The International Symposium on Biomedical Imaging (ISBI) held a grand
challenge to evaluate computational systems for the automated detection of
metastatic breast cancer in whole slide images of sentinel lymph node biopsies.
Our team won both competitions in the grand challenge, obtaining an area under
the receiver operating curve (AUC) of 0.925 for the task of whole slide image
classification and a score of 0.7051 for the tumor localization task. A
pathologist independently reviewed the same images, obtaining a whole slide
image classification AUC of 0.966 and a tumor localization score of 0.733.
Combining our deep learning system's predictions with the human pathologist's
diagnoses increased the pathologist's AUC to 0.995, representing an
approximately 85 percent reduction in human error rate. These results
demonstrate the power of using deep learning to produce significant
improvements in the accuracy of pathological diagnoses.
Description
Deep Learning for Identifying Metastatic Breast Cancer
%0 Generic
%1 wang2016learning
%A Wang, Dayong
%A Khosla, Aditya
%A Gargeya, Rishab
%A Irshad, Humayun
%A Beck, Andrew H.
%D 2016
%K Cancer Deep Detection Learning Lymph Metastasis Node
%T Deep Learning for Identifying Metastatic Breast Cancer
%U http://arxiv.org/abs/1606.05718
%X The International Symposium on Biomedical Imaging (ISBI) held a grand
challenge to evaluate computational systems for the automated detection of
metastatic breast cancer in whole slide images of sentinel lymph node biopsies.
Our team won both competitions in the grand challenge, obtaining an area under
the receiver operating curve (AUC) of 0.925 for the task of whole slide image
classification and a score of 0.7051 for the tumor localization task. A
pathologist independently reviewed the same images, obtaining a whole slide
image classification AUC of 0.966 and a tumor localization score of 0.733.
Combining our deep learning system's predictions with the human pathologist's
diagnoses increased the pathologist's AUC to 0.995, representing an
approximately 85 percent reduction in human error rate. These results
demonstrate the power of using deep learning to produce significant
improvements in the accuracy of pathological diagnoses.
@preprint{wang2016learning,
abstract = {The International Symposium on Biomedical Imaging (ISBI) held a grand
challenge to evaluate computational systems for the automated detection of
metastatic breast cancer in whole slide images of sentinel lymph node biopsies.
Our team won both competitions in the grand challenge, obtaining an area under
the receiver operating curve (AUC) of 0.925 for the task of whole slide image
classification and a score of 0.7051 for the tumor localization task. A
pathologist independently reviewed the same images, obtaining a whole slide
image classification AUC of 0.966 and a tumor localization score of 0.733.
Combining our deep learning system's predictions with the human pathologist's
diagnoses increased the pathologist's AUC to 0.995, representing an
approximately 85 percent reduction in human error rate. These results
demonstrate the power of using deep learning to produce significant
improvements in the accuracy of pathological diagnoses.},
added-at = {2016-06-21T19:13:50.000+0200},
author = {Wang, Dayong and Khosla, Aditya and Gargeya, Rishab and Irshad, Humayun and Beck, Andrew H.},
biburl = {https://www.bibsonomy.org/bibtex/2b611b06af0117e7914cc191f533b7558/humayun.irshad},
description = {Deep Learning for Identifying Metastatic Breast Cancer},
interhash = {36bbb5bb3ba83d200f7db86c2f8c53d7},
intrahash = {b611b06af0117e7914cc191f533b7558},
keywords = {Cancer Deep Detection Learning Lymph Metastasis Node},
note = {cite arxiv:1606.05718},
timestamp = {2016-06-21T19:13:50.000+0200},
title = {Deep Learning for Identifying Metastatic Breast Cancer},
url = {http://arxiv.org/abs/1606.05718},
year = 2016
}