Zobrazit v EDS

Automatic Classification of Conclusions from Multi-Tracer Reports of PET Brain Imaging in Cognitive Impairment

Uloženo v:
Podrobná bibliografie
Název: Automatic Classification of Conclusions from Multi-Tracer Reports of PET Brain Imaging in Cognitive Impairment
Autoři: Goldman, Jean-Philippe, Jane Soler, Pablo, Zaghir, Jamil, Andrade Teixeira, Eliluane Perazio, Peretti, Debora, Garibotto, Valentina, Lovis, Christian
Zdroj: Studies in Health Technology and Informatics ISBN: 9781643685335
Informace o vydavateli: IOS Press, 2024.
Rok vydání: 2024
Témata: Support Vector Machine, 616.0757, Brain / diagnostic imaging, Cognitive Dysfunction / classification, Brain, Reproducibility of Results, Sensitivity and Specificity, Machine Learning, Alzheimer Disease, Positron-Emission Tomography, Text classification, Brain molecular imaging reports, Humans, Cognitive Dysfunction / diagnostic imaging, Cognitive Dysfunction, Nuclear Medicine, Alzheimer Disease / classification, Alzheimer Disease / diagnostic imaging, Switzerland, Natural Language Processing
Popis: The goal of this paper is to build an automatic way to interpret conclusions from brain molecular imaging reports performed for investigation of cognitive disturbances (FDG, Amyloid and Tau PET) by comparing several traditional machine learning (ML) techniques-based text classification methods. Two purposes are defined: to identify positive or negative results in all three modalities, and to extract diagnostic impressions for Alzheimer’s Disease (AD), Fronto-Temporal Dementia (FTD), Lewy Bodies Dementia (LBD) based on metabolism of perfusion patterns. A dataset was created by manual parallel annotation of 1668 conclusions of reports from the Nuclear Medicine and Molecular Imaging Division of Geneva University Hospitals. The 6 Machine Learning (ML) algorithms (Support Vector Machine (Linear and Radial Basis function), Naive Bayes, Logistic Regression, Random Forrest, and K-Nearest Neighbors) were trained and evaluated with a 5-fold cross-validation scheme to assess their performance and generalizability. The best classifier was SVM showing the following accuracies: FDG (0.97), Tau (0.94), Amyloid (0.98), Oriented Diagnostic (0.87 for a diagnosis among AD, FTD, LBD, undetermined, other), paving the way for a paradigm shift in the field of data handling in nuclear medicine research.
Druh dokumentu: Part of book or chapter of book
Article
Popis souboru: application/pdf
DOI: 10.3233/shti240476
Přístupová URL adresa: https://pubmed.ncbi.nlm.nih.gov/39176804
https://archive-ouverte.unige.ch/unige:180154
https://doi.org/10.3233/shti240476
Rights: CC BY NC
Přístupové číslo: edsair.doi.dedup.....d9986cc135d65f05af04cc77d8cb0e29
Databáze: OpenAIRE
Popis
Abstrakt:The goal of this paper is to build an automatic way to interpret conclusions from brain molecular imaging reports performed for investigation of cognitive disturbances (FDG, Amyloid and Tau PET) by comparing several traditional machine learning (ML) techniques-based text classification methods. Two purposes are defined: to identify positive or negative results in all three modalities, and to extract diagnostic impressions for Alzheimer’s Disease (AD), Fronto-Temporal Dementia (FTD), Lewy Bodies Dementia (LBD) based on metabolism of perfusion patterns. A dataset was created by manual parallel annotation of 1668 conclusions of reports from the Nuclear Medicine and Molecular Imaging Division of Geneva University Hospitals. The 6 Machine Learning (ML) algorithms (Support Vector Machine (Linear and Radial Basis function), Naive Bayes, Logistic Regression, Random Forrest, and K-Nearest Neighbors) were trained and evaluated with a 5-fold cross-validation scheme to assess their performance and generalizability. The best classifier was SVM showing the following accuracies: FDG (0.97), Tau (0.94), Amyloid (0.98), Oriented Diagnostic (0.87 for a diagnosis among AD, FTD, LBD, undetermined, other), paving the way for a paradigm shift in the field of data handling in nuclear medicine research.
DOI:10.3233/shti240476