Multiple instance cancer detection by boosting regularised trees

Wenqi Li; Jianguo Zhang; Stephen McKenna

doi:10.1007/978-3-319-24553-9_79

Multiple instance cancer detection by boosting regularised trees

Wenqi Li, Jianguo Zhang, Stephen McKenna

Computing

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

18 Citations (Scopus)

510 Downloads (Pure)

Abstract

We propose a novel multiple instance learning algorithm for cancer detection in histopathology images. With images labelled at image-level, we rst search a set of region-level prototypes by solving a submodular set cover problem. Regularised regression trees are then constructed and combined on the set of prototypes using a multiple instance boosting framework. The method compared favourably with competing methods in experiments on breast cancer tissue microarray images and optical tomographic images of colorectal polyps.

Original language	English
Title of host publication	Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015)
Subtitle of host publication	18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part 1
Editors	Nassir Navab, Joachim Hornegger, William M. Wells, Alejandro F. Frangi
Publisher	Springer
Pages	645-652
Number of pages	8
Volume	9349
ISBN (Electronic)	9783319245539
ISBN (Print)	9783319245522
DOIs	https://doi.org/10.1007/978-3-319-24553-9_79
Publication status	Published - 2015
Event	Medical Image Computing and Computer Assisted Interventions18th International Conference - Munich, Germany Duration: 5 Oct 2015 → 9 Oct 2015

Publication series

Name	Lecture notes in computer science
Publisher	Springer
Volume	9349

Conference

Conference	Medical Image Computing and Computer Assisted Interventions18th International Conference
Country/Territory	Germany
City	Munich
Period	5/10/15 → 9/10/15

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-319-24553-9_79

PrePrint
The final publication is available at Springer via http://10.1007/978-3-319-24553-9_79
Submitted manuscript, 1.43 MB

http://www.springer.com/us/book/9783319245737

Embargoed Document

opt_miccai15_acceptedversion Not for public display
Accepted author manuscript, 1.33 MB
Embargo ends: 31/12/99

Embargoed Document

Preprint Not for Public Display
Submitted manuscript, 1.34 MB
Embargo ends: 31/12/99

Analysis of Colorectal Polyps in Optical Projection Tomography
Li, W. (Author), Zhang, J. (Supervisor) & McKenna, S. (Supervisor), 2015
Student thesis: Doctoral Thesis › Doctor of Philosophy

File

Cite this

Li, W., Zhang, J., & McKenna, S. (2015). Multiple instance cancer detection by boosting regularised trees. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015): 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part 1 (Vol. 9349, pp. 645-652). (Lecture notes in computer science ; Vol. 9349). Springer . https://doi.org/10.1007/978-3-319-24553-9_79

Li, Wenqi ; Zhang, Jianguo ; McKenna, Stephen. / Multiple instance cancer detection by boosting regularised trees. Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015): 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part 1. editor / Nassir Navab ; Joachim Hornegger ; William M. Wells ; Alejandro F. Frangi. Vol. 9349 Springer , 2015. pp. 645-652 (Lecture notes in computer science ).

@inbook{788b85c6c6c24efc8281da3a899d84dd,

title = "Multiple instance cancer detection by boosting regularised trees",

abstract = "We propose a novel multiple instance learning algorithm for cancer detection in histopathology images. With images labelled at image-level, we rst search a set of region-level prototypes by solving a submodular set cover problem. Regularised regression trees are then constructed and combined on the set of prototypes using a multiple instance boosting framework. The method compared favourably with competing methods in experiments on breast cancer tissue microarray images and optical tomographic images of colorectal polyps.",

author = "Wenqi Li and Jianguo Zhang and Stephen McKenna",

year = "2015",

doi = "10.1007/978-3-319-24553-9\_79",

language = "English",

isbn = "9783319245522",

volume = "9349",

series = "Lecture notes in computer science ",

publisher = "Springer ",

pages = "645--652",

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

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

note = "Medical Image Computing and Computer Assisted Interventions18th International Conference ; Conference date: 05-10-2015 Through 09-10-2015",

}

Li, W, Zhang, J & McKenna, S 2015, Multiple instance cancer detection by boosting regularised trees. in N Navab, J Hornegger, WM Wells & AF Frangi (eds), Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015): 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part 1. vol. 9349, Lecture notes in computer science , vol. 9349, Springer , pp. 645-652, Medical Image Computing and Computer Assisted Interventions18th International Conference, Munich, Germany, 5/10/15. https://doi.org/10.1007/978-3-319-24553-9_79

Multiple instance cancer detection by boosting regularised trees. / Li, Wenqi; Zhang, Jianguo; McKenna, Stephen.
Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015): 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part 1. ed. / Nassir Navab; Joachim Hornegger; William M. Wells; Alejandro F. Frangi. Vol. 9349 Springer , 2015. p. 645-652 (Lecture notes in computer science ; Vol. 9349).

Research output: Chapter in Book/Report/Conference proceeding › Chapter (peer-reviewed) › peer-review

TY - CHAP

T1 - Multiple instance cancer detection by boosting regularised trees

AU - Li, Wenqi

AU - Zhang, Jianguo

AU - McKenna, Stephen

PY - 2015

Y1 - 2015

N2 - We propose a novel multiple instance learning algorithm for cancer detection in histopathology images. With images labelled at image-level, we rst search a set of region-level prototypes by solving a submodular set cover problem. Regularised regression trees are then constructed and combined on the set of prototypes using a multiple instance boosting framework. The method compared favourably with competing methods in experiments on breast cancer tissue microarray images and optical tomographic images of colorectal polyps.

AB - We propose a novel multiple instance learning algorithm for cancer detection in histopathology images. With images labelled at image-level, we rst search a set of region-level prototypes by solving a submodular set cover problem. Regularised regression trees are then constructed and combined on the set of prototypes using a multiple instance boosting framework. The method compared favourably with competing methods in experiments on breast cancer tissue microarray images and optical tomographic images of colorectal polyps.

U2 - 10.1007/978-3-319-24553-9_79

DO - 10.1007/978-3-319-24553-9_79

M3 - Chapter (peer-reviewed)

SN - 9783319245522

VL - 9349

T3 - Lecture notes in computer science

SP - 645

EP - 652

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

T2 - Medical Image Computing and Computer Assisted Interventions18th International Conference

Y2 - 5 October 2015 through 9 October 2015

ER -

Li W, Zhang J, McKenna S. Multiple instance cancer detection by boosting regularised trees. In Navab N, Hornegger J, Wells WM, Frangi AF, editors, Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015): 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part 1. Vol. 9349. Springer . 2015. p. 645-652. (Lecture notes in computer science ). doi: 10.1007/978-3-319-24553-9_79

Multiple instance cancer detection by boosting regularised trees

Abstract

Publication series

Conference

UN SDGs

Access to Document

Embargoed Document

Embargoed Document

Fingerprint

Student theses

Analysis of Colorectal Polyps in Optical Projection Tomography

Cite this