An Explainable Convolutional Neural Network for the Early Diagnosis of Alzheimer's Disease from 18F-FDG PET.
Convolutional Neural Networks (CNN) which support the diagnosis of Alzheimer's Disease using 18F-FDG PET images are obtaining promising results; however, one of the main challenges in this domain is the fact that these models work as black-box systems. We developed a CNN that performs a multiclass c...
| Publicado en: | Journal of Digital Imaging Vol. 36; no. 1; pp. 189 - 204 |
|---|---|
| Autores principales: | , , , , |
| Formato: | diagnostic images equations & formulas pictorial research tables/charts Journal Article |
| Publicado: |
Springer Nature
Feb2023
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=162233268&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 162233268 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Feb2023 vid: 36 iid: 1 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 162233268 160082250 162233268 162233268 10.1007/s10278-022-00719-3 162233268 ppf: 189 ppct: 15 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: An Explainable Convolutional Neural Network for the Early Diagnosis of Alzheimer's Disease from 18F-FDG PET. aug: au: De Santi, Lisa Anita Pasini, Elena Santarelli, Maria Filomena Genovesi, Dario Positano, Vincenzo affil: University of Pisa - Department of Information Engineering, Pisa, Italy sug: subj: Alzheimer's Disease Radiography Early Diagnosis Methods Positron-Emission Tomography Methods Fludeoxyglucose F 18 Diagnostic Use Image Processing, Computer Assisted Methods Neural Networks (Computer) Predictive Value of Tests Human Artificial Intelligence Deep Learning Neuroradiography Prediction Models ROC Curve Post Hoc Analysis ab: Convolutional Neural Networks (CNN) which support the diagnosis of Alzheimer's Disease using 18F-FDG PET images are obtaining promising results; however, one of the main challenges in this domain is the fact that these models work as black-box systems. We developed a CNN that performs a multiclass classification task of volumetric 18F-FDG PET images, and we experimented two different post hoc explanation techniques developed in the field of Explainable Artificial Intelligence: Saliency Map (SM) and Layerwise Relevance Propagation (LRP). Finally, we quantitatively analyze the explanations returned and inspect their relationship with the PET signal. We collected 2552 scans from the Alzheimer's Disease Neuroimaging Initiative labeled as Cognitively Normal (CN), Mild Cognitive Impairment (MCI), and Alzheimer's Disease (AD) and we developed and tested a 3D CNN that classifies the 3D PET scans into its final clinical diagnosis. The model developed achieves, to the best of our knowledge, performances comparable with the relevant literature on the test set, with an average Area Under the Curve (AUC) for prediction of CN, MCI, and AD 0.81, 0.63, and 0.77 respectively. We registered the heatmaps with the Talairach Atlas to perform a regional quantitative analysis of the relationship between heatmaps and PET signals. With the quantitative analysis of the post hoc explanation techniques, we observed that LRP maps were more effective in mapping the importance metrics in the anatomic atlas. No clear relationship was found between the heatmap and the PET signal. pubtype: Academic Journal doctype: diagnostic images equations & formulas pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|