Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning

Liang Chen; Tong Tong; Chin Pang Ho; Rajiv Patel; David Cohen; Angela C. Dawson; Omid Halse; Olivia Geraghty; Paul E.M. Rinne; Christopher J. White; Tagore Nakornchai; Paul Bentley; Daniel Rueckert

doi:10.1007/978-3-319-24553-9_64

Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning

Liang Chen
, Tong Tong
, Chin Pang Ho
, Rajiv Patel
, David Cohen
, Angela C. Dawson
, Omid Halse
, Olivia Geraghty
, Paul E.M. Rinne
, Christopher J. White
, Tagore Nakornchai
, Paul Bentley
, Daniel Rueckert

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 12 - Chapter in an edited book (Author) › peer-review

16 Citations (Scopus)

Abstract

Cerebral small vessel disease (SVD) is a common cause of ageing-associated physical and cognitive impairment. Identifying SVD is important for both clinical and research purposes but is usually dependent on radiologists’ evaluation of brain scans. Computer tomography (CT) is the most widely used brain imaging technique but for SVD it shows a low signal-to-noise ratio, and consequently poor inter-rater reliability. We therefore propose a novel framework based on multiple instance learning (MIL) to distinguish between absent/mild SVD and moderate/severe SVD. Intensity patches are extracted from regions with high probability of containing lesions. These are then used as instances in MIL for the identification of SVD. A large baseline CT dataset, consisting of 590 CT scans, was used for evaluation. We achieved approximately 75% accuracy in classifying two different types of SVD, which is high for this challenging problem. Our results outperform those obtained by either standard machine learning methods or current clinical practice.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015
Subtitle of host publication	18th International Conference, Proceedings
Editors	Nassir Navab, Joachim Hornegger, William M. Wells, Alejandro F. Frangi
Publisher	Springer Verlag
Pages	523-530
ISBN (Electronic)	978-3-319-24553-9
ISBN (Print)	978-3-319-24552-2
DOIs	https://doi.org/10.1007/978-3-319-24553-9_64
Publication status	Published - 2015
Externally published	Yes
Event	18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2015) - Munich, Germany Duration: 5 Oct 2015 → 9 Oct 2015 https://www.miccai2015.org/frontend/index.php?sub=22

Publication series

Name	Lecture Notes in Computer Science
Volume	9349
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2015)
Abbreviated title	MICCAI 2015
Place	Germany
City	Munich
Period	5/10/15 → 9/10/15
Internet address	https://www.miccai2015.org/frontend/index.php?sub=22

Access Output

10.1007/978-3-319-24553-9_64

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Chen, L., Tong, T., Ho, C. P., Patel, R., Cohen, D., Dawson, A. C., Halse, O., Geraghty, O., Rinne, P. E. M., White, C. J., Nakornchai, T., Bentley, P., & Rueckert, D. (2015). Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Proceedings (pp. 523-530). (Lecture Notes in Computer Science; Vol. 9349). Springer Verlag. https://doi.org/10.1007/978-3-319-24553-9_64

Chen, Liang ; Tong, Tong ; Ho, Chin Pang et al. / Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Proceedings. editor / Nassir Navab ; Joachim Hornegger ; William M. Wells ; Alejandro F. Frangi. Springer Verlag, 2015. pp. 523-530 (Lecture Notes in Computer Science).

@inbook{bdc590bf61d64a4782de4da75f653c86,

title = "Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning",

abstract = "Cerebral small vessel disease (SVD) is a common cause of ageing-associated physical and cognitive impairment. Identifying SVD is important for both clinical and research purposes but is usually dependent on radiologists{\textquoteright} evaluation of brain scans. Computer tomography (CT) is the most widely used brain imaging technique but for SVD it shows a low signal-to-noise ratio, and consequently poor inter-rater reliability. We therefore propose a novel framework based on multiple instance learning (MIL) to distinguish between absent/mild SVD and moderate/severe SVD. Intensity patches are extracted from regions with high probability of containing lesions. These are then used as instances in MIL for the identification of SVD. A large baseline CT dataset, consisting of 590 CT scans, was used for evaluation. We achieved approximately 75\% accuracy in classifying two different types of SVD, which is high for this challenging problem. Our results outperform those obtained by either standard machine learning methods or current clinical practice.",

author = "Liang Chen and Tong Tong and Ho, \{Chin Pang\} and Rajiv Patel and David Cohen and Dawson, \{Angela C.\} and Omid Halse and Olivia Geraghty and Rinne, \{Paul E.M.\} and White, \{Christopher J.\} and Tagore Nakornchai and Paul Bentley and Daniel Rueckert",

year = "2015",

doi = "10.1007/978-3-319-24553-9\_64",

language = "English",

isbn = "978-3-319-24552-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer Verlag",

pages = "523--530",

editor = "Nassir Navab and Joachim Hornegger and Wells, \{William M.\} and Frangi, \{Alejandro F.\}",

booktitle = "Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015",

address = "Germany",

note = "18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2015), MICCAI 2015 ; Conference date: 05-10-2015 Through 09-10-2015",

url = "https://www.miccai2015.org/frontend/index.php?sub=22",

}

Chen, L, Tong, T, Ho, CP, Patel, R, Cohen, D, Dawson, AC, Halse, O, Geraghty, O, Rinne, PEM, White, CJ, Nakornchai, T, Bentley, P & Rueckert, D 2015, Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning. in N Navab, J Hornegger, WM Wells & AF Frangi (eds), Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Proceedings. Lecture Notes in Computer Science, vol. 9349, Springer Verlag, pp. 523-530, 18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2015), Munich, Germany, 5/10/15. https://doi.org/10.1007/978-3-319-24553-9_64

Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning. / Chen, Liang; Tong, Tong; Ho, Chin Pang et al.
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Proceedings. ed. / Nassir Navab; Joachim Hornegger; William M. Wells; Alejandro F. Frangi. Springer Verlag, 2015. p. 523-530 (Lecture Notes in Computer Science; Vol. 9349).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 12 - Chapter in an edited book (Author) › peer-review

TY - CHAP

T1 - Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning

AU - Chen, Liang

AU - Tong, Tong

AU - Ho, Chin Pang

AU - Patel, Rajiv

AU - Cohen, David

AU - Dawson, Angela C.

AU - Halse, Omid

AU - Geraghty, Olivia

AU - Rinne, Paul E.M.

AU - White, Christopher J.

AU - Nakornchai, Tagore

AU - Bentley, Paul

AU - Rueckert, Daniel

PY - 2015

Y1 - 2015

N2 - Cerebral small vessel disease (SVD) is a common cause of ageing-associated physical and cognitive impairment. Identifying SVD is important for both clinical and research purposes but is usually dependent on radiologists’ evaluation of brain scans. Computer tomography (CT) is the most widely used brain imaging technique but for SVD it shows a low signal-to-noise ratio, and consequently poor inter-rater reliability. We therefore propose a novel framework based on multiple instance learning (MIL) to distinguish between absent/mild SVD and moderate/severe SVD. Intensity patches are extracted from regions with high probability of containing lesions. These are then used as instances in MIL for the identification of SVD. A large baseline CT dataset, consisting of 590 CT scans, was used for evaluation. We achieved approximately 75% accuracy in classifying two different types of SVD, which is high for this challenging problem. Our results outperform those obtained by either standard machine learning methods or current clinical practice.

AB - Cerebral small vessel disease (SVD) is a common cause of ageing-associated physical and cognitive impairment. Identifying SVD is important for both clinical and research purposes but is usually dependent on radiologists’ evaluation of brain scans. Computer tomography (CT) is the most widely used brain imaging technique but for SVD it shows a low signal-to-noise ratio, and consequently poor inter-rater reliability. We therefore propose a novel framework based on multiple instance learning (MIL) to distinguish between absent/mild SVD and moderate/severe SVD. Intensity patches are extracted from regions with high probability of containing lesions. These are then used as instances in MIL for the identification of SVD. A large baseline CT dataset, consisting of 590 CT scans, was used for evaluation. We achieved approximately 75% accuracy in classifying two different types of SVD, which is high for this challenging problem. Our results outperform those obtained by either standard machine learning methods or current clinical practice.

UR - https://www.scopus.com/pages/publications/84947442380

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84947442380&origin=recordpage

U2 - 10.1007/978-3-319-24553-9_64

DO - 10.1007/978-3-319-24553-9_64

M3 - RGC 12 - Chapter in an edited book (Author)

SN - 978-3-319-24552-2

T3 - Lecture Notes in Computer Science

SP - 523

EP - 530

BT - Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015

A2 - Navab, Nassir

A2 - Hornegger, Joachim

A2 - Wells, William M.

A2 - Frangi, Alejandro F.

PB - Springer Verlag

T2 - 18th International Conference on Medical Image Computing and Computer Assisted Interventions (MICCAI 2015)

Y2 - 5 October 2015 through 9 October 2015

ER -

Chen L, Tong T, Ho CP, Patel R, Cohen D, Dawson AC et al. Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning. In Navab N, Hornegger J, Wells WM, Frangi AF, editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Proceedings. Springer Verlag. 2015. p. 523-530. (Lecture Notes in Computer Science). Epub 2015 Nov 18. doi: 10.1007/978-3-319-24553-9_64

Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning

Abstract

Publication series

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this