Skip to main navigation Skip to search Skip to main content

Multiple instance cancer detection by boosting regularised trees

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

617 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 languageEnglish
Title of host publicationMedical Image Computing and Computer-Assisted Intervention (MICCAI 2015)
Subtitle of host publication18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part 1
EditorsNassir Navab, Joachim Hornegger, William M. Wells, Alejandro F. Frangi
PublisherSpringer
Pages645-652
Number of pages8
Volume9349
ISBN (Electronic)9783319245539
ISBN (Print)9783319245522
DOIs
Publication statusPublished - 2015
EventMedical Image Computing and Computer Assisted Interventions18th International Conference - Munich, Germany
Duration: 5 Oct 2015 → 9 Oct 2015

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume9349

Conference

ConferenceMedical Image Computing and Computer Assisted Interventions18th International Conference
Country/TerritoryGermany
CityMunich
Period5/10/15 → 9/10/15

UN SDGs

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

  1. SDG 3 - Good Health and Well-being
    SDG 3 Good Health and Well-being

Fingerprint

Dive into the research topics of 'Multiple instance cancer detection by boosting regularised trees'. Together they form a unique fingerprint.

Cite this