Format

Send to

Choose Destination
Ann Oncol. 2019 Mar 21. pii: mdz108. doi: 10.1093/annonc/mdz108. [Epub ahead of print]

Predicting Response to Cancer Immunotherapy using Non-invasive Radiomic Biomarkers.

Author information

1
Department of Radiology, Netherlands Cancer Institute, Amsterdam, The Netherlands.
2
GROW School of Oncology and Developmental Biology, Maastricht, The Netherlands.
3
Departments of Radiation Oncology and Radiology, Dana Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
4
Department of Radiology, Milano-Bicocca University, San Gerardo Hospital, Monza, Italy.
5
The Francis Crick Institute & University College London, London, UK.
6
Affidea Romania, Cluj-Napoca, Romania.
7
ITAB Institute of Advanced Biomedical Technologies, University G. d'Annunzio, Chieti, Italy.
8
Department of Medical Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands.
9
Department of Surgery, Netherlands Cancer Institute, Amsterdam. The Netherlands.
10
Department of Thoracic Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands.

Abstract

INTRODUCTION:

Immunotherapy is regarded one of the major breakthroughs in cancer treatment. Despite its success, only a subset of patients responds - urging the quest for predictive biomarkers. We hypothesize that Artificial Intelligence (AI) algorithms can automatically quantify radiographic characteristics that are related to and may therefore act as non-invasive radiomic biomarkers for immunotherapy response.

PATIENTS AND METHODS:

In this study, we analyzed 1055 primary and metastatic lesions from 203 patients with advanced melanoma and non-small cell lung cancer (NSCLC) undergoing anti-PD1 therapy. We performed a AI-based characterization of each lesion on the pretreatment contrast-enhanced CT imaging data to develop and validate a non-invasive machine learning biomarker capable of distinguishing between immunotherapy responding and non-responding. To define the biological basis of the radiographic biomarker, we performed gene-set enrichment analysis in an independent dataset of 262 NSCLC patients.

RESULTS:

The biomarker reached significant performance on NSCLC lesions (up to 0.83 AUC, p < 0.001) and borderline significant for melanoma lymph nodes (0.64 AUC, p = 0.05). Combining these lesion-wide predictions on a patient level, immunotherapy response could be predicted with an AUC of up to 0.76 for both cancer types (p < 0.001), resulting in a one year survival difference of 24% (p = 0.02). We found highly significant associations with pathways involved in mitosis, indicating a relationship between increased proliferative potential and preferential response to immunotherapy.

CONCLUSIONS:

These results indicate that radiographic characteristics of lesions on standard-of-care imaging may function as non-invasive biomarkers for response to immunotherapy, and may show utility for improved patient stratification in both neoadjuvant and palliative settings.

KEYWORDS:

Artificial Intelligence; Immunotherapy; Machine Learning; Medical Imaging; Radiomics; Response Prediction

PMID:
30895304
DOI:
10.1093/annonc/mdz108

Supplemental Content

Full text links

Icon for Silverchair Information Systems
Loading ...
Support Center