Browsing by Author "Amaral, Horacio"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Image-based machine learning model as a tool for classification of [18F]PR04.MZ PET images in patients with parkinsonian syndrome
    (Elsevier B.V., 2025) Jiménez, María; Soza Ried, Cristian; Kramer, Vasko; Ríos, Sebastián A.; Haeger, Arlette; Juri Clavería, Carlos Andres; Amaral, Horacio; Chana Cuevas, Pedro
    Parkinsonian syndrome (PS) is characterized by bradykinesia, resting tremor, rigidity, and encapsulates the clinical manifestation observed in various neurodegenerative disorders. Positron emission tomography (PET) imaging plays an important role in diagnosing PS by detecting the progressive loss of dopaminergic neurons. This study aimed to develop and compare five machine-learning models for the automatic classification of 204 [18F]PR04.MZ PET images, distinguishing between patients with PS and subjects without clinical evidence for dopaminergic deficit (SWEDD). Previously analyzed and classified by three expert blind readers into PS compatible (1) and SWEDDs (0), the dataset was processed in both two-dimensional and three-dimensional formats. Five widely used pattern recognition algorithms were trained and validated their performance. These algorithms were compared against the majority reading of expert diagnosis, considered the gold standard. Comparing the accuracy of 2D and 3D format images suggests that, without the depth dimension, a single image may overemphasize specific regions. Overall, three models outperformed with an accuracy greater than 98 %, demonstrating that machine-learning models trained with [18F]PR04.MZ PET images can provide a highly accurate and precise tool to support clinicians in automatic PET image analysis. This approach may be a first step in reducing the time required for interpretation, as well as increase certainty in the diagnostic process.
  • Thumbnail Image
    Item
    Imaging Nigrostriatal Dopaminergic Deficit in Holmes Tremor with 18F-PR04.MZ-PET/CT
    (2015) Juri Clavería, Carlos Andrés; Chana, Pedro; Kramer, Vasko; Pruzzo, Rossana; Amaral, Horacio; Riss, Patrick J.; Rösch, Frank
  • No Thumbnail Available
    Item
    Pharmacokinetic evaluation of [18F]PR04.MZ for PET/CT imaging and quantification of dopamine transporters in the human brain
    (2020) Kramer, Vasko; Juri, Carlos; Riss, Patrick J.; Pruzzo, Rossana; Soza-Ried, Cristian; Flores, Jonathan; Hurtado, Ana; Roesch, Frank; Chana-Cuevas, Pedro; Amaral, Horacio
    Purpose Dopamine transporters (DAT) modulate pre-synaptic dopamine and physiological functions such as movement and reward. DAT also mirrors disease state in neurological disorders, rendering it an essential diagnostic target. [F-18]PR04.MZ is a new PET imaging agent for DAT with an improved affinity and selectivity profile, for which we here describe the complete pharmacokinetic evaluation in healthy controls. Methods Thirty-two healthy subjects underwent T1-weighted MRI and dynamic PET scans for 180 min with arterial blood sampling (n = 5) or 90 min without blood sampling (n = 25) after injection of 197.6 +/- 12.2 MBq [F-18]PR04.MZ. Blood and plasma metabolite analysis were performed. MRI-based normalization of brain images, delineation of VOIs, and kinetic modeling was conducted to determine distribution volumes (V-t) and binding potentials (BPnd). The impact of scan duration was evaluated and repeated PET scans were performed to assess test-retest variability (n = 5). A static imaging protocol has been validated for clinical applications. Results [F-18]PR04.MZ showed rapid metabolization in circulation, very high uptake in striatum and midbrain, and very low non-specific binding. The two-tissue compartment model 2TCM provided best fits for measured time-activity-curves and calculated V(t)s in putamen, caudate, substantia nigra pars compacta (SNpc), and cerebellar cortex were 11.83, 9.73, 2.12, and 0.57, respectively. All non-invasive models correlated well with BPnd values derived from 2TCM but underestimated DAT availability by about 28-33%. Of those, simplified reference tissue model (SRTM) provided the best fits, lowest Akaike Information Criteria values, and BPnd values of 14.82, 11.95, and 2.63 in putamen, caudate, and SNpc, respectively. BPnd estimates for striatal regions and SNpc were stable between 90 and 130 min post-injection. Test-retest results were excellent, showing low variability in all and excellent reliability in most relevant regions. Static imaging from 60 to 90-min post-injection is a viable alternative for quantification. Conclusions [F-18]PR04.MZ is a PET tracer with very high affinity, selectivity, and specific uptake in striatum and midbrain. 2TCM and SRTM provide good fits, high and stable V(t)s or BP(nd)s, and good test-retest reliability for precise quantification of DAT in human subjects.
  • No Thumbnail Available
    Item
    [18F]PR04.MZ PET/CT Imaging for Evaluation of Nigrostriatal Neuron Integrity in Patients With Parkinson Disease
    (2021) Juri, Carlos; Kramer, Vasko; Riss, Patrick J.; Soza-Ried, Cristian; Haeger, Arlette; Pruzzo, Rossana; Rosch, Frank; Amaral, Horacio; Chana-Cuevas, Pedro
    Introduction