Rexis
  • Rexis: The L1 for DeSci
  • Key Challenges in BioDeSci
    • Overview
  • Data Level: Secure Biomedical Sharing
  • Model Level: Privacy-Preserving Fine-Tuning
  • Evaluation Level: Reproducible Computation
  • The Rexis Solution: Layer for DeSci
    • Overview
    • Data Level: Decentralized Biomedical Data Market
    • Model Level: Privacy-Preserving Training & Inference via Equivariant Encryption
    • Evaluation Level: Secure and Verifiable Biomedical Computation
  • Example BioDeSci Data and Models
    • Overview
  • Tabular Data
  • Biomedical Signals
  • Biological Sequences
  • Medical Imaging
  • Volumetric Medical Imaging
  • Spatial Omics Data
  • Tokenomics
    • $REX Overview
  • Links
    • rexis.io
  • Term of Use
  • Privacy Policy
  • Community
Powered by GitBook
On this page

Volumetric Medical Imaging

PreviousMedical ImagingNextSpatial Omics Data

Last updated 1 month ago

Volumetric Medical Imaging

Volumetric imaging techniques generate 3D representations of internal anatomy, providing rich spatial information for diagnosis, surgical planning, and disease monitoring. These modalities capture detailed volumetric data beyond standard 2D slices.

Computed Tomography (CT)

CT scans create 3D cross-sectional images of the body using multiple X-ray projections from various angles. The data is reconstructed into volumetric form and is especially useful for:

  • Bone and organ segmentation

  • Cardiovascular imaging

  • Tumor detection and monitoring

Data Support

CT data is stored in the DICOM format as a stack of 2D slices forming a 3D volume.

Our platform ensures that CT images are securely processed using Equivariant Encryption (EE), enabling:

  • Fine-tuning and evaluation on encrypted CT volumes

  • Secure data storage and sharing

  • Full compliance with patient privacy regulations

Model Support

We support secure model training and evaluation on encrypted CT data.

Magnetic Resonance Imaging (MRI)

MRI is a non-invasive imaging modality that uses magnetic fields and radio waves to create high-contrast, high-resolution 3D scans of soft tissues. MRI is critical for:

  • Brain and spinal cord imaging

  • Musculoskeletal diagnostics

  • Internal organ evaluation (e.g., liver, prostate, heart)

Data Support

MRI data is typically stored in DICOM format and consists of 3D volumes or time series (4D). With EE, our platform supports:

  • Encrypted storage and computation on MRI scans

  • Secure sharing across institutions

  • Privacy-preserving training for clinical and research AI

Model Support

We support secure model evaluation and enhancement for encrypted MRI data.

A foundational 3D convolutional network architecture designed for volumetric segmentation of organs and lesions in CT images.

A flexible MRI enhancement model that improves image quality via motion correction, super-resolution, denoising, contrast enhancement, and harmonization.

VNet
BME-X