Magia: Robust Automated Image Processing and Kinetic Modeling Toolbox for PET Neuroinformatics

Tomi Karjalainen; Jouni Tuisku; Severi Santavirta; Tatu Kantonen; Marco Bucci; Lauri Tuominen; Jussi Hirvonen; Jarmo Hietala; Juha O Rinne; Lauri Nummenmaa

doi:10.3389/fninf.2020.00003

Magia: Robust Automated Image Processing and Kinetic Modeling Toolbox for PET Neuroinformatics

Front Neuroinform. 2020 Feb 4:14:3. doi: 10.3389/fninf.2020.00003. eCollection 2020.

Authors

Tomi Karjalainen¹, Jouni Tuisku¹, Severi Santavirta¹, Tatu Kantonen¹, Marco Bucci¹, Lauri Tuominen², Jussi Hirvonen^{1

3}, Jarmo Hietala^{1

4}, Juha O Rinne^{1

5}, Lauri Nummenmaa^{1

6}

Affiliations

¹ Turku PET Centre, University of Turku and Turku University Hospital, Turku, Finland.
² The Royal's Institute of Mental Health Research, University of Ottawa, Ottawa, ON, Canada.
³ Department of Radiology, University of Turku, Turku, Finland.
⁴ Department of Psychiatry, Faculty of Medicine, University of Turku and Turku University Hospital, Turku, Finland.
⁵ Division of Clinical Neurosciences, Turku University Hospital, Turku, Finland.
⁶ Department of Psychology, University of Turku, Turku, Finland.

Abstract

Processing of positron emission tomography (PET) data typically involves manual work, causing inter-operator variance. Here we introduce the Magia toolbox that enables processing of brain PET data with minimal user intervention. We investigated the accuracy of Magia with four tracers: [¹¹C]carfentanil, [¹¹C]raclopride, [¹¹C]MADAM, and [¹¹C]PiB. We used data from 30 control subjects for each tracer. Five operators manually delineated reference regions for each subject. The data were processed using Magia using the manually and automatically generated reference regions. We first assessed inter-operator variance resulting from the manual delineation of reference regions. We then compared the differences between the manually and automatically produced reference regions and the subsequently obtained binding potentials and standardized-uptake-value-ratios. The results show that manually produced reference regions can be remarkably different from each other, leading to substantial differences also in outcome measures. While the Magia-derived reference regions were anatomically different from the manual ones, Magia produced outcome measures highly consistent with the average of the manually obtained estimates. For [¹¹C]carfentanil and [¹¹C]PiB there was no bias, while for [¹¹C]raclopride and [¹¹C]MADAM Magia produced 3-5% higher binding potentials. Based on these results and considering the high inter-operator variance of the manual method, we conclude that Magia can be reliably used to process brain PET data.

Keywords: PET; carfentanil; madam; modeling; neuroinformatics; pib; raclopride; reference region.