Non-invasive measurement of pH provides multiple potential benefits in oncology such as better identifying the type of drug that can be more effective in chemotherapy, potentially identifying tumors that are more likely to metastasize and also better assessing the treatment effects. Chemical Exchange Saturation Transfer (CEST) Magnetic Resonance Imaging (MRI) is a versatile non-invasive technique for molecular imaging. AcidoCEST MRI techniques have been developed over the recent years to perform tumor pH measurements by utilizing a contrast agent for which chemical exchange saturation transfer effects depend on the pH of the microenvironment. Quantitative description of CEST MRI signals are generally done via modeling Bloch-McConnell equations by incorporating pH as a parameter or by fitting Lorentzian line shapes to observed z-spectra and then computing a log ratio of the CEST effects from multiple labile protons of the same molecule (ratiometric method). Modeling using Bloch-McConnell equations is complicated and requires careful inclusion of many scan parameters to infer pH. The ratiometric method requires contrast agents that have multiple labile protons, thus making it unsuitable to use for molecules with a single labile proton. Furthermore, depending on the pH, sometimes it might not be possible to numerically compute the ratio due to the inability of detecting signal peaks for certain labile protons. Our aim here is to develop a machine learning based method that learns the CEST signal patterns from observed z-spectra on temperature and concentration-controlled contrast agent phantoms independent of the type of the contrast agent. Our results indicate that the machine learning method provides more general and accurate prediction of pH in comparison to the ratiometric method based on the phantom CEST dataset. Our method is more general in the sense that it does not require explicit modeling of signal peaks that are dependent on the type of contrast agent. We also describe a state of the art variational autoencoder based algorithm extending our machine learning method to measure tumor pH in vivo using AcidoCEST MRI on mouse tumor models.

In the early 1920s, Otto Warburg demonstrated that tumor cells have a capacity to convert glucose and other substrates into lactic acid instead of CO2 and water, even under aerobic conditions. Consequently, Warburg assumed that the intracellular pH (pHi) of tumor was acidic. However, later studies have shown that maintenance of pHi within a pH range of 7.0-7.2 is necessary for normal cellular proliferation and that the extracellular pH (pHe) is partially acidic in solid tumors. A low pHe may be an important factor inducing invasive behavior in tumor cells. Research into causes and consequences of this acid pH of tumors are highly dependent on accurate, precise and reproducible measurements. Techniques for measuring tissue pHi and pHe have undergone great changes since 1950s. From microelectrode and dye distribution studies, measurement of pH underwent a revolution with the advent of pH-sensitive dyes that could be loaded into the cytosol. Further significant advances have come from the measurement of cell and tissue pH in whole organisms by magnetic resonance spectroscopy (MRS), magnetic resonance imaging (MRI) and pH-sensitive Positron Emission Tomography (PET) radiotracers.