How serious is data leakage in deep learning studies on Alzheimer's disease classification?

Junhao Wen​ 1 Elina Thibeau--Sutre​ 1 Jorge Samper-González​ 1 Alexandre Routier 1 Simona Bottani​ 1 Didier Dormont​ 1 Stanley Durrleman 1 Olivier Colliot 1 Ninon Burgos 1
1 ARAMIS - Algorithms, models and methods for images and signals of the human brain
SU - Sorbonne Université, Inria de Paris, ICM - Institut du Cerveau et de la Moëlle Epinière = Brain and Spine Institute
Complete list of metadatas

Cited literature [5 references]  Display  Hide  Download

https://hal.inria.fr/hal-02105133
Contributor : Junhao Wen <>
Submitted on : Tuesday, May 21, 2019 - 6:21:28 PM
Last modification on : Friday, May 24, 2019 - 1:13:18 PM

File

OHBM2019 DL_data_leakage.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02105133, version 2

Citation

Junhao Wen​, Elina Thibeau--Sutre​, Jorge Samper-González​, Alexandre Routier, Simona Bottani​, et al.. How serious is data leakage in deep learning studies on Alzheimer's disease classification?. 2019 OHBM Annual meeting - Organization for Human Brain Mapping, Jun 2019, Rome, Italy. ⟨hal-02105133v2⟩

Share

Metrics

Record views

62

Files downloads

328