Gargi Kothari1, James Korte2, Eric J Lehrer3, Nicholas G Zaorsky4, Smaro Lazarakis5, Tomas Kron6, Nicholas Hardcastle7, Shankar Siva8. 1. Department of Radiation Oncology, Peter MacCallum Cancer Centre, Melbourne, Australia; Sir Peter MacCallum Department of Oncology, University of Melbourne, Peter MacCallum Cancer Centre, Melbourne, Australia. Electronic address: Gargi.Kothari@petermac.org. 2. Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Australia; Department of Biomedical Engineering, School of Engineering, University of Melbourne, Melbourne, Australia. 3. Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, USA. 4. Department of Radiation Oncology, Penn State Cancer Institute, Hershey, USA; Department of Public Health Sciences, Penn State College of Medicine, Hershey, USA. 5. Health Sciences Library, Peter MacCallum Cancer Centre, Parkville, Australia. 6. Sir Peter MacCallum Department of Oncology, University of Melbourne, Peter MacCallum Cancer Centre, Melbourne, Australia; Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Australia; Centre for Medical Radiation Physics, University of Wollongong, Wollongong, Australia. 7. Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Australia; Centre for Medical Radiation Physics, University of Wollongong, Wollongong, Australia. 8. Department of Radiation Oncology, Peter MacCallum Cancer Centre, Melbourne, Australia; Sir Peter MacCallum Department of Oncology, University of Melbourne, Peter MacCallum Cancer Centre, Melbourne, Australia.
Abstract
BACKGROUND AND PURPOSE: Radiomics allows extraction of quantifiable features from imaging. This study performs a systematic review and meta-analysis of the performance of radiomics based prognostic models in non-small cell lung cancer (NSCLC). MATERIALS AND METHODS: A literature review was performed following PRISMA guidelines. Medline, EMBASE and Cochrane databases were searched for articles investigating radiomics features predictive of overall survival (OS) in NSCLC treated with curative intent radiotherapy. A random-effects meta-analysis of Harrell's Concordance Index (C-index) was performed on the performance of radiomics models. RESULTS: Of the 2746 articles retrieved, 40 studies of 55 datasets and 6223 patients were eligible for inclusion in the systematic review. There was significant heterogeneity in the methodology for feature selection and model development. Twelve datasets reported the C-index of radiomics based models in predicting OS and were included in the meta-analysis. The C-index random effects estimate was 0.57 (95% CI 0.53-0.62). There was significant heterogeneity (I2 = 70.3%). CONCLUSIONS: Based on this review, radiomics based models for lung cancer have to date demonstrated modest prognostic capabilities. Future research should consider using standardised radiomics features, robust feature selection and model development, and deep learning techniques, absolving the need for pre-defined features, to improve imaging-based models.
BACKGROUND AND PURPOSE: Radiomics allows extraction of quantifiable features from imaging. This study performs a systematic review and meta-analysis of the performance of radiomics based prognostic models in non-small cell lung cancer (NSCLC). MATERIALS AND METHODS: A literature review was performed following PRISMA guidelines. Medline, EMBASE and Cochrane databases were searched for articles investigating radiomics features predictive of overall survival (OS) in NSCLC treated with curative intent radiotherapy. A random-effects meta-analysis of Harrell's Concordance Index (C-index) was performed on the performance of radiomics models. RESULTS: Of the 2746 articles retrieved, 40 studies of 55 datasets and 6223 patients were eligible for inclusion in the systematic review. There was significant heterogeneity in the methodology for feature selection and model development. Twelve datasets reported the C-index of radiomics based models in predicting OS and were included in the meta-analysis. The C-index random effects estimate was 0.57 (95% CI 0.53-0.62). There was significant heterogeneity (I2 = 70.3%). CONCLUSIONS: Based on this review, radiomics based models for lung cancer have to date demonstrated modest prognostic capabilities. Future research should consider using standardised radiomics features, robust feature selection and model development, and deep learning techniques, absolving the need for pre-defined features, to improve imaging-based models.
Authors: Wouter A C van Amsterdam; Joost J C Verhoeff; Netanja I Harlianto; Gijs A Bartholomeus; Aahlad Manas Puli; Pim A de Jong; Tim Leiner; Anne S R van Lindert; Marinus J C Eijkemans; Rajesh Ranganath Journal: Sci Rep Date: 2022-04-07 Impact factor: 4.379