Cargando…
A Machine Learning–Based Approach to Discrimination of Tauopathies Using [ (18)F]PM‐PBB3 PET Images
BACKGROUND: We recently developed a positron emission tomography (PET) probe, [(18)F]PM‐PBB3, to detect tau lesions in diverse tauopathies, including mixed three‐repeat and four‐repeat (3R + 4R) tau fibrils in Alzheimer's disease (AD) and 4R tau aggregates in progressive supranuclear palsy (PSP...
Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley & Sons, Inc.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9805085/ https://www.ncbi.nlm.nih.gov/pubmed/36054492 http://dx.doi.org/10.1002/mds.29173 |
_version_ | 1784862262084763648 |
---|---|
author | Endo, Hironobu Tagai, Kenji Ono, Maiko Ikoma, Yoko Oyama, Asaka Matsuoka, Kiwamu Kokubo, Naomi Hirata, Kosei Sano, Yasunori Oya, Masaki Matsumoto, Hideki Kurose, Shin Seki, Chie Shimizu, Hiroshi Kakita, Akiyoshi Takahata, Keisuke Shinotoh, Hitoshi Shimada, Hitoshi Tokuda, Takahiko Kawamura, Kazunori Zhang, Ming‐Rong Oishi, Kenichi Mori, Susumu Takado, Yuhei Higuchi, Makoto |
author_facet | Endo, Hironobu Tagai, Kenji Ono, Maiko Ikoma, Yoko Oyama, Asaka Matsuoka, Kiwamu Kokubo, Naomi Hirata, Kosei Sano, Yasunori Oya, Masaki Matsumoto, Hideki Kurose, Shin Seki, Chie Shimizu, Hiroshi Kakita, Akiyoshi Takahata, Keisuke Shinotoh, Hitoshi Shimada, Hitoshi Tokuda, Takahiko Kawamura, Kazunori Zhang, Ming‐Rong Oishi, Kenichi Mori, Susumu Takado, Yuhei Higuchi, Makoto |
author_sort | Endo, Hironobu |
collection | PubMed |
description | BACKGROUND: We recently developed a positron emission tomography (PET) probe, [(18)F]PM‐PBB3, to detect tau lesions in diverse tauopathies, including mixed three‐repeat and four‐repeat (3R + 4R) tau fibrils in Alzheimer's disease (AD) and 4R tau aggregates in progressive supranuclear palsy (PSP). For wider availability of this technology for clinical settings, bias‐free quantitative evaluation of tau images without a priori disease information is needed. OBJECTIVE: We aimed to establish tau PET pathology indices to characterize PSP and AD using a machine learning approach and test their validity and tracer capabilities. METHODS: Data were obtained from 50 healthy control subjects, 46 patients with PSP Richardson syndrome, and 37 patients on the AD continuum. Tau PET data from 114 regions of interest were subjected to Elastic Net cross‐validation linear classification analysis with a one‐versus‐the‐rest multiclass strategy to obtain a linear function that discriminates diseases by maximizing the area under the receiver operating characteristic curve. We defined PSP‐ and AD‐tau scores for each participant as values of the functions optimized for differentiating PSP (4R) and AD (3R + 4R), respectively, from others. RESULTS: The discriminatory ability of PSP‐ and AD‐tau scores assessed as the area under the receiver operating characteristic curve was 0.98 and 1.00, respectively. PSP‐tau scores correlated with the PSP rating scale in patients with PSP, and AD‐tau scores correlated with Mini‐Mental State Examination scores in healthy control–AD continuum patients. The globus pallidus and amygdala were highlighted as regions with high weight coefficients for determining PSP‐ and AD‐tau scores, respectively. CONCLUSIONS: These findings highlight our technology's unbiased capability to identify topologies of 3R + 4R versus 4R tau deposits. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society |
format | Online Article Text |
id | pubmed-9805085 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | John Wiley & Sons, Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-98050852023-01-06 A Machine Learning–Based Approach to Discrimination of Tauopathies Using [ (18)F]PM‐PBB3 PET Images Endo, Hironobu Tagai, Kenji Ono, Maiko Ikoma, Yoko Oyama, Asaka Matsuoka, Kiwamu Kokubo, Naomi Hirata, Kosei Sano, Yasunori Oya, Masaki Matsumoto, Hideki Kurose, Shin Seki, Chie Shimizu, Hiroshi Kakita, Akiyoshi Takahata, Keisuke Shinotoh, Hitoshi Shimada, Hitoshi Tokuda, Takahiko Kawamura, Kazunori Zhang, Ming‐Rong Oishi, Kenichi Mori, Susumu Takado, Yuhei Higuchi, Makoto Mov Disord Research Articles BACKGROUND: We recently developed a positron emission tomography (PET) probe, [(18)F]PM‐PBB3, to detect tau lesions in diverse tauopathies, including mixed three‐repeat and four‐repeat (3R + 4R) tau fibrils in Alzheimer's disease (AD) and 4R tau aggregates in progressive supranuclear palsy (PSP). For wider availability of this technology for clinical settings, bias‐free quantitative evaluation of tau images without a priori disease information is needed. OBJECTIVE: We aimed to establish tau PET pathology indices to characterize PSP and AD using a machine learning approach and test their validity and tracer capabilities. METHODS: Data were obtained from 50 healthy control subjects, 46 patients with PSP Richardson syndrome, and 37 patients on the AD continuum. Tau PET data from 114 regions of interest were subjected to Elastic Net cross‐validation linear classification analysis with a one‐versus‐the‐rest multiclass strategy to obtain a linear function that discriminates diseases by maximizing the area under the receiver operating characteristic curve. We defined PSP‐ and AD‐tau scores for each participant as values of the functions optimized for differentiating PSP (4R) and AD (3R + 4R), respectively, from others. RESULTS: The discriminatory ability of PSP‐ and AD‐tau scores assessed as the area under the receiver operating characteristic curve was 0.98 and 1.00, respectively. PSP‐tau scores correlated with the PSP rating scale in patients with PSP, and AD‐tau scores correlated with Mini‐Mental State Examination scores in healthy control–AD continuum patients. The globus pallidus and amygdala were highlighted as regions with high weight coefficients for determining PSP‐ and AD‐tau scores, respectively. CONCLUSIONS: These findings highlight our technology's unbiased capability to identify topologies of 3R + 4R versus 4R tau deposits. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society John Wiley & Sons, Inc. 2022-08-28 2022-11 /pmc/articles/PMC9805085/ /pubmed/36054492 http://dx.doi.org/10.1002/mds.29173 Text en © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Articles Endo, Hironobu Tagai, Kenji Ono, Maiko Ikoma, Yoko Oyama, Asaka Matsuoka, Kiwamu Kokubo, Naomi Hirata, Kosei Sano, Yasunori Oya, Masaki Matsumoto, Hideki Kurose, Shin Seki, Chie Shimizu, Hiroshi Kakita, Akiyoshi Takahata, Keisuke Shinotoh, Hitoshi Shimada, Hitoshi Tokuda, Takahiko Kawamura, Kazunori Zhang, Ming‐Rong Oishi, Kenichi Mori, Susumu Takado, Yuhei Higuchi, Makoto A Machine Learning–Based Approach to Discrimination of Tauopathies Using [ (18)F]PM‐PBB3 PET Images |
title | A Machine Learning–Based Approach to Discrimination of Tauopathies Using [
(18)F]PM‐PBB3 PET Images |
title_full | A Machine Learning–Based Approach to Discrimination of Tauopathies Using [
(18)F]PM‐PBB3 PET Images |
title_fullStr | A Machine Learning–Based Approach to Discrimination of Tauopathies Using [
(18)F]PM‐PBB3 PET Images |
title_full_unstemmed | A Machine Learning–Based Approach to Discrimination of Tauopathies Using [
(18)F]PM‐PBB3 PET Images |
title_short | A Machine Learning–Based Approach to Discrimination of Tauopathies Using [
(18)F]PM‐PBB3 PET Images |
title_sort | machine learning–based approach to discrimination of tauopathies using [
(18)f]pm‐pbb3 pet images |
topic | Research Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9805085/ https://www.ncbi.nlm.nih.gov/pubmed/36054492 http://dx.doi.org/10.1002/mds.29173 |
work_keys_str_mv | AT endohironobu amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT tagaikenji amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT onomaiko amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT ikomayoko amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT oyamaasaka amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT matsuokakiwamu amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kokubonaomi amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT hiratakosei amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT sanoyasunori amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT oyamasaki amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT matsumotohideki amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kuroseshin amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT sekichie amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT shimizuhiroshi amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kakitaakiyoshi amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT takahatakeisuke amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT shinotohhitoshi amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT shimadahitoshi amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT tokudatakahiko amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kawamurakazunori amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT zhangmingrong amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT oishikenichi amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT morisusumu amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT takadoyuhei amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT higuchimakoto amachinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT endohironobu machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT tagaikenji machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT onomaiko machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT ikomayoko machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT oyamaasaka machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT matsuokakiwamu machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kokubonaomi machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT hiratakosei machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT sanoyasunori machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT oyamasaki machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT matsumotohideki machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kuroseshin machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT sekichie machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT shimizuhiroshi machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kakitaakiyoshi machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT takahatakeisuke machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT shinotohhitoshi machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT shimadahitoshi machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT tokudatakahiko machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT kawamurakazunori machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT zhangmingrong machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT oishikenichi machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT morisusumu machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT takadoyuhei machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages AT higuchimakoto machinelearningbasedapproachtodiscriminationoftauopathiesusing18fpmpbb3petimages |