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
2477 - Antecedent of cancer and mortality after the first ST segment elevation acute myocardial infarction treated with primary coronary angioplasty. A prospective cohort study
Presenter: Irene Sillero
Session: Poster Display session 3
Resources:
Abstract
1894 - Genomic characterisation of locally advanced pancreatic adenocarcinoma
Presenter: Sarah Picardo
Session: Poster Display session 3
Resources:
Abstract
3280 - Comparison of freshly prepared and frozen cells from colorectal cancer surgical samples for phenotyping experiments- a pilot study
Presenter: Sandra Mersakova
Session: Poster Display session 3
Resources:
Abstract
3419 - Hyaluronan (HA) Accumulation in the Tumor Microenvironment (TME) is Increased in Colorectal Cancer (CRC) and Associated with Consensus Molecular Subtypes (CMS) 4 Molecular Subtype
Presenter: Barbara Blouw
Session: Poster Display session 3
Resources:
Abstract
1833 - Evaluation of CT-based radiomics in patients with renal cell carcinoma
Presenter: An Zhao
Session: Poster Display session 3
Resources:
Abstract
5883 - Detection of Double Protein Expression in Diffuse Large B Cell Lymphoma
Presenter: Mohamed Gouda
Session: Poster Display session 3
Resources:
Abstract
5415 - Encyclopedic Tumor Analysis for organ agnostic treatment with Axitinib in combination regimens for advanced cancers
Presenter: Tim Crook
Session: Poster Display session 3
Resources:
Abstract
3297 - Computational model to predict response rate of clinical trials
Presenter: Orsolya Lorincz
Session: Poster Display session 3
Resources:
Abstract
4355 - Analysis of BRCA genes and homologous recombination deficiency (HRD) scores in tumours from patients (pts) with metastatic breast cancer (mBC) in the OlympiAD trial
Presenter: Mark Robson
Session: Poster Display session 3
Resources:
Abstract
2316 - A 3D co-culture platform of breast cancer and patient derived immune cells to analyse the response to chemotherapy and immunotherapies
Presenter: Diana Saraiva
Session: Poster Display session 3
Resources:
Abstract