Radiological classification of dementia from anatomical MRI assisted by machine learning-derived maps - 11/11/21
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
| pages | 7 |
| Iconographies | 2 |
| Vidéos | 0 |
| Autres | 0 |
Graphical abstract |
Highlights |
• | Artificial intelligence tools have good performance to diagnose dementia from magnetic resonance imaging. |
• | These tools are so far difficult to integrate in the clinical routine workflow. |
• | Weight maps extracted from automatic classification, can highlight relevant atrophic areas. |
• | The weight maps could easily be integrated to clinical practice. |
Abstract |
Background and purpose |
Many artificial intelligence tools are currently being developed to assist diagnosis of dementia from magnetic resonance imaging (MRI). However, these tools have so far been difficult to integrate in the clinical routine workflow. In this work, we propose a new simple way to use them and assess their utility for improving diagnostic accuracy.
Materials and methods |
We studied 34 patients with early-onset Alzheimer's disease (EOAD), 49 with late-onset AD (LOAD), 39 with frontotemporal dementia (FTD) and 24 with depression from the pre-existing cohort CLIN-AD. Support vector machine (SVM) automatic classifiers using 3D T1 MRI were trained to distinguish: LOAD vs. Depression, FTD vs. LOAD, EOAD vs. Depression, EOAD vs. FTD. We extracted SVM weight maps, which are tridimensional representations of discriminant atrophy patterns used by the classifier to take its decisions and we printed posters of these maps. Four radiologists (2 senior neuroradiologists and 2 unspecialized junior radiologists) performed a visual classification of the 4 diagnostic pairs using 3D T1 MRI. Classifications were performed twice: first with standard radiological reading and then using SVM weight maps as a guide.
Results |
Diagnostic performance was significantly improved by the use of the weight maps for the two junior radiologists in the case of FTD vs. EOAD. Improvement was over 10 points of diagnostic accuracy.
Conclusion |
This tool can improve the diagnostic accuracy of junior radiologists and could be integrated in the clinical routine workflow.
Le texte complet de cet article est disponible en PDF.Keywords : Alzheimer's disease, Dementia, Diagnosis, Anatomical MRI, Artificial intelligence
Abbreviations : EOAD, LOAD, FTD, SWM, GLMM, WMs, WBGM, AI, IWG, CV
Plan
Vol 48 - N° 6
P. 412-418 - novembre 2021 Retour au numéro
Article précédent
- A roadmap towards pollution prevention and sustainable development of Gadolinium
- Julien Ognard, Jean-Alix Barrat, François Cotton, Asim Mian, Stéphane Kremer, Yih Yian Sitoh, Sébastien Verclytte, Romaric Loffroy, Raphaël Tripier, Zarrin Alavi, Douraied Ben Salem
- Chorea-acanthocytosis: Time-dependent changes of symptoms and imaging findings
- Fumio Suzuki, Noriko Sato, Atsuhiko Sugiyama, Keiya Iijima, Yoko Shigemoto, Emiko Morimoto, Yukio Kimura, Hiroyuki Fujii, Yuji Takahashi, Yasuhiro Nakata, Hiroshi Matsuda, Osamu Abe
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’achat d’article à l’unité est indisponible à l’heure actuelle.
Déjà abonné à cette revue ?