Scanning the horizon: towards transparent and reproducible neuroimaging research
Top Cited Papers
Open Access
- 5 January 2017
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Reviews Neuroscience
- Vol. 18 (2), 115-126
- https://doi.org/10.1038/nrn.2016.167
Abstract
There is growing concern about the reproducibility of scientific research, and neuroimaging research suffers from many features that are thought to lead to high levels of false results. Statistical power of neuroimaging studies has increased over time but remains relatively low, especially for group comparison studies. An analysis of effect sizes in the Human Connectome Project demonstrates that most functional MRI studies are not sufficiently powered to find reasonable effect sizes. Neuroimaging analysis has a high degree of flexibility in analysis methods, which can lead to inflated false-positive rates unless controlled for. Pre-registration of analysis plans and clear delineation of hypothesis-driven and exploratory research are potential solutions to this problem. The use of appropriate corrections for multiple tests has increased, but some common methods can have highly inflated false-positive rates. The use of non-parametric methods is encouraged to provide accurate correction for multiple tests. Software errors have the potential to lead to incorrect or irreproducible results. The adoption of improved software engineering methods and software testing strategies can help to reduce such problems. Reproducibility will be improved through greater transparency in methods reporting and through increased sharing of data and code.Keywords
This publication has 78 references indexed in Scilit:
- Identification of common variants associated with human hippocampal and intracranial volumesNature Genetics, 2012
- Raise standards for preclinical cancer researchNature, 2012
- Inferring Mental States from Neuroimaging Data: From Reverse Inference to Large-Scale DecodingNeuron, 2011
- Large-scale automated synthesis of human functional neuroimaging dataNature Methods, 2011
- Matching Categorical Object Representations in Inferior Temporal Cortex of Man and MonkeyNeuron, 2008
- What we can do and what we cannot do with fMRINature, 2008
- Guidelines for reporting an fMRI studyNeuroImage, 2008
- Power calculation for group fMRI studies accounting for arbitrary design and temporal autocorrelationNeuroImage, 2008
- In praise of tedious anatomyNeuroImage, 2007
- Beyond mind-reading: multi-voxel pattern analysis of fMRI dataTrends in Cognitive Sciences, 2006