In recent years, with the development of artificial intelligence (AI) technology and the development of environments for collecting large datasets, AI has become increasingly important in areas such as basic science, marketing, logistics, finance, and medicine. .. In medicine, AI technology is used to analyze medical images such as functional magnetic resonance imaging (fMRI) to help diagnose illness.
On the other hand, reproducibility is indispensable for the practical application of this technology.For example, the results obtained by applying AI technology to MRI data from dozens of participants collected at one time. site Data collected on other sites cannot be duplicated. In addition, the data collected at different sites reflects differences in MRI hardware, protocols, and measurement biases.
Therefore, simply collecting large amounts of data collected by multiple sites cannot eliminate the differences between the sites. To solve these problems, a large amount of data collected from patients with different diseases using a common imaging protocol at multiple sites, and measured at the same participant at multiple sites (“travelers”). I need the data that was done. However, until now, no fMRI has been published. data set Meets these requirements.
In the current study published in the journal, Scientific data, FMRI data for multiple psychiatric or neurological disorders (Autism spectrum disorder, Major Depression, Bipolar disorder, schizophrenia, Obsessive-compulsive disorderChronic pain and stroke, measured by a unified imaging protocol at 14 sites) were compiled as a multi-site, multi-disease database (“SRPBS database”). This database contains 2,414 samples (993 patients and 1,421 healthy individuals) of resting fMRI (rs-fMRI) data, structural MRI data, and demographic data (gender, age, feel, diagnosis, clinical evaluation scale). ). To minimize differences between sites, “travel subject” data measured for 9 subjects in 143 sessions at 12 facilities was compiled into a single database.
We have published four datasets generated from the SRPBS database for various purposes.
- The SRPBS Multi-disorder Connectivity Dataset consists of functional connectivity data from patients and healthy participants.
- The SRPBS multidisciplinary MRI dataset (limited) consists of rs-fMRI and structural MRI images of patients and healthy participants.
- The SRPBS multidisciplinary MRI dataset (unlimited) consists of rs-fMRI and structural MRI images of patients and healthy participants.
- The SRPBS Traveling Subject MRI dataset consists of rs-fMRI and structural MRI images of the traveling subject.
By publishing data from multiple sites and multiple illnesses captured by a unified protocol along with data on traveling subjects, the data can be harmonized to minimize differences between sites and AI. I was able to apply the technology. Researchers have global access to these data, and the development of more accurate diagnostic markers and more sophisticated harmonization methods could dramatically speed up research.
This document is subject to copyright. No part may be reproduced without written permission, except for fair transactions for personal investigation or research purposes. The content is provided for informational purposes only.
844 total views, 1 views today