Het voorspellen van de reactie op immunotherapie door middel van kunstmatige intelligentie

VILLEJUIF, France–(BUSINESS WIRE)– Een studie, gepubliceerd in The Lancet Oncology, stelt voor het eerst vast dat kunstmatige intelligentie medische beelden kan verwerken om biologische en klinische informatie te geven. Medische onderzoekers van Gustave Roussy, CentraleSupélec, Inserm, de Parijs-Sud Universiteit en TheraPanacea (spin-off van CentraleSupélec, gespecialiseerd in kunstmatige intelligentie in oncologie-straling en precisiegeneeskunde) hebben door het ontwerpen van een algoritme en de ontwikkeling ervan voor de analyse van CT-scanbeelden een zogenaamde radiomische signatuur gecreëerd. Deze signatuur definieert het niveau van lymfocytinfiltratie van een tumor en geeft een voorspelling van de effectiviteit van immunotherapie bij de patiënt. In de toekomst kunnen artsen deze beeldvorming gebruiken om biologische fenomenen te identificeren in een tumor die zich ergens in het lichaam begeeft zonder dat dit biopsie nodig is.

Tot nu toe kan geen enkele marker nauwkeurig de patiënten identificeren die reageren op anti-PD-1/PD-L1 immunotherapie in een situatie waar slechts 15 tot 30% van de patiënten reageren op een dergelijke behandeling. Het is bekend dat hoe rijker de tumoromgeving immunologisch is (aanwezigheid van lymfocyten) hoe groter de kans is dat immunotherapie effectief zal zijn, dus de onderzoekers hebben geprobeerd deze omgeving te karakteriseren met behulp van beeldvorming en dit te correleren met de klinische respons van de patiënt. Dat is de doelstelling van de radiomische signatuur ontworpen en gevalideerd in de studie, gepubliceerd in The Lancet Oncology.

Predicting the Response to Immunotherapy Using Artificial Intelligence

VILLEJUIF, France–(BUSINESS WIRE)– A study published in The Lancet Oncology establishes for the first time that artificial intelligence can process medical images to extract biological and clinical information. By designing an algorithm and developing it to analyse CT scan images, medical researchers at Gustave Roussy, CentraleSupélec, Inserm, Paris-Sud University and TheraPanacea (spin-off from CentraleSupélec specialising in artificial intelligence in oncology-radiotherapy and precision medicine) have created a so-called radiomic signature. This signature defines the level of lymphocyte infiltration of a tumour and provides a predictive score for the efficacy of immunotherapy in the patient.
In the future, physicians might thus be able to use imaging to identify biological phenomena in a tumour located in any part of the body without having to perform a biopsy.

Up to now, no marker can accurately identify those patients who will respond to anti-PD-1/PD-L1 immunotherapy in a situation where only 15 to 30% of patients do respond to such treatment. It is known that the richer the tumour environment is immunologically (presence of lymphocytes) the greater the chance that immunotherapy will be effective, so the researchers have tried to characterise this environment using imaging and correlate this with the patients’ clinical response. Such is the objective of the radiomic signature designed and validated in the study published in The Lancet Oncology.

In this retrospective study, the radiomic signature was captured, developed and validated in 500 patients with solid tumours (all sites) from four independent cohorts. It was validated genomically, histologically and clinically, making it particularly robust.

Using an approach based on machine learning, the team first taught the algorithm to use relevant information extracted from CT scans of patients participating in the MOSCATO study¹, which also held tumor genome data. Thus, based solely on images, the algorithm learned to predict what the genome might have revealed about the tumour immune infiltrate, in particular with respect to the presence of cytotoxic T-lymphocytes (CD8) in the tumour, and it established a radiomic signature.

This signature was tested and validated in other cohorts including that of TCGA (The Cancer Genome Atlas) thus showing that imaging could predict a biological phenomenon, providing an estimation of the degree of immune infiltration of a tumour.

Then, to test the applicability of this signature in a real situation and correlate it to the efficacy of immunotherapy, it was evaluated using CT scans performed before the start of treatment in patients participating in 5 phase I trials of anti-PD-1/PD-L1 immunotherapy. It was found that the patients in whom immunotherapy was effective at 3 and 6 months had higher radiomic scores as did those with better overall survival.

The next clinical study will assess the signature both retrospectively and prospectively, will use larger numbers of patients and will stratify them according to cancer type in order to refine the signature.

This will also employ more sophisticated automatic learning and artificial intelligence algorithms to predict patient response to immunotherapy. To that end, the researchers are intending to integrate data from imaging, molecular biology and tissue analysis. This is the objective of the collaboration between Gustave Roussy, Inserm, Université Paris-Sud, CentraleSupélec and TheraPanacea to identify those patients who are the most likely to respond to treatment, thus improving the efficacy/cost ratio of the treatment.

// About radiomics
In radiomics, it is considered that imaging (CT, MRI, ultrasound, etc.) not only reveals the organisation and architecture of tissues but also their molecular or cellular composition. The technique involves the use of algorithms to analyse a medical image objectively in order to extract from it information which is invisible to the naked eye, such as the texture of a tumour, its micro-environment, its heterogeneity, etc. For the patient this represents a non-invasive approach that can be repeated over the course of the disease to follow its progress.

Lancet Oncology
http://www.thelancet.com/journals/lanonc/article/PIIS1470-2045(18)30413-3/fulltext
DOI : 10.1016/S1470-2045(18)30413-3

¹ Results of the MOSCATO study published in Cancer Discovery : http://cancerdiscovery.aacrjournals.org/content/early/2017/03/26/2159-8290.CD-16-1396

View source version on businesswire.com: https://www.businesswire.com/news/home/20180824005293/en/

Contacts

PRESS
GUSTAVE ROUSSY
Claire Parisel, 33.1.42.11.50.59
claire.parisel@gustaveroussy.fr
or
Inserm
Priscille Riviere, 33 1.44.23.60.97
presse@inserm.fr
or
CentraleSupélec
Laurence Wendling, 33 1.75.31.61.15
Laurence.wendling@centralesupelec.fr
or
TheraPanacea
Catherine Martineau-Huynh, 33 6.47.93.51.65
c.huynh@therapanacea.eu
or
Université Paris-Sud
Cécile Pérol, Tél. 33 1 69.15.41.99
cecile.perol@u-psud.fr

 

Check out our twitter: @NewsNovumpr