Image-based machine learning model as a tool for classification of [18F]PR04.MZ PET images in patients with parkinsonian syndrome

Simple item page
dc.article.number100232
dc.catalogadoryvc
dc.contributor.authorJiménez, María
dc.contributor.authorSoza Ried, Cristian
dc.contributor.authorKramer, Vasko
dc.contributor.authorRíos, Sebastián A.
dc.contributor.authorHaeger, Arlette
dc.contributor.authorJuri Clavería, Carlos Andres
dc.contributor.authorAmaral, Horacio
dc.contributor.authorChana Cuevas, Pedro
dc.date.accessioned2025-06-18T22:37:13Z
dc.date.available2025-06-18T22:37:13Z
dc.date.issued2025
dc.description.abstractParkinsonian 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.
dc.description.funderANID/FONDECYT No. 1220908
dc.fechaingreso.objetodigital2025-06-18
dc.format.extent10 páginas
dc.fuente.origenScopus
dc.identifier.doi10.1016/j.ibmed.2025.100232
dc.identifier.issn2666-5212
dc.identifier.scopusidScopus_ID: 86000643134
dc.identifier.urihttps://doi.org/10.1016/j.ibmed.2025.100232
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/104691
dc.information.autorucEscuela de Medicina; Juri Clavería, Carlos Andres; 0000-0002-1939-5976; 7476
dc.language.isoen
dc.nota.accesocontenido completo
dc.publisherElsevier B.V.
dc.revistaIntelligence-Based Medicine
dc.rightsacceso abierto
dc.rights.licenseCC BY-NC-ND
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectMachine learning
dc.subjectParkinson's disease
dc.subjectPositron emission tomography
dc.subject[18F]PR04.MZ PET tracer
dc.subject.ddc610
dc.subject.ods03 Good health and well-being
dc.subject.odspa03 Salud y bienestar
dc.titleImage-based machine learning model as a tool for classification of [18F]PR04.MZ PET images in patients with parkinsonian syndrome
dc.typeartículo
dc.volumen11
sipa.codpersvinculados7476
sipa.trazabilidadScopus;2025-03-23
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Parkinson.pdf
Size:
5.02 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas