b'

\n\t\xc2\xa0

\n\tb'

\n

\n

\n\tAbstract:

\n

\n

\n\tIn 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.\n\n

\n\tResults:

'\n

\n\tThe following figure shows the receiver operating characteristic (ROC) curve of the method.

\n

\n

\n

\n

\n\t\xc2\xa0

\n

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

\n
\n

\n\t\xc2\xa0

\n

\n\tThe 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.

\n

Error rendering graph from file

'