Abstract
Original language | English |
---|---|
Pages (from-to) | 99-122 |
Number of pages | 24 |
Journal | Information Fusion |
Volume | 82 |
DOIs | |
Publication status | Published - 1 Jun 2022 |
Keywords
- Information fusion
- data harmonisation
- data standardisation
- domain adaptation
- reproducibility
- DIFFUSION MRI DATA
- COLOR NORMALIZATION
- RADIOMIC FEATURES
- UNWANTED VARIATION
- GENE-EXPRESSION
- SCANNER
- REPRODUCIBILITY
- SEGMENTATION
- IMAGES
- COEFFICIENT
Access to Document
- 10.1016/j.inffus.2022.01.001Licence: CC BY
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver
}
In: Information Fusion, Vol. 82, 01.06.2022, p. 99-122.
Research output: Contribution to journal › (Systematic) Review article › peer-review
TY - JOUR
T1 - Data harmonisation for information fusion in digital healthcare: A state-of-the-art systematic review, meta-analysis and future research directions
AU - Nan, Y.
AU - Del Ser, J.
AU - Walsh, S.
AU - Schonlieb, C.
AU - Roberts, M.
AU - Selby, I.
AU - Howard, K.
AU - Owen, J.
AU - Neville, J.
AU - Guiot, J.
AU - Ernst, B.
AU - Pastor, A.
AU - Alberich-Bayarri, A.
AU - Menzel, M.I.
AU - Vos, W.
AU - Flerin, N.
AU - Charbonnier, J.P.
AU - van Rikxoort, E.
AU - Chatterjee, A.
AU - Woodruff, H.
AU - Lambin, P.
AU - Cerda-Alberich, L.
AU - Marti-Bonmati, L.
AU - Herrera, F.
AU - Yang, G.
N1 - Funding Information: This study was supported in part by the European Research Council Innovative Medicines Initiative (DRAGON # , H2020-JTI-IMI2 101005122 ), the AI for Health Imaging Award (CHAIMELEON ## , H2020-SC1-FA-DTS-2019–1 952172), the UK Research and Innovation Future Leaders Fellowship ( MR/V023799/1 ), the British Heart Foundation (Project Number: TG/18/5/34111, PG/16/78/32402), the SABRE project supported by Boehringer Ingelheim Ltd, the European Union's Horizon 2020 research and innovation programme (ICOVID, 101016131), the Euskampus Foundation (COVID19 Resilience, Ref. COnfVID19), and the Basque Government (consolidated research group MATHMODE, Ref. IT1294–19, and 3KIA project from the ELKARTEK funding program, Ref. KK-2020/00049). Funding Information: This study was supported in part by the European Research Council Innovative Medicines Initiative (DRAGON#, H2020-JTI-IMI2 101005122), the AI for Health Imaging Award (CHAIMELEON##, H2020-SC1-FA-DTS-2019?1 952172), the UK Research and Innovation Future Leaders Fellowship (MR/V023799/1), the British Heart Foundation (Project Number: TG/18/5/34111, PG/16/78/32402), the SABRE project supported by Boehringer Ingelheim Ltd, the European Union's Horizon 2020 research and innovation programme (ICOVID, 101016131), the Euskampus Foundation (COVID19 Resilience, Ref. COnfVID19), and the Basque Government (consolidated research group MATHMODE, Ref. IT1294?19, and 3KIA project from the ELKARTEK funding program, Ref. KK-2020/00049). # DRAGON Consortium:, Xiaodan Xinga, Ming Lia, Scott Wagersb, Rebecca Bakerc, Cosimo Nardid, Brice van Eeckhoute, Paul Skippf, Pippa Powellg, Miles Carrollh, Alessandro Ruggieroi, Muhunthan Thillaii, Judith Babari, Evis Salai, William Murchj, Julian Hiscoxk, Diana Barallel, Nicola Sverzellatim, ## CHAIMELEON Consortium:, Ana Miguel Blancon, Fuensanta Bellv?s Batallero, Mario Aznarp, Amelia Suarezp, Sergio Figueirasq, Katharina Krischakr, Monika Hierathr, Yisroel Mirskys, Yuval Elovicis, Jean Paul Beregit, Laure Fourniert, Francesco Sardanelliu, Tobias Penzkoferv, Karine Seymourw, Nacho Blanquerx, Emanuele Neriy, Andrea Laghiz, Manuela Fran?aaa, Ricard Martinezab, a National Heart and Lung Institute, Imperial College London, London, UK, b BioSci Consulting, Maasmechelen, Belgium, c Clinical Data Interchange Standards Consortium, Austin, Texas, United States, d University of Florence, Firenze, Italy, e Medical Cloud Company, Li?ge, Belgium, f TopMD, Southampton, UK, g European Lung Foundation, Sheffield, UK, h Department of Health, Public Health England, London, UK, i Department of Radiology, University of Cambridge, Cambridge, UK, j Owlstone Medical, Cambridge, UK, k University of Liverpool, Liverpool, UK, l University of Southampton, Southampton, UK, m University of Parma, Parma, Italy, n Medical Imaging Department, Hospital Universitari i Polit?cnic La Fe, Valencia, Spain, o QUIBIM, Valencia, Spain, p Matical Innovation, Madrid, Spain, q Bah?a Software, A Coru?a, Spain, r European Institute for Biomedical Imaging Research, Vienna, Austria, s Ben Gurion University of the Negev, Be'er Sheva, Israel, t Le Coll?ge des Enseignants en Radiologie de France, France, u Research Hospital Policlinico San Donato, Milan, Italy, v Charit? ? Universit?tsmedizin Berlin, Berlin, Germany, w Medexprim, Lab?ge, France, x Valencia Polytechnic University, Valencia, Spain, y University of Pisa, Pisa, Italy, z Sapienza University of Rome, Rome, Italy, aa The Centro Hospitalar Universit?rio do Porto, Portugal, ab University of Valencia, Valencia, Spain Publisher Copyright: © 2022 The Author(s)
PY - 2022/6/1
Y1 - 2022/6/1
N2 - Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.
AB - Removing the bias and variance of multicentre data has always been a challenge in large scale digital healthcare studies, which requires the ability to integrate clinical features extracted from data acquired by different scanners and protocols to improve stability and robustness. Previous studies have described various computational approaches to fuse single modality multicentre datasets. However, these surveys rarely focused on evaluation metrics and lacked a checklist for computational data harmonisation studies. In this systematic review, we summarise the computational data harmonisation approaches for multi-modality data in the digital healthcare field, including harmonisation strategies and evaluation metrics based on different theories. In addition, a comprehensive checklist that summarises common practices for data harmonisation studies is proposed to guide researchers to report their research findings more effectively. Last but not least, flowcharts presenting possible ways for methodology and metric selection are proposed and the limitations of different methods have been surveyed for future research.
KW - Information fusion
KW - data harmonisation
KW - data standardisation
KW - domain adaptation
KW - reproducibility
KW - DIFFUSION MRI DATA
KW - COLOR NORMALIZATION
KW - RADIOMIC FEATURES
KW - UNWANTED VARIATION
KW - GENE-EXPRESSION
KW - SCANNER
KW - REPRODUCIBILITY
KW - SEGMENTATION
KW - IMAGES
KW - COEFFICIENT
U2 - 10.1016/j.inffus.2022.01.001
DO - 10.1016/j.inffus.2022.01.001
M3 - (Systematic) Review article
C2 - 35664012
SN - 1566-2535
VL - 82
SP - 99
EP - 122
JO - Information Fusion
JF - Information Fusion
ER -