Deep learning for multi-task medical image segmentation in multiple modalities

P. Moeskops; J.M. Wolterink; B.H.M. van der Velden; K.G.A. Gilhuijs; T. Leiner; M.A. Viergever; I. Išgum

doi:10.1007/978-3-319-46723-8_55

Deep learning for multi-task medical image segmentation in multiple modalities

P. Moeskops, J.M. Wolterink, B.H.M. van der Velden, K.G.A. Gilhuijs, T. Leiner, M.A. Viergever, I. Išgum

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

273 Citations (Scopus)

9 Downloads (Pure)

Abstract

Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks.

A single CNN is trained to segment six tissues in MR brain images, the pectoral muscle in MR breast images, and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality, the visualised anatomical structures, and the tissue classes.

For each of the three tasks (brain MRI, breast MRI and cardiac CTA), this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task, demonstrating the high capacity of CNN architectures. Hence, a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016
Editors	S. Ourselin, L. Joskowicz, M.R. Sabuncu, G. Unal, W. Wells
Publisher	Springer
Pages	478-486
ISBN (Electronic)	978-3-319-46723-8
ISBN (Print)	978-3-319-46722-1
DOIs	https://doi.org/10.1007/978-3-319-46723-8_55
Publication status	Published - 19 Oct 2016
Event	19th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, Athens, Greece, October 17-21, 2016, - Intercontinental Athenaeum, Athens, Greece Duration: 17 Oct 2016 → 21 Oct 2016 http://www.miccai2016.org/en/

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	9901

Conference

Conference	19th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, Athens, Greece, October 17-21, 2016,
Abbreviated title	MICCAI2016
Country/Territory	Greece
City	Athens
Period	17/10/16 → 21/10/16
Internet address	http://www.miccai2016.org/en/

Access to Document

10.1007/978-3-319-46723-8_55

Cite this

Moeskops, P., Wolterink, J. M., van der Velden, B. H. M., Gilhuijs, K. G. A., Leiner, T., Viergever, M. A., & Išgum, I. (2016). Deep learning for multi-task medical image segmentation in multiple modalities. In S. Ourselin, L. Joskowicz, M. R. Sabuncu, G. Unal, & W. Wells (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016 (pp. 478-486). (Lecture notes in computer science; Vol. 9901). Springer. https://doi.org/10.1007/978-3-319-46723-8_55

@inproceedings{7e0add467a1c4121a1092aa6ad5bda82,

title = "Deep learning for multi-task medical image segmentation in multiple modalities",

abstract = "Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks.A single CNN is trained to segment six tissues in MR brain images, the pectoral muscle in MR breast images, and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality, the visualised anatomical structures, and the tissue classes.For each of the three tasks (brain MRI, breast MRI and cardiac CTA), this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task, demonstrating the high capacity of CNN architectures. Hence, a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.",

author = "P. Moeskops and J.M. Wolterink and {van der Velden}, B.H.M. and K.G.A. Gilhuijs and T. Leiner and M.A. Viergever and I. I{\v s}gum",

year = "2016",

month = oct,

day = "19",

doi = "10.1007/978-3-319-46723-8_55",

language = "English",

isbn = "978-3-319-46722-1",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "478--486",

editor = "Ourselin, {S. } and L. Joskowicz and M.R. Sabuncu and G. Unal and W. Wells",

booktitle = "Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016",

address = "Germany",

note = "19th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, Athens, Greece, October 17-21, 2016, , MICCAI2016 ; Conference date: 17-10-2016 Through 21-10-2016",

url = "http://www.miccai2016.org/en/",

}

Moeskops, P, Wolterink, JM, van der Velden, BHM, Gilhuijs, KGA, Leiner, T, Viergever, MA & Išgum, I 2016, Deep learning for multi-task medical image segmentation in multiple modalities. in S Ourselin, L Joskowicz, MR Sabuncu, G Unal & W Wells (eds), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016. Lecture notes in computer science, vol. 9901, Springer, pp. 478-486, 19th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, Athens, Greece, October 17-21, 2016, , Athens, Greece, 17/10/16. https://doi.org/10.1007/978-3-319-46723-8_55

Deep learning for multi-task medical image segmentation in multiple modalities. / Moeskops, P.; Wolterink, J.M.; van der Velden, B.H.M. et al.
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016. ed. / S. Ourselin; L. Joskowicz; M.R. Sabuncu; G. Unal; W. Wells. Springer, 2016. p. 478-486 (Lecture notes in computer science; Vol. 9901).

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

TY - GEN

T1 - Deep learning for multi-task medical image segmentation in multiple modalities

AU - Moeskops, P.

AU - Wolterink, J.M.

AU - van der Velden, B.H.M.

AU - Gilhuijs, K.G.A.

AU - Leiner, T.

AU - Viergever, M.A.

AU - Išgum, I.

PY - 2016/10/19

Y1 - 2016/10/19

N2 - Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks.A single CNN is trained to segment six tissues in MR brain images, the pectoral muscle in MR breast images, and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality, the visualised anatomical structures, and the tissue classes.For each of the three tasks (brain MRI, breast MRI and cardiac CTA), this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task, demonstrating the high capacity of CNN architectures. Hence, a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.

AB - Automatic segmentation of medical images is an important task for many clinical applications. In practice, a wide range of anatomical structures are visualised using different imaging modalities. In this paper, we investigate whether a single convolutional neural network (CNN) can be trained to perform different segmentation tasks.A single CNN is trained to segment six tissues in MR brain images, the pectoral muscle in MR breast images, and the coronary arteries in cardiac CTA. The CNN therefore learns to identify the imaging modality, the visualised anatomical structures, and the tissue classes.For each of the three tasks (brain MRI, breast MRI and cardiac CTA), this combined training procedure resulted in a segmentation performance equivalent to that of a CNN trained specifically for that task, demonstrating the high capacity of CNN architectures. Hence, a single system could be used in clinical practice to automatically perform diverse segmentation tasks without task-specific training.

U2 - 10.1007/978-3-319-46723-8_55

DO - 10.1007/978-3-319-46723-8_55

M3 - Conference contribution

SN - 978-3-319-46722-1

T3 - Lecture notes in computer science

SP - 478

EP - 486

BT - Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016

A2 - Ourselin, S.

A2 - Joskowicz, L.

A2 - Sabuncu, M.R.

A2 - Unal, G.

A2 - Wells, W.

PB - Springer

T2 - 19th International Conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, Athens, Greece, October 17-21, 2016,

Y2 - 17 October 2016 through 21 October 2016

ER -

Moeskops P, Wolterink JM, van der Velden BHM, Gilhuijs KGA, Leiner T, Viergever MA et al. Deep learning for multi-task medical image segmentation in multiple modalities. In Ourselin S, Joskowicz L, Sabuncu MR, Unal G, Wells W, editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016. Springer. 2016. p. 478-486. (Lecture notes in computer science). doi: 10.1007/978-3-319-46723-8_55

Deep learning for multi-task medical image segmentation in multiple modalities

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this