N J Wesdorp1, V J van Goor2, R Kemna2, E P Jansma3, J H T M van Waesberghe4, R J Swijnenburg5, C J A Punt6, J Huiskens7, G Kazemier2. 1. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Cancer Center Amsterdam, De Boelelaan, 1117, Amsterdam, Netherlands. Electronic address: n.wesdorp@amsterdamumc.nl. 2. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Cancer Center Amsterdam, De Boelelaan, 1117, Amsterdam, Netherlands. 3. Amsterdam UMC, University of Amsterdam, Department of Epidemiology and Biostatistics, Cancer Center Amsterdam, De Boelelaan, 1117, Amsterdam, Netherlands. 4. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Radiology and Molecular Imaging, Cancer Center Amsterdam, De Boelelaan, 1117, Amsterdam, Netherlands. 5. Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Surgery, Cancer Center Amsterdam, Meibergdreef 9, Amsterdam, Netherlands. 6. Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Department of Epidemiology, Utrecht, the Netherlands. 7. SAS Institute B.V., Flevolaan 69, Huizen, the Netherlands.
Abstract
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: 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: 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: 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.
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: 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: 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: 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.
Authors: Okker D Bijlstra; Maud M E Boreel; Sietse van Mossel; Mark C Burgmans; Ellen H W Kapiteijn; Daniela E Oprea-Lager; Daphne D D Rietbergen; Floris H P van Velden; Alexander L Vahrmeijer; Rutger-Jan Swijnenburg; J Sven D Mieog; Lioe-Fee de Geus-Oei Journal: Diagnostics (Basel) Date: 2022-03-15