PET scans involve intrusive introduction of radioactive tracers into the subject’s bloodstream. Organs, specifically of interest in SZ, brain tissue, absorb the tracer, which is concentrated in areas of higher chemical activity, appearing as bright spots on the PET scan. Neuroinflammation, which is well depicted by these scans, are areas of interest as there is presence of epidemiological, genetic and clinical evidence of its involvement in SZ. Microglia are the resident immune cells of the central nervous system and act as major mediators of neuroinflammation. When microglia are activated, they express high levels of the 18-kDa translocator protein which can be measured in vivo with PET radio-tracers. Images collected can be used to train a ML classifier, and patterns recognized from the algorithm can then be used to predict and detect SZ in new subjects.

Levy et al. [117] obtained PET scan images from 12 medicated SZ patients and 11 HC under resting conditions and while performing a visual task. A cortical/subcortical spatial pattern was found to be significant in two directions; anterior/posterior and chiasmatic (left-anterior/right-posterior). A total of 14 two-group linear discriminant analyses were performed to classify the sample. The best individual clinical classification (Jackknife classification) occurred under visual task at two axial brain levels: at the basal ganglia (with correct classification rates of 91% specificity and 84% sensitivity), and at the cerebellum (which had rates of 82% specificity and 92% sensitivity). These high classification rates were obtained using only four coefficients of the lowest spatial frequency. These results point to the generalized brain dysfunction of regional glucose metabolism in chronic medicated schizophrenics both at rest and at a visual image-tracking task. Josin and Liddle [118] reported an analysis using a neural network to discriminate between the patterns of functional connectivity in 16 SZ patients and six HC. After training on data from two healthy subjects and seven SZ patients, the neural network successfully assigned all members of a test set of four healthy subjects and nine SZ patients to the correct diagnostic category. Lastly, Bose et al. [119] also tested an artificial neural network model in the discrimination of 19 SZ patients from 31 HC using o-dihydroxyphenylalanine (DOPA) rate constants within the anterior–posterior subdivisions of the striatum. They obtained correct classification rates of 89% sensitivity and 94% specificity. Although PET scans are reporting relatively high classification predictions of remarkable accuracy, it does not evoke confidence as means of detecting SZ as that current work use small sample sizes.

Note: The content above has been extracted from a research article, so it may not display correctly.



Q&A
Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.



We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.