DeepStream-MRI

A complete automated analytics toolkit and workflow for AI-based brain MRI data processing, quantification, analysis and understanding.

Info/Github

  1. I. Automated processing streamline for mouse brain MRI
    1. Structure MRI (Automated processing workflow for mouse brain structural MRI)
      1. Brukertools
      2. AFT-Net and CU-Net github (Access permissions upon request)
      3. Accelerated MRI and Super-resolution recontruction github (Access permissions upon request)
      4. DL-BET: Deep Learning based Brain Extraction Tool github
      5. Cycle Inverse Consistent TransMorph: Cycle Inverse Consistent Deformable Medical Image Registration with Transfomer github (Access permissions upon request)
    2. CBV fMRI (Automated processing workflow for mouse brain CBV functional MRI)
      1. Brukertools
      2. AFT-Net and CU-Net github (Access permissions upon request)
      3. Accelerated MRI and Super-resolution recontruction github (Access permissions upon request)
      4. DL-BET: Deep Learning based Brain Extraction Tool github
      5. DRC: Dynamic Relaxation Contrast MRI processing tools for mouse brain imaging github
    3. AI-CBV mapping from T2-weighted MRI
      1. DeepContrast: Deep Learning of MRI Contrast Enhancement for Mapping Cerebral Blood Volume from Single-Modal Non-Contrast Scan github
    4. AI-Ktrans mapping from low-dose DCE MRI
      1. ST-Net: Deep Learning Enables Reduced Gadolinium Dose for Contrast-Enhanced Blood-Brain Barrier Opening Quantitative
  2. II. Automated mouse brain MRS processing streamline
    1. JET: J-Editing Toolkit github
    2. DeepMRS-Net
      1. CNN-FPC: Magnetic Resonance Spectroscopy Frequency and Phase Correction Using Convolutional Neural Networks github
      2. CNN-SR: Magnetic Resonance Spectroscopy Spectral Registration Using Deep Learning github
      3. DL-LCModel
  3. III. Automated human brain MRI processing streamline
    1. Structure MRI segmentation and registration
      1. TABS: Transformer-based Automated Brain Tissue Segmentation github
      2. Cycle Inverse Consistent TransMorph
    2. AI-CBV mapping from T1-weighted MRI
      1. DeepContrast: Deep Learning of MRI Contrast Enhancement for Mapping Cerebral Blood Volume from Single-Modal Non-Contrast Scan github
  4. IV. Automated human brain MRS processing streamline
    1. JET: J-Editing Toolkit github
    2. DeepMRS-Net
      1. CNN-FPC: Magnetic Resonance Spectroscopy Frequency and Phase Correction Using Convolutional Neural Networks github
      2. CNN-SR: Magnetic Resonance Spectroscopy Spectral Registration Using Deep Learning github
      3. DL-LCModel
  5. V. Cuttlebase is a scientifictoolkit for the dwarf cuttlefish, Sepia bandensis
    1. To create an MRI-based 3D brain atlas for the dwarf cuttlefish, ex vivo magnetic resonance imaging of 8 adult dwarf cuttlefish brains (4 males, 4 females) at 50 µm isotropic resolution was performed. Deep learning techniques were used to improve manually-annoted brain masks that were then used to extract the brain regions for subsequent diffeomorphic registration using the ANTs toolbox. github github
  6. VI. Statistical analyses and visualization for large neuroimaging dataset github
  7. VII. Predicting brainAGE with MRI using deep learning
    1. Regression model input: T1-weighted sMRI (to be announced)
    2. Regression model input: T1-weighted sMRI + AI-CBV fMRI (to be announced)
  8. VIII. Diagnosing Alzheimer’s disease with MRI using deep learning
    1. Classification model input: T1-weighted sMRI (to be announced)
    2. Classification model input: T1-weighted sMRI + AI-CBV fMRI (to be announced)
  9. IX. Diagnosing schizophrenia with MRI using deep learning
    1. Classification model input: T1-weighted sMRI (to be announced)
    2. Classification model input: T1-weighted sMRI + AI-CBV fMRI (to be announced)