 063 [NCT01721759]; B, n = 50 CheckMate 017). For the current study, pts with a measurable lung lesion and baseline and on-treatment assessments (8 weeks) were randomized to training (T) or validation (V) datasets (A: 72T, 20V; B: 32T, 18V;). For each pt, the largest measurable lung tumor was segmented to extract 1,749 radiomic features. Pts were classified as treatment-sensitive or -resistant using median progression-free survival (PFS) calculated from pts included in this study (A, B). Using AI-based methodologies, up to 4 features were selected and combined to develop a signature score (range, 0-1) in the T datasets and applied to each pt in the V datasets to classify sensitivity to treatment.
Results
The radiomics features associated with treatment sensitivity in the T datasets were a decrease in tumor volume (A, B), infiltration of tumor boundaries (A), or tumor spatial heterogeneity (A). The radiomic signatures predicted treatment sensitivity in the V dataset of each study group (AUC [95% CI]: A, 0.77 [0.55-1.00]; B, 0.67 [0.37-0.96]).
Conclusions
AI-based CT imaging detected early changes in radiomic features from baseline to first on-treatment tumor assessment—decrease in tumor volume, tumor heterogeneity, and tumor infiltrativeness along boundaries—that were associated with sensitivity to treatment in pts with sqNSCLC, offering an approach that could guide clinical decision-making to continue or modify systemic therapies.
Clinical trial identification
CheckMate 017 [NCT01642004] July 17, 2012 (first posted date) CheckMate 063 [NCT01721759] November 6, 2012 (first posted date).
Editorial acknowledgement
Legal entity responsible for the study
Bristol-Myers Squibb and Columbia University Medical Center.
Funding
Bristol-Myers Squibb.
Disclosure
M. Fronheiser: Shareholder / Stockholder / Stock options, Full / Part-time employment: Bristol-Myers Squibb. S. Du: Shareholder / Stockholder / Stock options, Full / Part-time employment: Bristol-Myers Squibb. W. Hayes: Shareholder / Stockholder / Stock options, Full / Part-time employment: Bristol-Myers Squibb. D.K. Leung: Shareholder / Stockholder / Stock options, Full / Part-time employment: Bristol-Myers Squibb. A. Roy: Shareholder / Stockholder / Stock options, Full / Part-time employment: Bristol-Myers Squibb. L.H. Schwartz: Research grant / Funding (self), Member DSMB: Merck; Research grant / Funding (self), Member DSMB: Novartis; Research grant / Funding (self), Consultant endpoint analysis: Boehringer Ingelheim. All other authors have declared no conflicts of interest.
Resources from the same session
5517 - Molecular fingerprinting in breast cancer (BC) screening using Quantum Optics (QO) technology combined with an artificial intelligence (AI) approach applying the concept of “molecular profiles at n variables (MPnV)”: a prospective pilot study.
Presenter: Jean-Marc Nabholtz
Session: Poster Display session 3
Resources:
Abstract
2152 - Inferring the correlation between incidence rates of melanoma and the average tumor-specific epitope binding ability of HLA class I molecules in different populations
Presenter: Istvan Miklos
Session: Poster Display session 3
Resources:
Abstract
4382 - Thermal Liquid Biopsy as a Valuable Tool in Lung Cancer Screening Programs
Presenter: Alberto Rodrigo
Session: Poster Display session 3
Resources:
Abstract
2465 - Towards a screening test for cancer by circulating DNA analysis
Presenter: Rita Tanos
Session: Poster Display session 3
Resources:
Abstract
3788 - Evaluation of a successful launch of the MammaPrint and BluePrint NGS kit
Presenter: Leonie Delahaye
Session: Poster Display session 3
Resources:
Abstract
3863 - Analysis of prognostic factors on overall survival in elderly women treated for early breast cancer using data mining and machine learning
Presenter: Pierre Heudel
Session: Poster Display session 3
Resources:
Abstract
1993 - Circulating tumor cell detection in epithelial ovarian cancer using dual-component antibodies targeting EpCAM and FRα
Presenter: Na Li
Session: Poster Display session 3
Resources:
Abstract
4281 - CEUS of the breast: Is it feasible in improved performance of BI-RADS evaluation of critical breast lesions?——A multi-center prospective study in China
Presenter: Jun Luo
Session: Poster Display session 3
Resources:
Abstract
2268 - Classification of abnormal findings on ring-type dedicated breast PET for detecting breast cancer
Presenter: Shinsuke Sasada
Session: Poster Display session 3
Resources:
Abstract
4035 - Prediction of benign and malignant breast masses using digital mammograms texture features
Presenter: Cui Yanhua
Session: Poster Display session 3
Resources:
Abstract