7 / 28
Pathology 2018
Research & Reviews: Journal of Medical and Health Sciences
ISSN: 2319-9865
Page 62
October 08-09, 2018
Edinburgh, Scotland
17
th
International Conference on
Pathology & Cancer
Epidemiology
C
ancer is the second important morbidity and mortality factor
among women and the most incident type is breast cancer.
The diagnosis of biopsy tissue with hematoxylin and eosin (H&E)
stained images is non-trivial and specialists often disagree on
the final diagnosis. Actually, computer-aided diagnosis systems
contribute to reduce the cost and increase the efficiency of this
process. Therefore, we have established a diagnostic tool based
on a deep-learning framework for the screening of patients with
invasive ductal carcinoma. The dataset of tissue slides used in
this project consists of 30,000 samples from eligible patients
in our hospital. Available tissue samples above were split into a
training set, for learning the CNN parameters, and test set, for
evaluating its performance. An accuracy of 94% was obtained
for non-cancer (i.e. normal or benign) vs. malignant (i.e. invasive
carcinoma). This will be helping specialists identify cancerization
which is not visible under a single microscope, and this is just the
start of what we have planned.
Biography
Weidong Xie is a inventor, founder and CEO of DM Intelligence. Following
graduation from Imperial College London with honor in Biological Medicine
he took office as Associate Professor in Sun Yat-sen University and Direc-
tor/PI in St. Jude Children‘s Research Hospital, USA. His research results in
regards to T-cell viral immunity which is listed as the remarkable scientific
breakthroughs by famous journals. After a decade of experience in small
molecule drug discovery, he leads technology startups successfully and AI
in medical imaging & pathology diagnosis is the key point he focuses on.
wdxie@rukingbiotech.comWeidong Xie
1
, Anjia Han
2
, Xunzhang Wang
3
, Tiantian Zhen
2
, Yan Yang
1
, Huijuan
Shi
2
, Elyas Mamatkadir
1
and
Jinwen Wang
3
1
The First Affiliated Hospital, Sun Yat-sen University, China
2
Sun Yat-sen University, China
3
DM Intelligence Ltd., China
Weidong Xie et al., RRJMHS 2018
Volume: 7
Classification of breast cancer histology images using deep
learning
Figure:
The prediction results of 2 samples in the validation
set AI(the black box)vs. pathologists (the yellow box).