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

Aug 5, 2026

Upload by Skyler

Spectral analysis is a model-free PET quantification approach where the time–space signal is treated as an impulse response to a bolus injection. Band-pass spectral analysis uses selected frequency ranges to derive separate voxel-wise parametric maps for receptor subtype binding, but selecting boundaries is currently manual and labor intensive. This study proposes machine learning to automate spectral boundary selection for dynamic [11C]Ro15-4513 PET, enabling voxel-wise parametric map generation. Models evaluated include 1D CNN, neural network, SVM, logistic regression, k-nearest neighbors, and fine tree.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Background

Results

Conclusion

Keywords

King’s Research Portal DOI: 10.1186/s13550-025-01251-5 Document Version Publisher's PDF, also known as Version of record Link to publication record in King's Research Portal Citation for published version (APA): Chang, Z. , McGinnity, C. , Hinz, R. , Wang, M. , Dunn, J. , Liu, R. , Yakubu, M. , Marsden, P. , & Hammers, A.(2025) . Machine learning to identify suitable boundaries for band-pass spectral analysis of dynamic [11C]Ro15- 4513 PET scan and voxel-wise parametric map generation. EJNMMI Research, 15(1), Article 85. [https://doi.org/10.1186/s13550-025-01251-5](https://doi.org/10.1186/s13550-025-01251-5) Citing this paper Please note that where the full-text provided on King's Research Portal is the Author Accepted Manuscript or Post-Print version this may differ from the final Published version. If citing, it is advised that you check and use the publisher's definitive version for pagination, volume/issue, and date of publication details. And where the final published version is provided on the Research Portal, if citing you are again advised to check the publisher's website for any subsequent corrections. General rights Copyright and moral rights for the publications made accessible in the Research Portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognize and abide by the legal requirements associated with these rights. •Users may download and print one copy of any publication from the Research Portal for the purpose of private study or research. •You may not further distribute the material or use it for any profit-making activity or commercial gain •You may freely distribute the URL identifying the publication in the Research Portal Take down policy If you believe that this document breaches copyright please contact [librarypure@kcl.ac.uk](librarypure@kcl.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim. Download date: 04. Aug. 2026 Chang etal. EJNMMI Research (2025) 15:85 [https://doi.org/10.1186/s13550-025-01251-5](https://doi.org/10.1186/s13550-025-01251-5) EJNMMI RESEARCH ORIGINAL RESEARCH Open Access Machine learning to identify suitable boundaries for band-pass spectral analysis of dynamic [ C]Ro15-4513 PET scan and voxel-wise parametric map generation Zeyu Chang1 , Colm J. McGinnity 1, Rainer Hinz2, Manlin Wang4, Joel Dunn1, Ruoyang Liu3, Mubaraq Yakubu1, Paul Marsden 1 and Alexander Hammers1* 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 [ C]Ro15-4513 binding to GABAA 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 offrequency ranges based on the data. To enhance the efficiency of band-pass spectral analysis and extend its application to a broader range oftracers, 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 ( 􀀞􀀝􀀜, largely representing 5) and 4 . 74% for fast component volume-of-distribution( 􀀞􀀝􀀜, largely representing 5), while the relative error was 2. 83%± 43 .47% for 􀀞􀀝􀀜 and 2. 01% ± 78. 04% for 􀀞􀀝􀀜 .

FAQs

What problem does the study address in band-pass spectral analysis?

Frequency boundaries for band-pass spectral analysis are currently selected manually by inspecting spectra and using prior knowledge. This limits efficiency and restricts broader application to other tracers.

Which machine learning models were evaluated for boundary selection?

The study tested 1D Convolutional Neural Networks, neural networks, support vector machines, logistic regression, k-nearest neighbors, and fine tree models.

How accurate were the best predictions of spectral boundaries?

The best-performing fine tree model matched the manual frequency boundary in 96.92% of 3185 ROIs, with reported mean and relative errors for slow and fast component volume-of-distribution.

Aug 5, 2026

Upload by Skyler