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

作者：Zeyu Chang, Colm J. McGinnity, Rainer Hinz, Manlin Wang, Joel Dunn, Ruoyang Liu, Mubaraq Yakubu, Paul Marsden, Alexander Hammers · 发表于：EJNMMI Research · 年份：2025 · DOI：10.1186/s13550-025-01251-5 · 被引用次数：2 · 研究领域：Medical Imaging Techniques and Applications、Radiopharmaceutical Chemistry and Applications、Radiation Detection and Scintillator Technologies

Abstract 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 [ $$^{11}$$ 11 C]Ro15-4513 binding to GABA A $$\alpha$$ α 1/5 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 selection 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 neighbors, 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 ( $$\hbox {V}_{slow}$$ V slow , largely representing $$\alpha$$ α 5) and 4.74% for fast component volume-of-distribution( $$\hbox {V}_{fast}$$ V fast ...