Machine learning to identify suitable boundaries for band-pass spectral analysis of dynamic [₁₁C]Ro15-4513 PET scan and voxel-wise parametric map generation

Background Spectral analysis is a model-free PET quantification technique that treats the time-space signal as an impulse response to a bolus injection. Band-pass spectral analysis, considering specific frequency ranges, enables calculation of separate parametric maps of receptor subtype tracer binding for suitable radiopharmaceuticals such as [¹¹C]Ro15-4513 binding to GABA_A α1/5 subunits. Frequency ranges are based on inspection of spectra, prior knowledge of receptor distribution, and blocking studies. The process currently requires the manual selection of frequency ranges based on the data. To enhance the efficiency of band-pass spectral analysis and extend its application to a broader range of tracers, we propose employing machine learning to automate the election of spectral boundaries. Based on these boundaries, voxel-wise parametric maps can be generated. The machine learning models utilized in this study include 1D Convolutional Neural Network, Neural Network, Support Vector Machine, Logistic Regression, K-nearest neighbours, and Fine Tree.

Results The best machine learning model, Fine Tree, agreed with the manual frequency boundary in 96.92% of 3185 ROIs. The absolute mean error was 3.80% for slow component volume-of-distribution (V_slow, largely representing α5) and 4.74% for fast component volume-of-distribution(V_fast, largely representing α5), while the relative error was 2.83% ± 43.47% for V_slow and−2.01% ± 78.04% for V_fast. The median test-retest intraclass correlation coefcient across six representative regions was 0.770 for V_slow, 0.670 for V_fast, and 0.502 for total component volume-of-distribution(V_d). Parametric maps applying diferent boundaries for different ROIs were generated.

Conclusion The machine learning model developed provided accurate boundary predictions in 96.92% of regions, with minimal average bias. However, when errors occur, they can be large, owing to the sparsity of peaks. The model enables setting boundaries automatically for the vast majority of regions, followed by manual checking of the outliers. It opens the possibility of accelerating analyses e.g. of GABA_A α1/2/3/5 subunit binding using [¹¹C]fumazenil and of extending band-pass spectral analysis to other receptor systems.