A generalizable brain extraction net (BEN) for multimodal MRI data from rodents, nonhuman primates, and humans

  1. Ziqi Yu
  2. Xiaoyang Han
  3. Wenjing Xu
  4. Jie Zhang
  5. Carsten Marr
  6. Dinggang Shen
  7. Tingying Peng  Is a corresponding author
  8. Xiao-Yong Zhang  Is a corresponding author
  9. Jianfeng Feng
  1. Fudan University, China
  2. Helmholtz Zentrum München, Germany
  3. ShanghaiTech University, China

Abstract

Accurate brain tissue extraction on magnetic resonance imaging (MRI) data is crucial for analyzing brain structure and function. While several conventional tools have been optimized to handle human brain data, there have been no generalizable methods to extract brain tissues for multimodal MRI data from rodents, nonhuman primates, and humans. Therefore, developing a flexible and generalizable method for extracting whole brain tissue across species would allow researchers to analyze and compare experiment results more efficiently. Here, we propose a domain-adaptive and semi-supervised deep neural network, named the Brain Extraction Net (BEN), to extract brain tissues across species, MRI modalities, and MR scanners. We have evaluated BEN on 18 independent datasets, including 783 rodent MRI scans, 246 nonhuman primate MRI scans, and 4,601 human MRI scans, covering five species, four modalities, and six MR scanners with various magnetic field strengths. Compared to conventional toolboxes, the superiority of BEN is illustrated by its robustness, accuracy, and generalizability. Our proposed method not only provides a generalized solution for extracting brain tissue across species but also significantly improves the accuracy of atlas registration, thereby benefiting the downstream processing tasks. As a novel fully automated deep-learning method, BEN is designed as an open-source software to enable high-throughput processing of neuroimaging data across species in preclinical and clinical applications.

Data availability

All data (MRI data, source codes, pretrained weights and replicate demo notebooks for Figure 1-7) are included in the manuscript or available at https://github.com/yu02019/BEN.

The following data sets were generated
The following previously published data sets were used

Article and author information

Author details

  1. Ziqi Yu

    Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-8201-5481
  2. Xiaoyang Han

    Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-3007-6079
  3. Wenjing Xu

    Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
    Competing interests
    No competing interests declared.
  4. Jie Zhang

    Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
    Competing interests
    No competing interests declared.
  5. Carsten Marr

    Institute of AI for Health, Helmholtz Zentrum München, Neuherberg, Germany
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0003-2154-4552
  6. Dinggang Shen

    School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
    Competing interests
    Dinggang Shen, is affiliated with Shanghai United Imaging Intelligence Co., Ltd. He has financial interests to declare..
  7. Tingying Peng

    Helmholtz AI, Helmholtz Zentrum München, Neuherberg, Germany
    For correspondence
    tingying.peng@helmholtz-muenchen.de
    Competing interests
    No competing interests declared.
  8. Xiao-Yong Zhang

    Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
    For correspondence
    xiaoyong_zhang@fudan.edu.cn
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-8965-1077
  9. Jianfeng Feng

    Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China
    Competing interests
    No competing interests declared.
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0001-5987-2258

Funding

National Natural Science Foundation of China (81873893,82171903,92043301)

  • Xiao-Yong Zhang

Fudan University (the Office of Global Partnerships (Key Projects Development Fund))

  • Xiao-Yong Zhang

Shanghai Municipal Science and Technology Major Project (No.2018SHZDZX01)

  • Xiao-Yong Zhang

The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.

Reviewing Editor

  1. Saad Jbabdi, University of Oxford, United Kingdom

Ethics

Animal experimentation: Partial rodent MRI data collection were approved by the Animal Care and Use Committee of Fudan University, China. The rest rodent data (Rat-T2WI-9.4T and Rat-EPI-9.4T datasets) are publicly available (CARMI: https://openneuro.org/datasets/ds002870/versions/1.0.0). Marmoset MRI data collection were approved by the Animal Care and Use Committee of the Institute of Neuroscience, Chinese Academy of Sciences, China. Macaque MRI data are publicly available from the nonhuman PRIMatE Data Exchange (PRIME-DE) (https://fcon_1000.projects.nitrc.org/indi/indiPRIME.html).

Human subjects: The Zhangjiang International Brain Biobank (ZIB) protocols were approved by the Ethics Committee of Fudan University (AF/SC-03/20200722) and written informed consents were obtained from all volunteers. UK Biobank (UKB) and Adolescent Brain Cognitive Development (ABCD) are publicly available.

Version history

  1. Preprint posted: May 26, 2022 (view preprint)
  2. Received: June 20, 2022
  3. Accepted: December 21, 2022
  4. Accepted Manuscript published: December 22, 2022 (version 1)
  5. Version of Record published: February 17, 2023 (version 2)
  6. Version of Record updated: February 21, 2023 (version 3)

Copyright

© 2022, Yu et al.

This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 1,336
    views
  • 184
    downloads
  • 6
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Ziqi Yu
  2. Xiaoyang Han
  3. Wenjing Xu
  4. Jie Zhang
  5. Carsten Marr
  6. Dinggang Shen
  7. Tingying Peng
  8. Xiao-Yong Zhang
  9. Jianfeng Feng
(2022)
A generalizable brain extraction net (BEN) for multimodal MRI data from rodents, nonhuman primates, and humans
eLife 11:e81217.
https://doi.org/10.7554/eLife.81217

Share this article

https://doi.org/10.7554/eLife.81217

Further reading

    1. Computational and Systems Biology
    2. Epidemiology and Global Health
    Javier I Ottaviani, Virag Sagi-Kiss ... Gunter GC Kuhnle
    Research Article

    The chemical composition of foods is complex, variable, and dependent on many factors. This has a major impact on nutrition research as it foundationally affects our ability to adequately assess the actual intake of nutrients and other compounds. In spite of this, accurate data on nutrient intake are key for investigating the associations and causal relationships between intake, health, and disease risk at the service of developing evidence-based dietary guidance that enables improvements in population health. Here, we exemplify the importance of this challenge by investigating the impact of food content variability on nutrition research using three bioactives as model: flavan-3-ols, (–)-epicatechin, and nitrate. Our results show that common approaches aimed at addressing the high compositional variability of even the same foods impede the accurate assessment of nutrient intake generally. This suggests that the results of many nutrition studies using food composition data are potentially unreliable and carry greater limitations than commonly appreciated, consequently resulting in dietary recommendations with significant limitations and unreliable impact on public health. Thus, current challenges related to nutrient intake assessments need to be addressed and mitigated by the development of improved dietary assessment methods involving the use of nutritional biomarkers.

    1. Cancer Biology
    2. Computational and Systems Biology
    Marie Breeur, George Stepaniants ... Vivian Viallon
    Research Article

    Untargeted metabolomic profiling through liquid chromatography-mass spectrometry (LC-MS) measures a vast array of metabolites within biospecimens, advancing drug development, disease diagnosis, and risk prediction. However, the low throughput of LC-MS poses a major challenge for biomarker discovery, annotation, and experimental comparison, necessitating the merging of multiple datasets. Current data pooling methods encounter practical limitations due to their vulnerability to data variations and hyperparameter dependence. Here, we introduce GromovMatcher, a flexible and user-friendly algorithm that automatically combines LC-MS datasets using optimal transport. By capitalizing on feature intensity correlation structures, GromovMatcher delivers superior alignment accuracy and robustness compared to existing approaches. This algorithm scales to thousands of features requiring minimal hyperparameter tuning. Manually curated datasets for validating alignment algorithms are limited in the field of untargeted metabolomics, and hence we develop a dataset split procedure to generate pairs of validation datasets to test the alignments produced by GromovMatcher and other methods. Applying our method to experimental patient studies of liver and pancreatic cancer, we discover shared metabolic features related to patient alcohol intake, demonstrating how GromovMatcher facilitates the search for biomarkers associated with lifestyle risk factors linked to several cancer types.