CLASSIFICATION OF BREAST CANCER

MALIGNANCY USING
CYTOLOGICAL IMAGES OF FINE NEEDLE
ASPIRATION BIOPSIES
Breast cancer is the most often diagnosed
cancer among women aged 40 to 60.
According to the World Health Organization
there are 7.6 million deaths worldwide due to
cancer each year, out of which 502,000 are
caused by breast cancer alone.
Cancers in their early stages are vulnerable to
treatment while cancers in their most advanced
stages are usually almost impossible to treat.
The most common diagnostic tools are mammography
and a fine needle aspiration biopsy (FNA).
Mammography, which is a non-invasive method, is most
often used for screening purposes rather than for precise
diagnosis.
It allows a physician to find possible locations of
microcalcifications and other indicators in breast tissue.
When a suspicious region is found, the patient is sent to
a pathologist for a more precise diagnosis. This is when
the FNA is taken.
A fine needle aspiration biopsy is an invasive method to
extract a small sample of the questionable breast tissue
that allows the pathologist to describe the type of the
cancer in detail.
Using this method pathologists can very adequately
describe not only the type of the cancer but also its
genealogy and malignancy.
The stage of cancer depends on the malignancy factor
that is assigned during an FNA examination. The
determination of malignancy is essential when predicting
the progression of cancer.
Block diagram of the cell classification system
Segmentation
Feature Extraction
Classification
Cell images
Application of PR Technique
in image segmentation
Fuzzy c-means clustering
The FCM clustering algorithm assigns a fuzzy
membership value to each data point based on its
proximity to the cluster centroids in the feature space.
FCM is a clustering algorithm, but the resulting partition
is fuzzy.
The input feature vectors are not assigned exclusively to
a single class, but partially to all classes.
If a single class must be chosen, the data point chosen
should be in the class with the higher membership
grade.
This is called defuzzification and yields a crisp label.
The FCM algorithm assumes that the number of clusters
c is known and minimizes the objective function to find
the best set of cluster centers.
Fuzzy c- means clustering
The standard FCM objective function for partitioning x
k
,k=1,2,N into c
clusters is given by
The parameter m

is a weighing exponent on each fuzzy membership and

determines the amount of fuzziness of the resulting classification.
The FCM objective function is minimized when high membership values
are assigned to pixels whose intensities are close to the centroid
of its particular class, and low membership values are assigned
when the pixel data are far from the centroid.
The cluster centers are calculated using
Fuzzy c-means Algorithm
Example
x1=(1, 3) x2=(1.5, 3.2)
x3=(1.3, 2.8) x4=(3, 1)