Radiological classification of dementia from anatomical MRI assisted by machine learning-derived maps

Pierre Chagué (1, 2) , Béatrice Marro (2) , Sarah Fadili (2) , Marion Houot (3) , Alexandre Morin (3, 1) , Jorge Samper-González (1) , Paul Beunon (2) , Lionel Arrivé (2) , Didier Dormont (4, 1) , Bruno Dubois (3, 3) , Marc Teichmann (5, 3) , Stephane Epelbaum (3, 1) , Olivier Colliot (1)

1 ARAMIS - Algorithms, models and methods for images and signals of the human brain = Algorithmes, modèles et méthodes pour les images et les signaux du cerveau humain [ICM Paris]
2 CHU Saint-Antoine [AP-HP]
3 CHU Pitié-Salpêtrière [AP-HP]
4 ICM - Institut du Cerveau = Paris Brain Institute
5 FRONTlab - Equipe Fonctions et dysfonctions de systèmes frontaux [ICM Paris]

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.

Mots clés: Machine learning; Alzheimer's disease; Dementia; anatomical MRI; artificial intelligence; diagnosis

Domaines: Neurobiologie; Imagerie; Traitement des images [eess.IV]; Imagerie médicale; Vision par ordinateur et reconnaissance de formes [cs.CV]; Traitement du signal et de l'image [eess.SP]

Pierre Chagué, Béatrice Marro, Sarah Fadili, Marion Houot, Alexandre Morin, et al.. Radiological classification of dementia from anatomical MRI assisted by machine learning-derived maps. Journal de Neuroradiologie / Journal of Neuroradiology, 2021, 48 (6), pp.412-418. ⟨10.1016/j.neurad.2020.04.004⟩. ⟨hal-02641005⟩