HomeWhy Challenges?All ChallengesCreate Your Own ChallengeContributorsForum
Sign in / Register

 

Team: Department of Computer Science and Engineering, The Chinese University of Hong Kong, Sha Tin, Hong Kong

Authors: Hao Chen, Huang-Jing Lin, Qi Dou, and Pheng-Ann Heng

Abstract:

In this ISBI challenge, we developed a multi-scale deep contextual network for automatic metastasis detection. Taking advantage of powerful feature representation and end-to-end learning framework, multi-level contextual information were explored by deep supervision. We first search the regions of interest with threshold, then segment the metastasis masks utilizing the deep contextual network, a variant of fully convolutional network. Moreover, we extend it into multi-scale resolutions, hence the results can be further improved.

Results:

The following figure shows the receiver operating characteristic (ROC) curve of the method.

 

The following figure shows the free-response receiver operating characteristic (FROC) curve of the method.

 

The table below presents the average sensitivity of the developed system at 6 predefined false positive rates: 1/4, 1/2, 1, 2, 4, and 8 FPs per whole slide image.

FPs/WSI0.250.51248
Sensitivity0.4040.4710.4930.5820.6310.684


Consortium for Open Medical Image Computing © 2012-