Multiple Instance Cancer Detection by Boosting Regularised Trees.

Wenqi Li, Jianguo Zhang, Stephen J. McKennaMICCAI 2015 · OpenReview

Abstract

We propose a novel multiple instance learning algorithm for cancer detection in histopathology images. With images labelled at image-level, we first 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.
BibTeX
@inproceedings{li2015multiple,
  author = {Wenqi Li and Jianguo Zhang and Stephen J. McKenna},
  title = {{Multiple Instance Cancer Detection by Boosting Regularised Trees.}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2015},
  url = {https://openreview.net/forum?id=qrcNQXNpt9},
}
Figure