Abstract
Despite the wide application of the magnetic resonance imaging (MRI) technique, there are no widely used standards on naming and describing MRI sequences. The absence of consistent naming conventions presents a major challenge in automating image processing since most MRI software require a priori knowledge of the type of the MRI sequences to be processed. This issue becomes increasingly critical with the current efforts toward open-sharing of MRI data in the neuroscience community. This manuscript reports an MRI sequence detection method using imaging metadata and a supervised machine learning technique. Three datasets from the Brain Center for Ontario Data Exploration (Brain-CODE) data platform, each involving MRI data from multiple research institutes, are used to build and test our model. The preliminary results show that a random forest model can be trained to accurately identify MRI sequence types, and to recognize MRI scans that do not belong to any of the known sequence types. Therefore the proposed approach can be used to automate processing of MRI data that involves a large number of variations in sequence names, and to help standardize sequence naming in ongoing data collections. This study highlights the potential of the machine learning approaches in helping manage health data.
Highlights
Magnetic resonance imaging (MRI), as a non-invasive technology that can provide detailed images of organs and tissues in the body, has been routinely used in early detection and diagnosis of various cerebral and cardiovascular diseases (Teipel et al, 2013; Lemaître et al, 2015; Zhou et al, 2015; Abbasi and Tajeripour, 2017)
For each size of the training dataset, 20 runs were performed independently to assess the reproducibility of the machine learning procedure and the variations of the prediction accuracy
Inconsistencies in magnetic resonance imaging (MRI) sequence naming have been a known issue in the neuroscience community for a long time
Summary
Magnetic resonance imaging (MRI), as a non-invasive technology that can provide detailed images of organs and tissues in the body, has been routinely used in early detection and diagnosis of various cerebral and cardiovascular diseases (Teipel et al, 2013; Lemaître et al, 2015; Zhou et al, 2015; Abbasi and Tajeripour, 2017). One needs to identify the T1-weighted images and pass the file/folder names to FreeSurfer’s recon-all command1 Even small variations, such as extra spaces or mixed usage of hyphens and dashes, in sequence names, can cause problems to computer software programs. The absence of consistent naming conventions presents a major challenge in automating image processing and pre-processing procedures This issue becomes increasingly critical giving the current efforts toward open sharing of MRI data in the neuroscience community (Laird et al, 2005; Teeters et al, 2008; Yarkoni et al, 2011; Hall et al, 2012; Poldrack et al, 2013; Ferguson et al, 2014; Vaccarino et al, 2018), and the wide interests in performing meta-analyses of neuroimaging studies (Müller et al, 2018). The rapid growth of the volume and heterogeneity of the data makes it unrealistic to process without an automated approach
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
