Convolutional neural networks for the identification of regions of interests in PET scans: A study of representation learning for diagnosing Alzheimer's disease

Alzheimer’s Disease Neuroimaging Initiative

doi:10.1007/978-3-319-59758-4_36

Convolutional neural networks for the identification of regions of interests in PET scans: A study of representation learning for diagnosing Alzheimer's disease

Alzheimer’s Disease Neuroimaging Initiative

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

When diagnosing patients suffering from dementia based on imaging data like PET scans, the identification of suitable predictive regions of interest (ROIs) is of great importance. We present a case study of 3-D Convolutional Neural Networks (CNNs) for the detection of ROIs in this context, just using voxel data, without any knowledge given a priori. Our results on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) suggest that the predictive performance of the method is on par with that of state-of-the-art methods, with the additional benefit of potential insights into affected brain regions.

Original language	English
Title of host publication	Artificial Intelligence in Medicine
Subtitle of host publication	AIME 2017
Pages	316-321
ISBN (Electronic)	9783319597584
DOIs	https://doi.org/10.1007/978-3-319-59758-4_36
Publication status	E-pub ahead of print - 30 May 2017
Event	AIME 2017: 16th Conference on Artificial Intelligence in Medicine - Vienna, Austria Duration: 17 Jun 2017 → 24 Jun 2017 http://aime17.aimedicine.info/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10259

Conference

Conference	AIME 2017
Country/Territory	Austria
City	Vienna
Period	17/06/17 → 24/06/17
Internet address	http://aime17.aimedicine.info/

Keywords

alzheimer
deep learning
machine learning
medicine
visualization

Access to Document

10.1007/978-3-319-59758-4_36

Cite this

Alzheimer’s Disease Neuroimaging Initiative (2017). Convolutional neural networks for the identification of regions of interests in PET scans: A study of representation learning for diagnosing Alzheimer's disease. In Artificial Intelligence in Medicine: AIME 2017 (pp. 316-321). (Lecture Notes in Computer Science; Vol. 10259). Advance online publication. https://doi.org/10.1007/978-3-319-59758-4_36

@inproceedings{524db492c1fd4e75bd0efbd09139c8af,

title = "Convolutional neural networks for the identification of regions of interests in PET scans: A study of representation learning for diagnosing Alzheimer's disease",

abstract = "When diagnosing patients suffering from dementia based on imaging data like PET scans, the identification of suitable predictive regions of interest (ROIs) is of great importance. We present a case study of 3-D Convolutional Neural Networks (CNNs) for the detection of ROIs in this context, just using voxel data, without any knowledge given a priori. Our results on data from the Alzheimer{\textquoteright}s Disease Neuroimaging Initiative (ADNI) suggest that the predictive performance of the method is on par with that of state-of-the-art methods, with the additional benefit of potential insights into affected brain regions.",

keywords = "alzheimer, deep learning, machine learning, medicine, visualization",

author = "Andreas Karwath and Markus Hubrich and Stefan Kramer and {Alzheimer{\textquoteright}s Disease Neuroimaging Initiative}",

year = "2017",

month = may,

day = "30",

doi = "10.1007/978-3-319-59758-4_36",

language = "English",

isbn = "9783319597577",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "316--321",

booktitle = "Artificial Intelligence in Medicine",

note = "AIME 2017 : 16th Conference on Artificial Intelligence in Medicine ; Conference date: 17-06-2017 Through 24-06-2017",

url = "http://aime17.aimedicine.info/",

}

Alzheimer’s Disease Neuroimaging Initiative 2017, Convolutional neural networks for the identification of regions of interests in PET scans: A study of representation learning for diagnosing Alzheimer's disease. in Artificial Intelligence in Medicine: AIME 2017. Lecture Notes in Computer Science, vol. 10259, pp. 316-321, AIME 2017, Vienna, Austria, 17/06/17. https://doi.org/10.1007/978-3-319-59758-4_36

Convolutional neural networks for the identification of regions of interests in PET scans: A study of representation learning for diagnosing Alzheimer's disease. / Alzheimer’s Disease Neuroimaging Initiative.
Artificial Intelligence in Medicine: AIME 2017. 2017. p. 316-321 (Lecture Notes in Computer Science; Vol. 10259).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Convolutional neural networks for the identification of regions of interests in PET scans

T2 - AIME 2017

AU - Karwath, Andreas

AU - Hubrich, Markus

AU - Kramer, Stefan

AU - Alzheimer’s Disease Neuroimaging Initiative

PY - 2017/5/30

Y1 - 2017/5/30

N2 - When diagnosing patients suffering from dementia based on imaging data like PET scans, the identification of suitable predictive regions of interest (ROIs) is of great importance. We present a case study of 3-D Convolutional Neural Networks (CNNs) for the detection of ROIs in this context, just using voxel data, without any knowledge given a priori. Our results on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) suggest that the predictive performance of the method is on par with that of state-of-the-art methods, with the additional benefit of potential insights into affected brain regions.

AB - When diagnosing patients suffering from dementia based on imaging data like PET scans, the identification of suitable predictive regions of interest (ROIs) is of great importance. We present a case study of 3-D Convolutional Neural Networks (CNNs) for the detection of ROIs in this context, just using voxel data, without any knowledge given a priori. Our results on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) suggest that the predictive performance of the method is on par with that of state-of-the-art methods, with the additional benefit of potential insights into affected brain regions.

KW - alzheimer

KW - deep learning

KW - machine learning

KW - medicine

KW - visualization

U2 - 10.1007/978-3-319-59758-4_36

DO - 10.1007/978-3-319-59758-4_36

M3 - Conference contribution

SN - 9783319597577

T3 - Lecture Notes in Computer Science

SP - 316

EP - 321

BT - Artificial Intelligence in Medicine

Y2 - 17 June 2017 through 24 June 2017

ER -

Convolutional neural networks for the identification of regions of interests in PET scans: A study of representation learning for diagnosing Alzheimer's disease

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this