Related Experiment Video
Updated: Jul 9, 2026
09:53
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
Investigating the uncertainty of cellular microenvironment parameter estimations via diffusion MRI cytometry
Wen Li1, Yan Dai2, Arely Perez Rodriguez2
1Department of Radiation Oncology and Molecular Radiation Sciences, Johns Hopkins University, Baltimore, Maryland, USA.
Medical Physics
|July 8, 2026
Summary
This study identifies robust cell microenvironment parameters using IMPULSED diffusion MRI (dMRI) and develops a mapping framework for accurate estimation. This advances noninvasive monitoring of radiation therapy response.
Area of Science:
- Biomedical Imaging
- Quantitative MRI
- Tumor Microenvironment Analysis
Background:
- Cell microenvironment features are key biomarkers for assessing early tumor response to radiation therapy.
- Diffusion MRI (dMRI) offers a noninvasive method to study these features, but conventional models have high uncertainty and poor robustness.
Purpose of the Study:
- Establish a theoretical basis for robustly estimating cell microenvironment parameters from IMPULSED dMRI signals.
- Develop a reliable mapping-based framework for accurate parameter estimation.
Main Methods:
- Simulated dMRI signals using the IMPULSED model with PGSE and OGSE sequences.
- Quantified parameter uncertainty via Jacobian-based sensitivity analysis.
- Developed mapping models (linear regression, polynomial regression, neural network) using dimension-reduced, logarithmically transformed dMRI signals.
Main Results:
- Identified cell diameter (d), intracellular volume fraction (Vin), and extracellular diffusion coefficient (Dex) as robustly derivable parameters with low uncertainty.
- A 4-layer neural network achieved the best performance, with low mean absolute errors for d, Vin, and Dex.
- In vitro validation showed a 6.7% error in cell diameter estimation.
Conclusions:
- Successfully identified robust cell microenvironment parameters from IMPULSED dMRI.
- Established a mapping-based framework for accurate and robust parameter estimation.
- Provides a foundation for noninvasive monitoring of tumor microenvironment changes during radiation therapy.
