Research Article
Histopathological Breast Cancer Image Classification by
Deep Neural Network Techniques Guided by Local Clustering
Abdullah-Al Nahid , Mohamad Ali Mehrabi, and Yinan Kong
School of Engineering, Macquarie University, Sydney, NSW 2109, Australia
Correspondence should be addressed to Abdullah-Al Nahid; abdullah-al.nahid@students.mq.edu.au
Received 30 October 2017; Revised 25 January 2018; Accepted 6 February 2018; Published 7 March 2018
Academic Editor: Wen-Hwa Lee
Copyright © 2018 Abdullah-Al Nahid et al. his is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly
cited.
Breast Cancer is a serious threat and one of the largest causes of death of women throughout the world. he identiication of cancer
largely depends on digital biomedical photography analysis such as histopathological images by doctors and physicians. Analyzing
histopathological images is a nontrivial task, and decisions from investigation of these kinds of images always require specialised
knowledge. However, Computer Aided Diagnosis (CAD) techniques can help the doctor make more reliable decisions. he state-
of-the-art Deep Neural Network (DNN) has been recently introduced for biomedical image analysis. Normally each image contains
structural and statistical information. his paper classiies a set of biomedical breast cancer images (BreakHis dataset) using novel
DNN techniques guided by structural and statistical information derived from the images. Speciically a Convolutional Neural
Network (CNN), a Long-Short-Term-Memory (LSTM), and a combination of CNN and LSTM are proposed for breast cancer image
classiication. Sotmax and Support Vector Machine (SVM) layers have been used for the decision-making stage ater extracting
features utilising the proposed novel DNN models. In this experiment the best Accuracy value of 91.00% is achieved on the 200x
dataset, the best Precision value 96.00% is achieved on the 40x dataset, and the best F-Measure value is achieved on both the 40x
and 100x datasets.
1. Introduction
he unwanted growth of cells causes cancer which is a serious
threat to humans. Statistics show that millions of people all
over the world sufer various cancer diseases. As an example
Table 1 summarises the statistics concerning the recent cancer
situation in Australia. hese statistics reveal the number of
newly cancer-afected people diagnosed in Australia and also
the number of people who died in 2017 in Australia. hese
statistics also divulge that the number of females afected and
the number of females dying due to breast cancer are more
than the numbers for males. his indicates that females are
more vulnerable to breast cancer (BC) than males. Although
these statistics are for Australia they might be representative
of what is happening throughout the world.
Proper BC diagnosis can save thousands of women’s lives,
and proper diagnosis largely depends on identiication of the
cancer. Finding BC largely depends on capturing a photo-
graph of the cancer-afected area which gives information
about the current situation of the cancer. A few biomedical
imaging techniques have been utilised, some of which are
noninvasive such as Ultrasound imaging, X-ray imaging,
and Computer Aided Tomography (CAT) imaging. Other
imaging techniques are invasive such as histopathological
images. Investigation of these kinds of images is always
very challenging, especially in the case of histopathological
imaging due to its complex nature. Histopathological image
analysis is nontrivial, and the investigation of this kind
of image always produces some contradictory decisions by
doctors. Since doctors and physicians are human, it is natural
that errors will occur.
A Computer Aided Diagnosis (CAD) system provides
doctors and physicians with valuable information, for exam-
ple, classiication of the disease. Diferent research groups
investigate opportunities to improve the CAD systems’ per-
formance. Some advanced engineering techniques have been
utilised to take a general image classiier and adjust it as a
biomedical image classiier, such as a breast image classiier.
Hindawi
BioMed Research International
Volume 2018, Article ID 2362108, 20 pages
https://doi.org/10.1155/2018/2362108