Consistent Brain Ageing Synthesis

Alzheimers Disease Neuroimaging Initiative

Consistent Brain Ageing Synthesis

Alzheimers Disease Neuroimaging Initiative

School of Engineering

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

Abstract

Brain ageing is associated with morphological changes and cognitive degeneration, and can be affected by neurodegenerative dis- eases which can accelerate the ageing process. The ability to separate accelerated from healthy ageing is useful from a diagnostic perspective and towards developing subject-specific models of progression. In this paper we start with the ‘simpler’ problem of synthesising age-progressed 2D slices. We adopt adversarial training to learn the joint distribution of brain images and ages, and simulate aged images by a network condi- tioned on age (a continuous variable) encoded as an ordinal embedding vector. We introduce a loss to help preserve subject identity despite that we train with cross-sectional (unpaired) data. To evaluate the quality of aged images, a pre-trained age predictor is used to estimate an appar- ent age. We show qualitatively and quantitatively that our method can progressively synthesise realistic brain images of different target ages.

Original language	English
Title of host publication	Medical Image Computing and Computer Assisted Intervention -MICCAI 2019
Subtitle of host publication	22nd International Conference, Shenzhen, China 13-17 October 2019
Publisher	Springer
Publication status	Published - 13 Oct 2019
Event	22nd International Conference on Medical Image Computing and Computer Assisted Intervention - InterContinental Shenzhen, Shenzhen, China Duration: 13 Oct 2019 → 17 Oct 2019 Conference number: 22 https://www.miccai2019.org/

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	22nd International Conference on Medical Image Computing and Computer Assisted Intervention
Abbreviated title	MICCAI 2019
Country/Territory	China
City	Shenzhen
Period	13/10/19 → 17/10/19
Internet address	https://www.miccai2019.org/

Access to Document

Tian_MICCAI_2019Accepted author manuscript, 4.53 MB

Canon Medical / RAEng Senior Research Fellow in Healthcare AI
Tsaftaris, S.
Canon Medical Research Europe Limited
31/03/19 → 30/06/26
Project: Research
Funding from the EPSRC (EP/P0229281), project title: Machine learning for the analysis of multimodal cardiac MR images used in the diagnosis of coronary heart disease. £ 100.904, PI: Dr. Sotirios Tsaftaris, 2017 (grant associate, researcher)
Papanastasiou, G.
1/09/17 → …
Project: Research Collaboration with external organisation

Cite this

@inproceedings{a2472c0052614366bec40303ee800078,

title = "Consistent Brain Ageing Synthesis",

abstract = "Brain ageing is associated with morphological changes and cognitive degeneration, and can be affected by neurodegenerative dis- eases which can accelerate the ageing process. The ability to separate accelerated from healthy ageing is useful from a diagnostic perspective and towards developing subject-specific models of progression. In this paper we start with the {\textquoteleft}simpler{\textquoteright} problem of synthesising age-progressed 2D slices. We adopt adversarial training to learn the joint distribution of brain images and ages, and simulate aged images by a network condi- tioned on age (a continuous variable) encoded as an ordinal embedding vector. We introduce a loss to help preserve subject identity despite that we train with cross-sectional (unpaired) data. To evaluate the quality of aged images, a pre-trained age predictor is used to estimate an appar- ent age. We show qualitatively and quantitatively that our method can progressively synthesise realistic brain images of different target ages.",

author = "Tian Xia and Agisilaos Chartsias and Sotirios Tsaftaris and {Alzheimers Disease Neuroimaging Initiative}",

note = "Acceptance date set to exclude from REF OA Policy; 22nd International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2019 ; Conference date: 13-10-2019 Through 17-10-2019",

year = "2019",

month = oct,

day = "13",

language = "English",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

booktitle = "Medical Image Computing and Computer Assisted Intervention -MICCAI 2019",

address = "United Kingdom",

url = "https://www.miccai2019.org/",

}

Alzheimers Disease Neuroimaging Initiative 2019, Consistent Brain Ageing Synthesis. in Medical Image Computing and Computer Assisted Intervention -MICCAI 2019: 22nd International Conference, Shenzhen, China 13-17 October 2019. Lecture Notes in Computer Science, Springer, 22nd International Conference on Medical Image Computing and Computer Assisted Intervention, Shenzhen, China, 13/10/19.

TY - GEN

T1 - Consistent Brain Ageing Synthesis

AU - Xia, Tian

AU - Chartsias, Agisilaos

AU - Tsaftaris, Sotirios

AU - Alzheimers Disease Neuroimaging Initiative

N1 - Conference code: 22

PY - 2019/10/13

Y1 - 2019/10/13

N2 - Brain ageing is associated with morphological changes and cognitive degeneration, and can be affected by neurodegenerative dis- eases which can accelerate the ageing process. The ability to separate accelerated from healthy ageing is useful from a diagnostic perspective and towards developing subject-specific models of progression. In this paper we start with the ‘simpler’ problem of synthesising age-progressed 2D slices. We adopt adversarial training to learn the joint distribution of brain images and ages, and simulate aged images by a network condi- tioned on age (a continuous variable) encoded as an ordinal embedding vector. We introduce a loss to help preserve subject identity despite that we train with cross-sectional (unpaired) data. To evaluate the quality of aged images, a pre-trained age predictor is used to estimate an appar- ent age. We show qualitatively and quantitatively that our method can progressively synthesise realistic brain images of different target ages.

AB - Brain ageing is associated with morphological changes and cognitive degeneration, and can be affected by neurodegenerative dis- eases which can accelerate the ageing process. The ability to separate accelerated from healthy ageing is useful from a diagnostic perspective and towards developing subject-specific models of progression. In this paper we start with the ‘simpler’ problem of synthesising age-progressed 2D slices. We adopt adversarial training to learn the joint distribution of brain images and ages, and simulate aged images by a network condi- tioned on age (a continuous variable) encoded as an ordinal embedding vector. We introduce a loss to help preserve subject identity despite that we train with cross-sectional (unpaired) data. To evaluate the quality of aged images, a pre-trained age predictor is used to estimate an appar- ent age. We show qualitatively and quantitatively that our method can progressively synthesise realistic brain images of different target ages.

M3 - Conference contribution

T3 - Lecture Notes in Computer Science

BT - Medical Image Computing and Computer Assisted Intervention -MICCAI 2019

PB - Springer

T2 - 22nd International Conference on Medical Image Computing and Computer Assisted Intervention

Y2 - 13 October 2019 through 17 October 2019

ER -

Consistent Brain Ageing Synthesis

Abstract

Publication series

Conference

Access to Document

Fingerprint

Projects

Canon Medical / RAEng Senior Research Fellow in Healthcare AI

Funding from the EPSRC (EP/P0229281), project title: Machine learning for the analysis of multimodal cardiac MR images used in the diagnosis of coronary heart disease. £ 100.904, PI: Dr. Sotirios Tsaftaris, 2017 (grant associate, researcher)

Cite this