Whole Slide Image Classification via Iterative Patch Labelling

Chaoyi Zhang, Yang Song, Donghao Zhang, Sidong Liu, Mei Chen, Weidong Cai

Abstract

Brain tumor can be a fatal disease in the world. With the aim of improving survival rates, many computerized algorithms have been proposed to assist the pathologists to make a diagnosis' using Whole Slide Pathology Images (WSI). Most methods focus on performing patch-level classification and aggregating the patch-level results to obtain the image classification. Since not all patches carry diagnostic information, it is thus important for our algorithm to recognize discriminative and non-discriminative patches. In this study, we propose an iterative patch labelling algorithm based on the Convolutional Neural Network (CNN), with a well-designed thresholding scheme, a training policy and a novel discriminative model architecture, to distinguish patches and use the discriminative ones to achieve WSI -classification. Our method is evaluated on the MICCAI 2015 Challenge Dataset, and shows a large improvement over the baseline approaches.
BibTeX
@inproceedings{zhang2018whole,
  author = {Chaoyi Zhang and Yang Song and Donghao Zhang and Sidong Liu and Mei Chen and Weidong Cai},
  title = {{Whole Slide Image Classification via Iterative Patch Labelling}},
  booktitle = {ICIP},
  year = {2018},
  doi = {10.1109/icip.2018.8451551},
}

Loading related content...

Figure