Artificial intelligence combining radiomics and clinical data for predicting response to immunotherapy

Date 28 September 2019
Event ESMO 2019 Congress
Session Proffered Paper session: Artificial intelligence and machine learning as tools for practice in oncology
Topics Imaging
Personalised/Precision Medicine
Immunotherapy
Basic Principles in the Management and Treatment (of cancer)
Therapy
Presenter Marta Ligero
Citation Annals of Oncology (2019) 30 (suppl_5): v475-v532. 10.1093/annonc/mdz253
Authors M. Ligero1, A. Garcia-Ruiz1, C. Viaplana2, M.V. Raciti1, I. Matos3, J. Martín Liberal3, C. Hierro4, M. Gonzalez5, R. Morales Barrera5, C. Suárez5, E. Elez5, I. Brana5, E. Muñoz-Couselo5, A. Oaknin3, E. Felip4, J. Tabernero5, J. Carles5, R. Dienstmann2, E. Garralda5, R. Perez Lopez1
  • 1Radiomics Group, Vall d'Hebron University Hospital - Vall d'Hebron Institute of Oncology VHIO, 08035 - Barcelona/ES
  • 2Oncology Data Science, Vall d'Hebron University Hospital, 08035 - Barcelona/ES
  • 3Department Of Medical Oncology, Vall d’Hebron University Hospital and Vall d’Hebron Institute of Oncology (VHIO), 08035 - Barcelona/ES
  • 4Oncology, Vall d’Hebron University Hospital and Vall d’Hebron Institute of Oncology (VHIO), 08001 - Barcelona/ES
  • 5Medical Oncology Dept., Vall d'Hebron University Hospital, 08035 - Barcelona/ES

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.

Clinical trial identification

Editorial acknowledgement

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.