Skip to Main content Skip to Navigation
Master Thesis

Utilisation pratique de l'intelligence artificielle : une classification radiologique de démences à partir d’IRM morphologiques avec assistance par des cartes issues de l'apprentissage automatique

Abstract : Background: many artificial intelligence tools are currently being developed to assist diagnosis of dementia from magnetic resonance imaging (MRI). However, these tools are so far difficult to integrate in the clinical routine workflow. In this work, we propose a new simple way to use them in neuroradiological routine and assess its 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 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 is easy to integrate in the clinical routine workflow.
Document type :
Master Thesis
Complete list of metadatas

https://dumas.ccsd.cnrs.fr/dumas-02990678
Contributor : Université Paris Descartes - Scd <>
Submitted on : Thursday, November 5, 2020 - 4:28:40 PM
Last modification on : Wednesday, February 17, 2021 - 3:19:23 AM

File

ThExe_CHAGUE_Pierre_DUMAS.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International License

Identifiers

  • HAL Id : dumas-02990678, version 1

Citation

Pierre Chagué. Utilisation pratique de l'intelligence artificielle : une classification radiologique de démences à partir d’IRM morphologiques avec assistance par des cartes issues de l'apprentissage automatique. Médecine humaine et pathologie. 2019. ⟨dumas-02990678⟩

Share

Metrics

Record views

3

Files downloads

6