- Anton Berns (Amsterdam, Netherlands)
- Fatima Cardoso (Lisbon, Portugal)
Session DOI (ID 7317)
1176O - Artificial intelligence combining radiomics and clinical data for predicting response to immunotherapy (ID 5475)
- Marta Ligero (Barcelona, Spain)
Abstract
Background
There are currently no good indicators of which patients with cancer will respond or not to immunotherapy. Novel computational analysis of computed tomography scans (CT) (i.e. radiomics) provides information about the tumour-infiltrating CD8 and predict response to immunotherapy. We aim to validate in an external cohort the VHIO CT-radiomics signature and to develop a combined radiomics-clinical signature that predicts the response to immune checkpoint inhibitors in patients with advanced solid tumours.
Methods
The VHIO CT-radiomics signature was developed in a population of 115 consecutive patients treated with immune checkpoint inhibitors (programmed-death protein 1 [PD-1] or programmed-death ligand 1 [PD-L1] inhibitors) monotherapy in phase I clinical trials (Cohort 1). The external validation included 62 consecutive patients with urinary bladder cancer treated with anti-PD-1 or PD-L1 monotherapy (Cohort 2). From the baseline CT, a target lesion per patient was delineated. Radiomics variables of first-order, shape, and texture were extracted. An elastic-net model combining radiomics and clinical features was implemented. The association between the radiomics score and changes in tumour shrinkage was assessed using Mann-Whitney analysis.
Results
In the Cohort 1 the CT-radiomics signature associates with response (area under the curve [AUC] of 0.81, p-value=2.74x10-5 and 0.72, p = 0.001 in the training and internal validation sets, respectively). In the external validation set (Cohort 2), the CT-radiomics signature predicts a response with an AUC of and 0.76 (p = 0.001). The model combining radiomics and clinical features has an AUC of 0.84 (p-value=5.04x10-9) for response prediction. Tumour homogeneity, hypodensity and spherical shape together with high lymphocytes and albumin and low neutrophils, corresponding to a high clinical-radiomics signature score, are indicators of tumour response. A higher CT-radiomics signature score is associated with a larger tumour shrinkage (p < 0.05).
Conclusions
CT-radiomics signature at baseline predicts the response to immune checkpoint inhibitors. Integrating radiomics and clinical data improved the response prediction capacity.
Legal entity responsible for the study
The authors.
Funding
This study was supported by the Banco Bilbao Vizcaya Argentaria and Fundacio La Caixa. RPL is supported by a Prostate Cancer Foundation Young Investigator award.
Disclosure
J. Martín Liberal: Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Roche; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Novartis; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: MSD; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Pfizer; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Ipsen; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Pierre Fabre; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Astellas; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Bristol-Myers Squibb. R. Morales Barrera: Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Sanofi Aventis; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Bayer; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Janssen; Advisory / Consultancy, Speaker Bureau / Expert testimony: AstraZeneca; Advisory / Consultancy, Speaker Bureau / Expert testimony, Travel / Accommodation / Expenses: Merck Sharp & Dohme; Advisory / Consultancy, Speaker Bureau / Expert testimony: Asofarm; Travel / Accommodation / Expenses: Roche; Travel / Accommodation / Expenses: Astellas; Travel / Accommodation / Expenses: Pharmacyclics; Travel / Accommodation / Expenses: Clovis Oncology; Travel / Accommodation / Expenses: Lilly. E. Elez: Travel / Accommodation / Expenses: Merck; Travel / Accommodation / Expenses: Sanofi; Travel / Accommodation / Expenses: Roche; Travel / Accommodation / Expenses: Servier and Amge ; Research grant / Funding (self): Merck. E. Felip: Honoraria (self): AbbVie; Honoraria (self): AstraZeneca; Honoraria (self): Blue Print Medicines; Honoraria (self): Boehringer Ingelheim; Honoraria (self): Bristol-Myers Squibb; Honoraria (self): Celgene; Honoraria (self): Eli Lilly; Honoraria (self): Guardant Health; Honoraria (self): Janssen; Honoraria (self): Medscape; Honoraria (self): Merck KGaA; Honoraria (self): MSD; Honoraria (self): Novartis; Honoraria (self): Pfizer; Honoraria (self): Takeda; Honoraria (self): Touchtime. J. Tabernero: Advisory / Consultancy: Array Biopharma; Advisory / Consultancy: AstraZeneca; Advisory / Consultancy: Bayer; Advisory / Consultancy: BeiGene; Advisory / Consultancy: Boehringer Ingelheim; Advisory / Consultancy: Chugai; Advisory / Consultancy: Genentech, Inc; Advisory / Consultancy: Genmab A/S; Advisory / Consultancy: Halozyme; Advisory / Consultancy: Imugene Limited; Advisory / Consultancy: Inflection Biosciences Limited; Advisory / Consultancy: Ipsen; Advisory / Consultancy: Kura Oncology; Advisory / Consultancy: Lilly; Advisory / Consultancy: MSD; Advisory / Consultancy: Menarini; Advisory / Consultancy: Merck Serono; Advisory / Consultancy: Merus; Advisory / Consultancy: Molecular Partners; Advisory / Consultancy: Novartis; Advisory / Consultancy: Peptomyc; Advisory / Consultancy: Pfizer; Advisory / Consultancy: Pharmacyclics; Advisory / Consultancy: ProteoDesign SL; Advisory / Consultancy: F. Hoffmann-La Roche Ltd; Advisory / Consultancy: Sanofi; Advisory / Consultancy: SeaGen; Advisory / Consultancy: Seattle Genetics; Advisory / Consultancy: Servier; Advisory / Consultancy: Symphogen; Advisory / Consultancy: Taiho; Advisory / Consultancy: VCN Biosciences; Advisory / Consultancy: Biocartis; Advisory / Consultancy: Foundation Medicine; Advisory / Consultancy: HalioDX SAS. R. Dienstmann: Advisory / Consultancy, Speaker Bureau / Expert testimony: Roche; Speaker Bureau / Expert testimony: Symphogen; Speaker Bureau / Expert testimony: Ipsen; Speaker Bureau / Expert testimony: Amgen; Speaker Bureau / Expert testimony: Sanofi; Speaker Bureau / Expert testimony: MSD; Speaker Bureau / Expert testimony: Servier; Research grant / Funding (self): Merck. All other authors have declared no conflicts of interest.
176O - Machine learning-assisted prognostication based on genomic expression in the tumour microenvironment of estrogen receptor positive and HER2 negative breast cancer (ID 4387)
- Yara Abdou (Buffalo, United States of America)
Abstract
Background
Stroma in the tumor microenvironment (TME) is known to impact prognosis and responses to therapy. Few mathematical models exist to prognosticate patients (pts), based on mRNA expressivity in the TME.
Methods
Clinical outcomes data and mRNA-seq of 246 pts with stage 2 estrogen receptor (ER) positive (+) and HER2 negative (-) breast cancer were obtained from TCGA. 26 gene groups composed of 191 genes* enriched in cellular and non-cellular elements of TME, mutational burden (MB), and clinical data were analyzed by Kaplan-Meier (KM) analysis and multivariate nonlinear regression assisted by machine learning to achieve confined optimization with model-data minimization among multiple distribution functions. *Due to character limit, more details about these genes will be shown at actual presentation.
Results
Prognostication was modeled with higher risk score (RS) representing worse prognosis in stage 2 ER+HER2- breast cancer. Six genes (C15orf53, PDGFB, IL10, HS3ST2, GPNMB, PADI4) and seven genes (FCRL3, IFNGR2, ICAM2, CXCR4, HLA-DMB, LGMN, ICOSLG) out of 191 genes associated with poor prognosis were identified (p < 0.05 and 0.05<p<0.1, respectively). Genomic expression of the six and seven gene groups were labeled as P1 and P2, respectively. RS = -0.173 + 0.151 × (Age at diagnosis0.334) + 0.080 × (P10.528) + 0.156 × (P2-0.116). Based on RS, pts were clustered into 2 groups; high and low RS groups, showing two KM curves with P < 0.001, HR = 3.762 (95% CI 2.914 – 4.939), confirming the validity of RS modeling. Analysis of immune profiles in high and low RS groups shows that expression of genes associated with immunosuppressive factors, T-helper 2 cells, macrophages, neutrophils, co-inhibitory factors of T-cells, and antigen presenting cells are higher in high RS group (p < 0.05). MB did not contribute to survival.
Conclusions
Machine learning-assisted mathematical modeling of RS and gene analysis identified TME-related genes and gene groups that are strongly associated with worse prognosis in stage 2 ER+HER2- breast cancer. RS could potentially prognosticate pts in the clinic with available genomic profiles.
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Invited Discussant: The perspective of the mathematician (ID 7294)
- Nikos Paragios (Gif sur Yvette, France)
Invited Discussant: The impact for the clinician (ID 7295)
- Christos Sotiriou (Brussels, Belgium)
Interpretable deep-learning to improve mesothelioma prognosis (ID 7296)
- Giles Wainrib (Paris, France)