Final Breast Cancer

SIR C R REDDY COLLEGE OF ENGINEERING
Department of Computer Science and Engineering
DETECTION OF BREAST CANCER USING DEEP LEARNING
Submitted by
Under the guidance of N.Sunil Kumar (19B81A05C3)
Mrs.B.Rama Lakshmi, P.Lahari (19B81A05C4)
M.Tech Assistant Professor P.Sesha Sai (19B81A05C5)
P.M.R.Bhupathi (19B81A05C6)
Contents
 Abstract
 Problem Statement
 Literature Review
 Existing system
 Proposed system
 System requirements
Abstract
 Artificial intelligence and machine learning have been used effectively in
detection and treatment of several dangerous diseases.
 Deep learning has been useful to analyze the most important features
affecting detection and treatment of serious diseases.
 For example, breast cancer can be detected using genes or histopathological
imaging.
 We systematically reviewed previous work done on detection and treatment
of breast cancer.
Problem statement
 Using radiation it is unable to find the architectural distortion. So

to find this we need a special technique to find the breast cancer.
Our project is to find the breast cancer at early-stage using
architectural distortion as this process leads to find whether a
person has Breast cancer or not.
LITERATURE REVIEW
Title of Paper Description Publication Details
Prediction of Breast Most appropriate method that will IEEE Access
Cancer ,Comparative Review of support the large dataset with good

Machine Learning Techniques and accuracy of prediction.
their Analysis.

Deep learning radiomics in breast Providing Comprehensive overview Elsevier Ltd .All right reserved
cancer with different modalities of the recent research efforts on DLR
2020
in breast cancer with different
modalities and proposed future
directions in this field.
A Genetic algorithm model based on The value of regression and accuracy Elsevier Ltd .All right reserved
artificial neural network for of the GA Based MLP with 9
2012
prediction of the auxilliary lymph features
node status in breast cancer.
A Comprehensive Review for breast Diagnosis and treatment of breast IEEE Access
Histopathology Image Analysis cancer using histopathology images

using classical and Deep Neural contain sufficient phenotypic
Network information.
Gene mutation detection for Breast Analysis of DNA abnormalities from ICIEVE, Volume 9 Issue 1,2019.
cancer disease. blood cell samples to detect cancer
early.
EXISTING SYSTEM AND DRAWBACKS
 Since the 1960s radiologists have noticed that women have unique and widely
variable patterns of breast tissue visible on the mammogram,” says Lehman.
“These patterns can represent the influence of genetics, hormones, pregnancy,
lactation, diet, weight loss, and weight gain. We can now leverage this detailed
information to be more precise in our risk assessment at the individual level.”
 Sometimes, stiffness in the breast after breast cancer due to radiation is mostly
common among women. Other problems that can show up include having
heart diseases as well as certain lung ailments as well.
 The patient also feels tired most of the time after being given radiation therapy.
They turn out to be irritating and feel the victim of sore throat as well.
Proposed System
 So the first step in the cancer diagnosis process is to do what we call it final
needle aspirate or if any process which is simply extracting some of the cells
out of the Tumor. And at that stage, we don’t know if that human is malignant
or benign. And when we say benign that means that the tumor is kind of not
spreading across the bodies of the patient is safe somehow.
 It’s if it’s malignant that means it’s cancerous. That means we need to
intervene and actually stop the cancer growth
 So to find this we need a special technique. that special technique is based on
deep learning which is very easy to find whether a person is affected or not
using algorithm like Convolutional Neural Networks.
HARDWARE AND SOFTWARE REQUIREMENTS
HARDWARE REQUIREMENTS
 Operating system : Windows -Linux

 Processor : Minimum intel i3
 Ram : Minimum 4 GB
 Hard disk : Minimum 250 GB
SOFTWARE REQUIREMENTS
 Python IDLE 3.7 version (or)

 Anaconda 3.7 (or)
 Jupiter (or)
 Google Collab
SYSTEM ARCHITECTURE
Methods:
Logistic regression:
Logistic regression is a data analysis technique that uses mathematics to find the relationships
between two data factors. It then uses this relationship to predict the value of one of those factors
based on the other. The prediction usually has a finite number of outcomes, like yes or no.
Decision trees:
Decision trees help you to evaluate your options. Decision trees are excellent tools for helping
you to choose between several courses of action. They provide a highly effective structure within
which you can lay out options and investigate the possible outcomes of choosing those options.
Random forest:
Random forest is a commonly-used machine learning algorithm trademarked by Leo Breiman
and Adele Cutler, which combines the output of multiple decision trees to reach a single result.
DESIGN
Systems design is the process or art of defining the architecture, components,

modules, interfaces, and data for a system to satisfy specified requirements.
UML DIAGRAMS
 The Unified Modelling Language allows the software engineer to express an
analysis model using the behavior notation that is governed by a set of syntactic
semantic and pragmatic rules.
USE CASE DIAGRAM
CLASS DIAGRAM
STATE CHART DIAGRAM
SEQUENCE DIAGRAM FOR TRAINING FLOW
SEQUENCE DIAGRAM FOR PREDICTION
ACTIVITY DIAGRAM
IMPLEMENTATION
IMPLEMENTATION
IMPLEMENTATION
CONCLUSION
 We have analysed various machine learning techniques to find out best
technique for classification of Histopathological images of breast into benign
and malignant.
 The techniques analysed are logistic regression, decision tree and random
forest.
 The accuracy achieved by
Logistic regression:0.9649122807017544
Decision tree:0.9385964912280702
Random forest:0.9736842105263158
Hence we conclude that the CNN with Random forest algorithm is best
suited for classification of histopathological breast cancer images
Future scope
 One direction is to improve the recognition accuracy of
features using patches, size and the overlapping of patches.
 stain normalization, deeper architectures, and splitting the
network before the last fully-connected layer could be
investigated.
 Additional data with increased number of patients should be
introduced.
 A better investigation on feature and classiﬁer selection
could also improve performance .
THANK YOU

Final Breast Cancer

Uploaded by

Final Breast Cancer

Uploaded by

SIR C R REDDY COLLEGE OF ENGINEERING

Department of Computer Science and Engineering

DETECTION OF BREAST CANCER USING DEEP LEARNING

 Using radiation it is unable to find the architectural distortion. So

 Operating system : Windows -Linux

 Python IDLE 3.7 version (or)

Systems design is the process or art of defining the architecture, components,

You might also like