Advanced image analytics predicting clinical outcomes in patients with colorectal liver metastases: A systematic review of the literature.
Antineoplastic Combined Chemotherapy Protocols
/ therapeutic use
Colorectal Neoplasms
/ diagnostic imaging
Humans
Image Processing, Computer-Assisted
/ methods
Liver Neoplasms
/ diagnostic imaging
Neoplasm Recurrence, Local
/ diagnostic imaging
Prognosis
Survival Rate
Tomography, X-Ray Computed
/ methods
Advanced image analytics
Colorectal liver metastases
Radiomics
Journal
Surgical oncology
ISSN: 1879-3320
Titre abrégé: Surg Oncol
Pays: Netherlands
ID NLM: 9208188
Informations de publication
Date de publication:
Sep 2021
Sep 2021
Historique:
received:
12
01
2021
revised:
30
03
2021
accepted:
01
04
2021
pubmed:
19
4
2021
medline:
18
1
2022
entrez:
18
4
2021
Statut:
ppublish
Résumé
To better select patients with colorectal liver metastases (CRLM) for an optimal selection of treatment strategy (i.e. local, systemic or combined treatment) new prognostic models are warranted. In the last decade, radiomics has emerged as a field to create predictive models based on imaging features. This systematic review aims to investigate the current state and potential of radiomics to predict clinical outcomes in patients with CRLM. A comprehensive literature search was conducted in the electronic databases of PubMed, Embase, and Cochrane Library, according to PRISMA guidelines. Original studies reporting on radiomics predicting clinical outcome in patients diagnosed with CRLM were included. Clinical outcomes were defined as response to systemic treatment, recurrence of disease, and survival (overall, progression-free, disease-free). Primary outcome was the predictive performance of radiomics. A narrative synthesis of the results was made. Methodological quality was assessed using the radiomics quality score. In 11 out of 14 included studies, radiomics was predictive for response to treatment, recurrence of disease, survival, or a combination of outcomes. Combining clinical parameters and radiomic features in multivariate modelling often improved the predictive performance. Different types of individual features were found prognostic. Noticeable were the contrary levels of heterogeneous and homogeneous features in patients with good response. The methodological quality as assessed by the radiomics quality score varied considerably between studies. Radiomics appears a promising non-invasive method to predict clinical outcome and improve personalized decision-making in patients with CRLM. However, results were contradictory and difficult to compare. Standardized prospective studies are warranted to establish the added value of radiomics in patients with CRLM.
Sections du résumé
BACKGROUND
BACKGROUND
To better select patients with colorectal liver metastases (CRLM) for an optimal selection of treatment strategy (i.e. local, systemic or combined treatment) new prognostic models are warranted. In the last decade, radiomics has emerged as a field to create predictive models based on imaging features. This systematic review aims to investigate the current state and potential of radiomics to predict clinical outcomes in patients with CRLM.
METHODS
METHODS
A comprehensive literature search was conducted in the electronic databases of PubMed, Embase, and Cochrane Library, according to PRISMA guidelines. Original studies reporting on radiomics predicting clinical outcome in patients diagnosed with CRLM were included. Clinical outcomes were defined as response to systemic treatment, recurrence of disease, and survival (overall, progression-free, disease-free). Primary outcome was the predictive performance of radiomics. A narrative synthesis of the results was made. Methodological quality was assessed using the radiomics quality score.
RESULTS
RESULTS
In 11 out of 14 included studies, radiomics was predictive for response to treatment, recurrence of disease, survival, or a combination of outcomes. Combining clinical parameters and radiomic features in multivariate modelling often improved the predictive performance. Different types of individual features were found prognostic. Noticeable were the contrary levels of heterogeneous and homogeneous features in patients with good response. The methodological quality as assessed by the radiomics quality score varied considerably between studies.
CONCLUSION
CONCLUSIONS
Radiomics appears a promising non-invasive method to predict clinical outcome and improve personalized decision-making in patients with CRLM. However, results were contradictory and difficult to compare. Standardized prospective studies are warranted to establish the added value of radiomics in patients with CRLM.
Identifiants
pubmed: 33866191
pii: S0960-7404(21)00067-0
doi: 10.1016/j.suronc.2021.101578
pii:
doi:
Types de publication
Journal Article
Systematic Review
Langues
eng
Sous-ensembles de citation
IM
Pagination
101578Informations de copyright
Copyright © 2021 The Authors. Published by Elsevier Ltd.. All rights reserved.