Predicting Carbon Spectrum in Heteronuclear Single Quantum Coherence Spectroscopy for Online Feedback During Surgery

<inline-formula><tex-math notation="LaTeX">${}^{1}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>1</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq1-2920646.gif"/></alternatives></inline-formula>H High-Resolution Magic Angle Spinning (HRMAS) Nuclear Magnetic Resonance (NMR) is a reliable technology used for detecting metabolites in solid tissues. Fast response time enables guiding surgeons in real time, for detecting tumor cells that are left over in the excision cavity. However, severe overlap of spectral resonances in 1D signal often render distinguishing metabolites impossible. In that case, Heteronuclear Single Quantum Coherence Spectroscopy (HSQC) NMR is applied which can distinguish metabolites by generating 2D spectra (<inline-formula><tex-math notation="LaTeX">${}^{1}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>1</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq2-2920646.gif"/></alternatives></inline-formula>H-<inline-formula><tex-math notation="LaTeX">${}^{13}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>13</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq3-2920646.gif"/></alternatives></inline-formula>C). Unfortunately, this analysis requires much longer time and prohibits real time analysis. Thus, obtaining 2D spectrum fast has major implications in medicine. In this study, we show that using multiple multivariate regression and statistical total correlation spectroscopy, we can learn the relation between the <inline-formula><tex-math notation="LaTeX">${}^{1}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>1</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq4-2920646.gif"/></alternatives></inline-formula>H and <inline-formula><tex-math notation="LaTeX">${}^{13}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>13</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq5-2920646.gif"/></alternatives></inline-formula>C dimensions. Learning is possible with small sample sizes and without the need for performing the HSQC analysis, we can predict the <inline-formula><tex-math notation="LaTeX">${}^{13}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>13</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq6-2920646.gif"/></alternatives></inline-formula>C dimension by just performing <inline-formula><tex-math notation="LaTeX">${}^{1}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>1</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq7-2920646.gif"/></alternatives></inline-formula>H HRMAS NMR experiment. We show on a rat model of central nervous system tissues (80 samples, 5 tissues) that our methods achieve 0.971 and 0.957 mean <inline-formula><tex-math notation="LaTeX">$R^2$</tex-math><alternatives><mml:math><mml:msup><mml:mi>R</mml:mi><mml:mn>2</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq8-2920646.gif"/></alternatives></inline-formula> values, respectively. Our tests on 15 human brain tumor samples show that we can predict 104 groups of 39 metabolites with 97 percent accuracy. Finally, we show that we can predict the presence of a drug resistant tumor biomarker (creatine) despite obstructed signal in <inline-formula><tex-math notation="LaTeX">${}^{1}$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mn>1</mml:mn></mml:msup></mml:math><inline-graphic xlink:href="cicek-ieq9-2920646.gif"/></alternatives></inline-formula>H dimension. In practice, this information can provide valuable feedback to the surgeon to further resect the cavity to avoid potential recurrence.