Amide Proton Transfer (APT) imaging in tumor with a machine learning approach using partially synthetic data
Malvika Viswanathan1,2, Leqi Yin3, Yashwant Kurmi1,4
1Vanderbilt University Institute of Imaging Science, Vanderbilt University Medical Center, Nashville, US.
This study introduces a novel method using partially synthetic chemical exchange saturation transfer (CEST) data to train machine learning (ML) models. This approach enhances the accuracy and robustness of predicting amide proton transfer (APT) effects compared to traditional methods.
Area of Science:
- Biomedical Imaging
- Machine Learning
- Quantitative MRI
Background:
- Machine learning (ML) is vital for quantifying chemical exchange saturation transfer (CEST) effects in MRI.
- Current ML training methods face limitations: insufficient measured data or simulation bias.
- Developing robust ML models for CEST analysis requires addressing these data challenges.
Conclusions:
- Partially synthetic CEST data effectively overcomes limitations of conventional ML training methods.
- This approach offers a more accurate and robust solution for ML-based CEST quantification.
- The developed platform holds significant potential for advancing quantitative MRI techniques.
More Related Videos
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
09:53Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020