Machine learning-based amide proton transfer imaging using partially synthetic training data

Abstract

Purpose: Machine learning (ML) has been increasingly used to quantify CEST effect. ML models are typically trained using either measured data or fully simulated data. However, training with measured data often lacks sufficient training data, whereas training with fully simulated data may introduce bias because of limited simulations pools. This study introduces a new platform that combines simulated and measured components to generate partially synthetic CEST data, and to evaluate its feasibility for training ML models to predict amide proton transfer (APT) effect.

Methods: Partially synthetic CEST signals were created using an inverse summation of APT effects from simulations and the other components from measurements. Training data were generated by varying APT simulation parameters and applying scaling factors to adjust the measured components, achieving a balance between simulation flexibility and fidelity. First, tissue-mimicking CEST signals along with ground truth information were created using multiple-pool model simulations to validate this method. Second, an ML model was trained individually on partially synthetic data, in vivo data, and fully simulated data, to predict APT effect in rat brains bearing 9 L tumors.

Results: Experiments on tissue-mimicking data suggest that the ML method using the partially synthetic data is accurate in predicting APT. In vivo experiments suggest that our method provides more accurate and robust prediction than the training using in vivo data and fully synthetic data.

Conclusion: Partially synthetic CEST data can address the challenges in conventional ML methods.

Keywords: amide proton transfer; chemical exchange saturation transfer; machine learning; tumor.

Fig. 1

Flowchart of the machine learning method.

Fig. 2

Multiple-pool Lorentzian fitted ${\mathrm{R}}_{\mathrm{eff}}$ (a) and fitted APT, amine CEST, NOE(−1.6), NOE(−3.5), and MT spectra (b) from the average of the measured CEST Z-spectra in normal tissues in eight rat brains. Comparison between the measured CEST Z-spectra and synthetic Z-spectrum generated using all multiple-pool Lorentzian fitted components (c) as well as between the measured CEST Z-spectra and synthetic CEST Z-spectrum without APT (d).

Fig. 3

(a) A representative Z-spectrum from the tissue-mimicking data. (b) A comparison of the corresponding APT spectra from the ML prediction, multiple-pool Lorentzian fit, and ground truth. (c) A comparison of losses between the ML prediction and the multiple-pool Lorentzian fit for all testing data.

Fig. 4

Measured CEST Z-spectra from tumors and contralateral normal tissues in the three testing rats (a, b), the corresponding APT spectra from the ML prediction using the partially synthetic data for type 1 selection of 50, 100, 500, and 2157 voxels within five rat brains (c, d), and the corresponding APT spectra from the ML prediction using the measured in vivo data for type 1 selection of 50, 100, 500, and 2157 voxels within five rat brains as well as with data augmentation (e, f). The multiple-pool Lorentzian fitted APT spectra were also plotted in (c-f) for comparison. Data are averaged across different subjects.

Fig. 5

Measured CEST Z-spectra from tumors and contralateral normal tissues in the eight rats (a, b), the corresponding APT spectra from the ML prediction using the partially synthetic data for type 2 selection of tumors and normal tissues (c, d), the corresponding APT spectra from the ML prediction using the measured in vivo data for type 2 selection of tumors and normal tissues (e, f), and ML prediction using fully synthetic data with the type 1 and type 2 simulations (g, h). The multiple-pool Lorentzian fitted APT spectra were also plotted in (c-h) for comparison. Data are averaged across different subjects.

Fig. 6

APT amplitude maps from three testing rat brains (from left to right – Rat 6, Rat 7, Rat 8) using the Lorentzian fitting (a), ML prediction using partially synthetic data with the measured components from the in vivo data with type 1 selection of 50 (b), 100 (c), 500 (d), and 2157 (e) voxels from five rat brains, ML prediction using the measured in vivo data with type 1 selection of 50 (f), 100 (g), 500 (h), and 2157 (i) voxels from five rat brains as well as ML prediction using the measured in vivo data using all voxels from five rat brains with data augmentation (j).

Fig. 7

APT amplitude maps from the one rat brain (Rat 1) using the Lorentzian fitting (a), ML prediction using partially synthetic data with the measured components from the in vivo data with type 2 selection of tumors (b) and normal tissues (c), ML prediction using the measured in vivo data with type 2 selection of tumors (d) and normal tissues (e), ML prediction using the measured in vivo data with type 2 selection of tumors with data augmentation (f) and normal tissues with data augmentation (g), as well as ML prediction using fully synthetic data with the type 1 (h) and type 2 (i) simulations.

Fig. 8

Statistical differences in ${\mathrm{R}}_{1\mathrm{obs}}$ (a), ${\mathrm{f}}_{\mathrm{m}}$ (b), the ML predicted APT amplitude using partially synthetic data with measured components from the type 1 selection of 50 voxels (c), and the multiple-pool Lorentzian fitted APT amplitude, between tumor and normal tissues in the three testing rat brains.