What does this research mean for the field?

Random forest regression using only CEST spectra provides a highly accurate and computationally efficient alternative to Bloch-McConnell fitting for mapping extracellular tumor pH in vivo using acidoCEST MRI. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To evaluate whether machine learning models can accurately and efficiently estimate extracellular tumor pH from in vivo acidoCEST MRI data compared with computationally intensive Bloch–McConnell fitting.

August 28, 2026NMR in BiomedicineOpen Access

A Machine Learning Approach That Measures Extracellular pH Within an In Vivo Tumor Model Using acidoCEST MRI

View Full Paper

Ask AI

Bookmark

Authors

AKAlia KhaledThe University of Texas MD Anderson Cancer Center CDChetan DhakanUniversity of Wisconsin–Madison LMLucas McCullumThe University of Texas MD Anderson Cancer Center

Discussion

Member takes

Implication

Preclinical study demonstrates that random forest regression accurately predicts extracellular tumor pH from acidoCEST MRI in mice, indicating a fast alternative to conventional Bloch fitting.

Key Points

To evaluate whether machine learning models can accurately and efficiently estimate extracellular tumor pH from in vivo acidoCEST MRI data compared with computationally intensive Bloch–McConnell fitting.
Acquired CEST-FISP MRI alongside T1, T2, B1, and B0 maps in 38 tumor-bearing mice using a 4T1 murine breast cancer model.
Trained and evaluated three machine learning architectures using pixel-wise Bloch–McConnell fitting as the reference: random forest regression (RFR) with multiparametric maps, RFR with CEST spectra alone, and a convolutional neural network (CNN) with CEST spectra alone.
The random forest regression model using only CEST spectra achieved the highest accuracy, with mean absolute percentage errors of 0.29% in training (0.020 pH units) and 0.79% in testing (0.054 pH units).
Spatial pH maps generated by random forest regression closely matched reference Bloch–McConnell maps, whereas CNN-derived maps showed compressed pH ranges and reduced correlation with reference values.

Cite This Study

Khaled et al. (2026) studied this question.

synapsesocial.com/papers/6a914613d15324a1df3a95bf https://doi.org/10.1002/nbm.70379

View Full Paper

Ask AI

Bookmark

Implication

Preclinical study demonstrates that random forest regression accurately predicts extracellular tumor pH from acidoCEST MRI in mice, indicating a fast alternative to conventional Bloch fitting.

A Machine Learning Approach That Measures Extracellular pH Within an In Vivo Tumor Model Using acidoCEST MRI

Discussion

Member takes

Implication

Key Points

Cite This Study

A Machine Learning Approach That Measures Extracellular pH Within an In Vivo Tumor Model Using acidoCEST MRI

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider