MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set

Elina Thibeau-Sutre; Baptiste Couvy-Duchesne; Didier Dormont; Olivier Colliot; Ninon Burgos

doi:10.1109/ISBI52829.2022.9761504

MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set

Elina Thibeau-Sutre, Baptiste Couvy-Duchesne, Didier Dormont, Olivier Colliot, Ninon Burgos

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

7 Citations (Scopus)

26 Downloads (Pure)

Abstract

The Alzheimer's Disease Neuroimaging Initiative (ADNI) data set has been extensively used for the prediction of the progression of prodromal patients to Alzheimer's disease dementia. However, the deep learning community is not always aware of the biases that may contaminate neuroimaging data sets, which may lead to flawed results. In this case example, we demonstrated how ignoring the magnetic resonance (MR) field strength can bias performance of deep learning prediction when using MR images as input. Finally, we discussed options to overcome this problem.

Original language	English
Title of host publication	MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set
ISBN (Electronic)	978-1-6654-2923-8
DOIs	https://doi.org/10.1109/ISBI52829.2022.9761504
Publication status	Published - 26 Apr 2022
Externally published	Yes
Event	IEEE International Symposium on Biomedical Imaging, ISBI 2022 - Kolkata, India Duration: 28 Mar 2022 → 31 Mar 2022

Conference

Conference	IEEE International Symposium on Biomedical Imaging, ISBI 2022
Abbreviated title	ISBI 2022
Country/Territory	India
City	Kolkata
Period	28/03/22 → 31/03/22

Access to Document

10.1109/ISBI52829.2022.9761504

ISBI_2022___ADNI_field_strength_BIASAccepted author version, 225 KB

Cite this

@inproceedings{08d1456eab3046a797639b2c4a4dd483,

title = "MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set",

abstract = "The Alzheimer's Disease Neuroimaging Initiative (ADNI) data set has been extensively used for the prediction of the progression of prodromal patients to Alzheimer's disease dementia. However, the deep learning community is not always aware of the biases that may contaminate neuroimaging data sets, which may lead to flawed results. In this case example, we demonstrated how ignoring the magnetic resonance (MR) field strength can bias performance of deep learning prediction when using MR images as input. Finally, we discussed options to overcome this problem.",

author = "Elina Thibeau-Sutre and Baptiste Couvy-Duchesne and Didier Dormont and Olivier Colliot and Ninon Burgos",

year = "2022",

month = apr,

day = "26",

doi = "10.1109/ISBI52829.2022.9761504",

language = "English",

booktitle = "MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set",

note = "IEEE International Symposium on Biomedical Imaging, ISBI 2022, ISBI 2022 ; Conference date: 28-03-2022 Through 31-03-2022",

}

Thibeau-Sutre, E, Couvy-Duchesne, B, Dormont, D, Colliot, O & Burgos, N 2022, MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set. in MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set. IEEE International Symposium on Biomedical Imaging, ISBI 2022, Kolkata, India, 28/03/22. https://doi.org/10.1109/ISBI52829.2022.9761504

MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set. / Thibeau-Sutre, Elina; Couvy-Duchesne, Baptiste; Dormont, Didier et al.
MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set. 2022.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set

AU - Thibeau-Sutre, Elina

AU - Couvy-Duchesne, Baptiste

AU - Dormont, Didier

AU - Colliot, Olivier

AU - Burgos, Ninon

PY - 2022/4/26

Y1 - 2022/4/26

N2 - The Alzheimer's Disease Neuroimaging Initiative (ADNI) data set has been extensively used for the prediction of the progression of prodromal patients to Alzheimer's disease dementia. However, the deep learning community is not always aware of the biases that may contaminate neuroimaging data sets, which may lead to flawed results. In this case example, we demonstrated how ignoring the magnetic resonance (MR) field strength can bias performance of deep learning prediction when using MR images as input. Finally, we discussed options to overcome this problem.

AB - The Alzheimer's Disease Neuroimaging Initiative (ADNI) data set has been extensively used for the prediction of the progression of prodromal patients to Alzheimer's disease dementia. However, the deep learning community is not always aware of the biases that may contaminate neuroimaging data sets, which may lead to flawed results. In this case example, we demonstrated how ignoring the magnetic resonance (MR) field strength can bias performance of deep learning prediction when using MR images as input. Finally, we discussed options to overcome this problem.

U2 - 10.1109/ISBI52829.2022.9761504

DO - 10.1109/ISBI52829.2022.9761504

M3 - Conference contribution

BT - MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set

T2 - IEEE International Symposium on Biomedical Imaging, ISBI 2022

Y2 - 28 March 2022 through 31 March 2022

ER -

MRI field strength predicts Alzheimer's disease: a case example of bias in the ADNI data set

Abstract

Conference

Access to Document

Fingerprint

Cite this