Cargando…
Automated differential diagnosis of dementia syndromes using FDG PET and machine learning
BACKGROUND: Metabolic brain imaging with 2-[(18)F]fluoro-2-deoxy-D-glucose positron emission tomography (FDG PET) is a supportive diagnostic and differential diagnostic tool for neurodegenerative dementias. In the clinic, scans are usually visually interpreted. However, computer-aided approaches can...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9667048/ https://www.ncbi.nlm.nih.gov/pubmed/36408106 http://dx.doi.org/10.3389/fnagi.2022.1005731 |
_version_ | 1784831642893811712 |
---|---|
author | Perovnik, Matej Vo, An Nguyen, Nha Jamšek, Jan Rus, Tomaž Tang, Chris C. Trošt, Maja Eidelberg, David |
author_facet | Perovnik, Matej Vo, An Nguyen, Nha Jamšek, Jan Rus, Tomaž Tang, Chris C. Trošt, Maja Eidelberg, David |
author_sort | Perovnik, Matej |
collection | PubMed |
description | BACKGROUND: Metabolic brain imaging with 2-[(18)F]fluoro-2-deoxy-D-glucose positron emission tomography (FDG PET) is a supportive diagnostic and differential diagnostic tool for neurodegenerative dementias. In the clinic, scans are usually visually interpreted. However, computer-aided approaches can improve diagnostic accuracy. We aimed to build two machine learning classifiers, based on two sets of FDG PET-derived features, for differential diagnosis of common dementia syndromes. METHODS: We analyzed FDG PET scans from three dementia cohorts [63 dementia due to Alzheimer’s disease (AD), 79 dementia with Lewy bodies (DLB) and 23 frontotemporal dementia (FTD)], and 41 normal controls (NCs). Patients’ clinical diagnosis at follow-up (25 ± 20 months after scanning) or cerebrospinal fluid biomarkers for Alzheimer’s disease was considered a gold standard. FDG PET scans were first visually evaluated. Scans were pre-processed, and two sets of features extracted: (1) the expressions of previously identified metabolic brain patterns, and (2) the mean uptake value in 95 regions of interest (ROIs). Two multi-class support vector machine (SVM) classifiers were tested and their diagnostic performance assessed and compared to visual reading. Class-specific regional feature importance was assessed with Shapley Additive Explanations. RESULTS: Pattern- and ROI-based classifier achieved higher overall accuracy than expert readers (78% and 80% respectively, vs. 71%). Both SVM classifiers performed similarly to one another and to expert readers in AD (F1 = 0.74, 0.78, and 0.78) and DLB (F1 = 0.81, 0.81, and 0.78). SVM classifiers outperformed expert readers in FTD (F1 = 0.87, 0.83, and 0.63), but not in NC (F1 = 0.71, 0.75, and 0.92). Visualization of the SVM model showed bilateral temporal cortices and cerebellum to be the most important features for AD; occipital cortices, hippocampi and parahippocampi, amygdala, and middle temporal lobes for DLB; bilateral frontal cortices, middle and anterior cingulum for FTD; and bilateral angular gyri, pons, and vermis for NC. CONCLUSION: Multi-class SVM classifiers based on the expression of characteristic metabolic brain patterns or ROI glucose uptake, performed better than experts in the differential diagnosis of common dementias using FDG PET scans. Experts performed better in the recognition of normal scans and a combined approach may yield optimal results in the clinical setting. |
format | Online Article Text |
id | pubmed-9667048 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-96670482022-11-17 Automated differential diagnosis of dementia syndromes using FDG PET and machine learning Perovnik, Matej Vo, An Nguyen, Nha Jamšek, Jan Rus, Tomaž Tang, Chris C. Trošt, Maja Eidelberg, David Front Aging Neurosci Aging Neuroscience BACKGROUND: Metabolic brain imaging with 2-[(18)F]fluoro-2-deoxy-D-glucose positron emission tomography (FDG PET) is a supportive diagnostic and differential diagnostic tool for neurodegenerative dementias. In the clinic, scans are usually visually interpreted. However, computer-aided approaches can improve diagnostic accuracy. We aimed to build two machine learning classifiers, based on two sets of FDG PET-derived features, for differential diagnosis of common dementia syndromes. METHODS: We analyzed FDG PET scans from three dementia cohorts [63 dementia due to Alzheimer’s disease (AD), 79 dementia with Lewy bodies (DLB) and 23 frontotemporal dementia (FTD)], and 41 normal controls (NCs). Patients’ clinical diagnosis at follow-up (25 ± 20 months after scanning) or cerebrospinal fluid biomarkers for Alzheimer’s disease was considered a gold standard. FDG PET scans were first visually evaluated. Scans were pre-processed, and two sets of features extracted: (1) the expressions of previously identified metabolic brain patterns, and (2) the mean uptake value in 95 regions of interest (ROIs). Two multi-class support vector machine (SVM) classifiers were tested and their diagnostic performance assessed and compared to visual reading. Class-specific regional feature importance was assessed with Shapley Additive Explanations. RESULTS: Pattern- and ROI-based classifier achieved higher overall accuracy than expert readers (78% and 80% respectively, vs. 71%). Both SVM classifiers performed similarly to one another and to expert readers in AD (F1 = 0.74, 0.78, and 0.78) and DLB (F1 = 0.81, 0.81, and 0.78). SVM classifiers outperformed expert readers in FTD (F1 = 0.87, 0.83, and 0.63), but not in NC (F1 = 0.71, 0.75, and 0.92). Visualization of the SVM model showed bilateral temporal cortices and cerebellum to be the most important features for AD; occipital cortices, hippocampi and parahippocampi, amygdala, and middle temporal lobes for DLB; bilateral frontal cortices, middle and anterior cingulum for FTD; and bilateral angular gyri, pons, and vermis for NC. CONCLUSION: Multi-class SVM classifiers based on the expression of characteristic metabolic brain patterns or ROI glucose uptake, performed better than experts in the differential diagnosis of common dementias using FDG PET scans. Experts performed better in the recognition of normal scans and a combined approach may yield optimal results in the clinical setting. Frontiers Media S.A. 2022-11-02 /pmc/articles/PMC9667048/ /pubmed/36408106 http://dx.doi.org/10.3389/fnagi.2022.1005731 Text en Copyright © 2022 Perovnik, Vo, Nguyen, Jamšek, Rus, Tang, Trošt and Eidelberg. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Aging Neuroscience Perovnik, Matej Vo, An Nguyen, Nha Jamšek, Jan Rus, Tomaž Tang, Chris C. Trošt, Maja Eidelberg, David Automated differential diagnosis of dementia syndromes using FDG PET and machine learning |
title | Automated differential diagnosis of dementia syndromes using FDG PET and machine learning |
title_full | Automated differential diagnosis of dementia syndromes using FDG PET and machine learning |
title_fullStr | Automated differential diagnosis of dementia syndromes using FDG PET and machine learning |
title_full_unstemmed | Automated differential diagnosis of dementia syndromes using FDG PET and machine learning |
title_short | Automated differential diagnosis of dementia syndromes using FDG PET and machine learning |
title_sort | automated differential diagnosis of dementia syndromes using fdg pet and machine learning |
topic | Aging Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9667048/ https://www.ncbi.nlm.nih.gov/pubmed/36408106 http://dx.doi.org/10.3389/fnagi.2022.1005731 |
work_keys_str_mv | AT perovnikmatej automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning AT voan automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning AT nguyennha automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning AT jamsekjan automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning AT rustomaz automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning AT tangchrisc automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning AT trostmaja automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning AT eidelbergdavid automateddifferentialdiagnosisofdementiasyndromesusingfdgpetandmachinelearning |