i
E n h a n c e d M e d i c a l I m a g e P ro c e s s i n g u s i n g
LSA and PCA in CNN
PHASE II REPORT
Submitted by
Thasneem Suhaifa.S
(REGISTER NO: 911523405010)
In partial fulfillment for the award of the degree of
MASTER OF ENGINEERING
IN
COMPUTER SCIENCE AND ENGINEERING
DEPARTMENT OF COMPUTER SCIENCE AND
ENGINEERING
MOHAMED SATHAK ENGINEERING COLLEGE
(AUTONOMOUS INSTITUTION)
KILAKARAI-623806
J U N E 2025
ii
MOHAMED SATHAK ENGINEERING COLLEGE
(AUTONOMOUS INSTITUTION)
KILAKARAI-623806
BONAFIDE CERTIFICATE
Certified that this Report titled “E N H A N C E D M E D I C A L I M A G E
PROCESSING USING LSA AND P C A I N C N N ” is the
bonafide work of THASNEEM SUHAIFA S (REG.NO:911523405010) who
carried out the Project Phase - II under my supervision. Certified further that to
the best of my knowledge the work reported herein does not form part of any
other thesis or dissertation on the basis of which a degree or award was
conferred on an earlier occasion on this or any other candidate.
SIGNATURE SIGNATURE
Mr.N.Balasubramanian.,M.E.,(Ph.D.,) Mrs.M.Kayathri Devi.,M.E.,
HEAD OF THE DEPARTMENT ASSISTANT PROFESSOR & SUPERVISOR
Computer Science and Engineering, Computer Science and Engineering,
Mohamed Sathak Engineering college, Mohamed Sathak Engineering college,
Kilakarai-623806 Kilakarai-623806
Submitted for the End Semester Project Viva-Voice examination held on…………..
Internal Examiner External Examiner
iii
ABSTRACT
We are presently living in the era where in medical field, the use of technology play
a major role in disease diagnosis and in treatment. In recent years Medical Image
Processing play a significant role in modern diagnostics, where precision and
accuracy are of highly important for planning and treatment of diseases. In this
study, we present an enhanced approach that integrates Least Squares (LSA)
alongside with Principal Component Analysis (PCA) within the Convolutional
Neural Network (CNN) framework of deep learning to improve image processing
and image resolution for medical diagnostics .Here LSA is employed to reduce the
noise to the greater extent and to refine the feature for better clarity, while PCA
employed in dimensionality reduction for efficient processing and preserving
critical image details and at the same time CNN enables the automatic feature
extraction and interpretation of image. Our results demonstrate that this combined
LSA and PCA in CNN model offers significant improvement in image processing
speed, efficiency in computation, reduction in noise present in the medical image,
increasing sharpness of the image for high resolution leads to the accuracy in
detection of diseases making it a promising method for advanced and enhanced
medical imaging applications.
iv
ACKNOWLEDGEMENT
We thank God Almighty for giving us an opportunity to study in this prestigious
institution Mohamed Sathak Engineering College which provided us tremendous
facilities and support.
We are highly indebted to Our Chairman Alhaj S.M.Mohamed Yousuf, Mohamed
Sathak Trust Chennai as well as Our Director Alhaj S.M.A.J.Habeeb Mohamed
Sathakathullah. Their complete inspiration and motivation helped us throughout
the course of this project.
We undergo much tribute to express my sincere gratefulness to Principal
Dr.V. Nirmal Kannan M.E., Ph.D., Mohamed Sathak Engineering College,
Kilakarai, for making the resources available at right time and providing valuable
insights leading to the successful completion of this project.
We take this opportunity to express our profound gratitude and deep regards to Our
Head of the Department Mr. Balasubramanian.,M.E.,( Ph.D.,)Department of
Computer Science and Engineering for his exemplary guidance, monitoring and
constant encouragement throughout the course of this project.
We also extend our gratitude to the Project Coordinator Ms.R. Bavana Mercy.,M.E
Assistant Professor, Department of Computer Science and Engineering for her
critical advice and guidance without which this project would not have been
possible.
We are sincerely grateful to our Project Supervisor Mrs.M.Kayathri Devi.,M.E
Assistant Professor, Department of Computer Science and Engineering for sharing
her truthful and illuminating views on a number of issues related to this project.
We also thank all other Faculty members and Supporting Staff of Department of
Computer Science and Engineering for their support and encouragement.
We wish to express a sense of gratitude to our friends and our beloved parents for
their manual support, strength and help and for everything.
We take this opportunity to express our gratitude to the people who have been
instrumental in the successful completion of this project.
v
TABLE OF CONTENTS
CHAPTER TITLE PAGE
NO NO
ABSTRACT iii
LIST OF FIGURE vii
LIST OF ABBREVIATION viii
1 INTRODUCTION
1.1 Medical Image Classification and Its Importance 1
1.2 Existing system 3
1.3 Proposed system 5
1.4 Objective of the Study 6
2 LITERATURE REVIEW
2.1 Deep learning in breast cancer 7
screening."Artificial Intelligence in medical
imaging: opportunities,applications and risk
2.2 Distributed deep learning networks among 8
institutions for medical imaging
2.3 Imagenet Classification with Deep 9
Convolutional Neural Networks.”Neural
Information Processing Systems
2.4 Least square based image deblurring,"2017 9
International Conference on Advances in
Computing, Communication and Informatics
2.5 The Effect of Principal Component Analysis on 11
Machine Learning Accuracy with High
Dimensional Spectral Data
2.6 Deep Constrained Least Squares for Blind 12
Image Super Resolution
2.7 An Analysis on Implementation of Various 13
Deblurring Techniques in Image Processing
2.8 A comprehensive review of deep neural 14
networks for Medical image processing:
Recent developments and future
opportunities,Healthcare Analytics(2023)
2.9 GCRSR: Sequential gradient constrained 15
regression for single image super-
resolution,Signal Processing: Image
Communication
2.10 Rich Feature Hierarchies for Accurate Object 16
vi
Detection and Semantic Segmentation
3 SYSTEM STUDY
3.1 Deep Neural Network 18
3.2 DNN architecture for object detection 22
4 SYSTEM MODEL
4.1 Components of the System 26
4.1.1 Least Square Analysis 26
4.1.2 Principal Component Analysis (PCA) 28
4.1.3 Convolutional Neural Networks (CNNs) 30
4.2 Hybridization of least Squares (LS),Principal 35
Component (PCA) and CNN
5 IMPLEMENTATION TECHNIQUES
5.1 Framework Overview 37
5.2 LS-PCA-CNN Algorithm 42
6 SAMPLE OUTPUT AND RESULT ANALYSIS
6.1 Sample output 44
6.2 Result Analysis 50
7 CONCLUSION
7.1 Conclusion 52
7.2 Future Work 52
APPENDIX
A) System Requirement 53
B) Sample Coding 57
C) Publication 60
REFERENCES 74
vii
LIST OF FIGURES
FIGURE NO FIGURE NAME PAGE NO
1 Steps Involved in CNN 35
2 Medical Image Analysis Sequence 36
3 CNN based Classification 38
4 CNN based Detection 39
5 Medical Image Classification 41
6 Flowchart of System Design 43
viii
LIST OF ABBREVIATION
ABBREVIATION DESCRIPTION
AI Artificial Intelligence
ML Machine Learning
DL Deep Learning
CNN Convolutional Neural Network
PCA Principle Component Analysis
LSA Least Square Algorithm
CT Computed Tomography
MRI Magnetic Resonance Imaging
VOIP Voice over Internet Protocol
CAD Computer Aided Detection
DNN Deep Neural Network
RNN Recurrent Neural Network
