Pseudo-healthy image synthesis for white matter lesion segmentation

Christopher Bowles, Chen Qin, Christian Ledig, Ricardo Guerrero, Roger Gunn, Alexander Hammers, Eleni Sakka, David Alexander Dickie, Maria Valdés Hernández, Natalie Royle, Joanna Wardlaw, Hanneke Rhodius-Meester, Betty Tijms, Afina W. Lemstra, Wiesje van Der Flier, Frederik Barkhof, Philip Scheltens, Daniel Rueckert

Research output: Contribution to conferencePaperOther research output

Abstract

White matter hyperintensities (WMH) seen on FLAIR images are established as a key indicator of Vascular Dementia (VD) and other pathologies.We propose a novel modality transformation technique to generate a subject-specific pathology-free synthetic FLAIR image from a T1 -weighted image. WMH are then accurately segmented by comparing this synthesized FLAIR image to the actually acquired FLAIR image. We term this method Pseudo-Healthy Image Synthesis (PHI-Syn). The method is evaluated on data from 42 stroke patients where we compare its performance to two commonly used methods from the Lesion Segmentation Toolbox. We show that the proposed method achieves superior performance for a number of metrics. Finally, we show that the features extracted from the WMH segmentations can be used to predict a Fazekas lesion score that supports the identification of VD in a dataset of 468 dementia patients. In this application the automatically calculated features perform comparably to clinically derived Fazekas scores.

Conference

Conference1st International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016
CountryGreece
CityAthens
Period21/10/201621/10/2016

Cite this

Bowles, C., Qin, C., Ledig, C., Guerrero, R., Gunn, R., Hammers, A., ... Rueckert, D. (2016). Pseudo-healthy image synthesis for white matter lesion segmentation. 87-96. Paper presented at 1st International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016, Athens, Greece. https://doi.org/10.1007/978-3-319-46630-9_9
Bowles, Christopher ; Qin, Chen ; Ledig, Christian ; Guerrero, Ricardo ; Gunn, Roger ; Hammers, Alexander ; Sakka, Eleni ; Dickie, David Alexander ; Hernández, Maria Valdés ; Royle, Natalie ; Wardlaw, Joanna ; Rhodius-Meester, Hanneke ; Tijms, Betty ; Lemstra, Afina W. ; van Der Flier, Wiesje ; Barkhof, Frederik ; Scheltens, Philip ; Rueckert, Daniel. / Pseudo-healthy image synthesis for white matter lesion segmentation. Paper presented at 1st International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016, Athens, Greece.10 p.
@conference{1f510540b28c4774980dd42ab47a0a01,
title = "Pseudo-healthy image synthesis for white matter lesion segmentation",
abstract = "White matter hyperintensities (WMH) seen on FLAIR images are established as a key indicator of Vascular Dementia (VD) and other pathologies.We propose a novel modality transformation technique to generate a subject-specific pathology-free synthetic FLAIR image from a T1 -weighted image. WMH are then accurately segmented by comparing this synthesized FLAIR image to the actually acquired FLAIR image. We term this method Pseudo-Healthy Image Synthesis (PHI-Syn). The method is evaluated on data from 42 stroke patients where we compare its performance to two commonly used methods from the Lesion Segmentation Toolbox. We show that the proposed method achieves superior performance for a number of metrics. Finally, we show that the features extracted from the WMH segmentations can be used to predict a Fazekas lesion score that supports the identification of VD in a dataset of 468 dementia patients. In this application the automatically calculated features perform comparably to clinically derived Fazekas scores.",
author = "Christopher Bowles and Chen Qin and Christian Ledig and Ricardo Guerrero and Roger Gunn and Alexander Hammers and Eleni Sakka and Dickie, {David Alexander} and Hern{\'a}ndez, {Maria Vald{\'e}s} and Natalie Royle and Joanna Wardlaw and Hanneke Rhodius-Meester and Betty Tijms and Lemstra, {Afina W.} and {van Der Flier}, Wiesje and Frederik Barkhof and Philip Scheltens and Daniel Rueckert",
year = "2016",
doi = "10.1007/978-3-319-46630-9_9",
language = "English",
pages = "87--96",
note = "1st International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016 ; Conference date: 21-10-2016 Through 21-10-2016",

}

Bowles, C, Qin, C, Ledig, C, Guerrero, R, Gunn, R, Hammers, A, Sakka, E, Dickie, DA, Hernández, MV, Royle, N, Wardlaw, J, Rhodius-Meester, H, Tijms, B, Lemstra, AW, van Der Flier, W, Barkhof, F, Scheltens, P & Rueckert, D 2016, 'Pseudo-healthy image synthesis for white matter lesion segmentation' Paper presented at 1st International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016, Athens, Greece, 21/10/2016 - 21/10/2016, pp. 87-96. https://doi.org/10.1007/978-3-319-46630-9_9

Pseudo-healthy image synthesis for white matter lesion segmentation. / Bowles, Christopher; Qin, Chen; Ledig, Christian; Guerrero, Ricardo; Gunn, Roger; Hammers, Alexander; Sakka, Eleni; Dickie, David Alexander; Hernández, Maria Valdés; Royle, Natalie; Wardlaw, Joanna; Rhodius-Meester, Hanneke; Tijms, Betty; Lemstra, Afina W.; van Der Flier, Wiesje; Barkhof, Frederik; Scheltens, Philip; Rueckert, Daniel.

2016. 87-96 Paper presented at 1st International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016, Athens, Greece.

Research output: Contribution to conferencePaperOther research output

TY - CONF

T1 - Pseudo-healthy image synthesis for white matter lesion segmentation

AU - Bowles, Christopher

AU - Qin, Chen

AU - Ledig, Christian

AU - Guerrero, Ricardo

AU - Gunn, Roger

AU - Hammers, Alexander

AU - Sakka, Eleni

AU - Dickie, David Alexander

AU - Hernández, Maria Valdés

AU - Royle, Natalie

AU - Wardlaw, Joanna

AU - Rhodius-Meester, Hanneke

AU - Tijms, Betty

AU - Lemstra, Afina W.

AU - van Der Flier, Wiesje

AU - Barkhof, Frederik

AU - Scheltens, Philip

AU - Rueckert, Daniel

PY - 2016

Y1 - 2016

N2 - White matter hyperintensities (WMH) seen on FLAIR images are established as a key indicator of Vascular Dementia (VD) and other pathologies.We propose a novel modality transformation technique to generate a subject-specific pathology-free synthetic FLAIR image from a T1 -weighted image. WMH are then accurately segmented by comparing this synthesized FLAIR image to the actually acquired FLAIR image. We term this method Pseudo-Healthy Image Synthesis (PHI-Syn). The method is evaluated on data from 42 stroke patients where we compare its performance to two commonly used methods from the Lesion Segmentation Toolbox. We show that the proposed method achieves superior performance for a number of metrics. Finally, we show that the features extracted from the WMH segmentations can be used to predict a Fazekas lesion score that supports the identification of VD in a dataset of 468 dementia patients. In this application the automatically calculated features perform comparably to clinically derived Fazekas scores.

AB - White matter hyperintensities (WMH) seen on FLAIR images are established as a key indicator of Vascular Dementia (VD) and other pathologies.We propose a novel modality transformation technique to generate a subject-specific pathology-free synthetic FLAIR image from a T1 -weighted image. WMH are then accurately segmented by comparing this synthesized FLAIR image to the actually acquired FLAIR image. We term this method Pseudo-Healthy Image Synthesis (PHI-Syn). The method is evaluated on data from 42 stroke patients where we compare its performance to two commonly used methods from the Lesion Segmentation Toolbox. We show that the proposed method achieves superior performance for a number of metrics. Finally, we show that the features extracted from the WMH segmentations can be used to predict a Fazekas lesion score that supports the identification of VD in a dataset of 468 dementia patients. In this application the automatically calculated features perform comparably to clinically derived Fazekas scores.

UR - http://www.scopus.com/inward/record.url?scp=84994074794&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-46630-9_9

DO - 10.1007/978-3-319-46630-9_9

M3 - Paper

SP - 87

EP - 96

ER -

Bowles C, Qin C, Ledig C, Guerrero R, Gunn R, Hammers A et al. Pseudo-healthy image synthesis for white matter lesion segmentation. 2016. Paper presented at 1st International Workshop on Simulation and Synthesis in Medical Imaging, SASHIMI 2016 held in conjunction with 19th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2016, Athens, Greece. https://doi.org/10.1007/978-3-319-46630-9_9