Professional Documents
Culture Documents
Sample Copy of Black Book
Sample Copy of Black Book
BACHELOR OF ENGINEERING
(COMPUTER ENGINEERING)
SUBMITTED BY
Submitted by
is a bonafide student at this institute and the work has been carried out by him/her under
the supervision of Prof. Pramod G. Patil and it is approved for the partial fulfillment of
the requirement of Savitribai Phule Pune University, for the award of the degree of
Bachelor of Engineering (Computer Engineering).
It gives us great pleasure in presenting the project report on the topic ‘Alzheimer’s
Disease Detection Using Machine Learning Techniques In 3D MR Images’.
We would like to express our heartfelt gratitude to our internal guide, Prof. Pramod G.
Patil, for providing us with the necessary help and guidance we needed. We are truly
grateful for their kind support and valuable suggestions.
We are also thankful to Dr. Amol D. Potgantwar, Head of the Computer Engineering
Department at SITRC, for his invaluable support and suggestions.
Furthermore, we extend our gratitude to Dr. M. M. Patil for providing various resources
such as a well-equipped laboratory with the required software platforms and a continuous
internet connection for our project.
Lastly, I would like to extend my sincere thanks to our project coordinator, Prof. Sunil
Kale, for his constant support and guidance throughout the completion of this project.
LIST OF ABBREVATIONS i
LIST OF FIGURES ii
LIST OF TABLES iii
01 Introduction 1-4
1.1 Overview
1.2 Motivation
1.3 Problem Definition
02 Literature Survey 5-14
03 Software Requirements Specification 15-26
3.1 Introduction 16
3.1.1 Project Scope
3.1.2 User Classes and Characteristics
3.1.3 Assumptions and Dependencies
3.2 Functional Requirements 18
3.3 External Interface Requirements 18
3.3.1 User Interfaces
3.3.2 Hardware Interfaces
3.3.3 Software Interfaces
3.3.4 Communication Interfaces
3.4 Nonfunctional Requirements 19
3.4.1 Performance Requirements
3.4.2 Safety Requirements
3.4.3 Software Quality Attributes
3.5 System Requirements 20
3.3.1 Database Requirements
3.3.2 Software Requirements
5.3.3 Hardware Requirements
3.6 Analysis Models: SDLC Model to be applied 21
3.7 System Implementation Plan 24
04 System Design 27-35
4.1 System Architecture
4.2 Mathematical Model
4.3 Data Flow Diagrams
4.4 UML Diagrams
05 Other Specification 36-37
5.1 Advantages
5.2 Limitations
5.3 Applications
06 Project Implementation 38-40
6.1 Algorithm & Flowcharts
07 Results & Screenshots 41-46
08 Conclusion & Future Work 47-48
09 References 49-53
10 Information of Project Group Members 54-58
11 Research Paper 59-61
12 Paper Publication Certificate 62-67
13 Sponsorship Letter 68-70
14 Plagiarism Report 71-72
LIST OF ABBREVATIONS
ABBREVIATION ILLUSTRATION
AD Alzheimer’s Disease
CNN Convolutional Neural Networks
DFD Data Flow Diagram
MRI Magnetic Resonance Image
UML Unified Modeling Language
LIST OF FIGURES
INTRODUCTION
The main motivation of our project is to develop a system that can accurately detect
Alzheimer's disease using advanced technologies like Convolutional Neural Networks
(CNN) and Magnetic Resonance Imaging (MRI). Our goal is to catch the disease at an
early stage so that doctors can provide timely care and treatment to patients. By using
CNN and MRI, we aim to minimize incorrect diagnoses, unnecessary tests, and improve
patient outcomes.
The problem we aim to address is the early detection of Alzheimer's disease using MRI
scans. The current methods are slow, costly, and may not catch early signs. Our idea is to
use advanced computer technology called deep learning to quickly analyze MRI scans
and find patterns that suggest Alzheimer's disease. This can help us detect the disease
more accurately and quickly, leading to better treatment and outcomes for patients.
LITERATURE SURVEY
SOFTWARE REQUIREMENTS
SPECIFICATION
The goal of this project is to develop a system that utilizes CNN and MRI technology to
detect Alzheimer's disease at an early stage. The system will involve collecting MRI
scans from individuals with and without Alzheimer's disease, preprocessing the data, and
designing a CNN model. The trained model will be capable of accurately identifying
Alzheimer's disease based on the MRI scans.
1. Login/Registration:
The system includes a login and registration feature, allowing users to access their
accounts and obtain results. Users have the option to log in if they already have an
account or register if they are new users. This feature ensures that only authorized
individuals can utilize the system and view the results.
It is assumed that users possess basic knowledge of operating the internet and have access
to an internet connection. Users should be familiar with common internet browsing
techniques and be able to navigate through the system's interface. Additionally, the
administrator is expected to be familiar with the interface of the tech support system.
1. Python Language: The project relies on the use of Python as the primary programming
language for implementing machine learning (ML) algorithms. Python offers a wide
range of libraries and frameworks specifically designed for ML tasks, making it a popular
choice in the field.
3. Input as Image through Image Processing: The project assumes that the input data for
the model will be in the form of images. These images will undergo various image
processing techniques to extract relevant features required for accurate Alzheimer's
disease detection.
4. Software: The project utilizes the Anaconda Navigator software, which provides an
integrated development environment (IDE) and package management for Python.
Specifically, the IDE Spyder is used for coding and developing the ML model.
5. Libraries: The project relies on several Python libraries for implementing various
functionalities. The main libraries used include Keras (for building and training deep
learning models), OpenCV (for image processing tasks), TensorFlow (for ML
computations), Matplotlib (for data visualization), and Pillow (for image manipulation).
The system can work only in online mode hence, communication interfaces are
compulsory.
1. The application is designed in modules where errors can be detected and fixed easily.
2. This makes it easier to install and update new functionality if required.
Our software has many quality attributes that are given below:
1. Adaptability: This software is adaptable by all users.
2. Availability: This software is freely available to all users. The availability of the
software is easy for everyone.
3. Maintainability: After the deployment of the project if any error occurs then it can be
easily maintained by the software developer.
3. Reliability: The performance of the software is better which will increase the reliability
of the Software.
• Database : DBSQLite
The first Process Model to be introduced was the Waterfall Model. The term "linear
sequential life cycle model" is also used to describe it. It is incredibly easy to use and
comprehend. There is no overlap between phases in a waterfall model; each step must be
finished before the subsequent phase can start. The first SDLC methodology for software
development was the waterfall model. The software development process is depicted
using the waterfall model, which follows a linear sequential flow. This implies that a
phase of development can only start if the one before it is finished. The phases in this
waterfall model do not cross over.
The Waterfall Approach was the first commonly used SDLC Model in software
engineering to ensure project success. The entire software development process is split
into distinct phases using "The Waterfall" technique. Typically, the results of one step in
this waterfall model serve as the input for the subsequent phases in turn. The several
stages of the Waterfall Model are depicted in the figure.
• Requirement Analysis and Gathering - During this stage, all prospective system
requirements are gathered and compiled into a requirement specification document.
• System Design - In this phase, the required specifications from the first phase are
examined, and the system design is created. This system design aids in determining
the overall system architecture as well as the hardware and system requirements.
• Integration and Testing - Following the testing of each unit created during the
implementation phase, the entire system is merged. The entire system is tested for
errors and failures after integration.
2 Deciding the topic for Choosing a specific topic for the project. 15
the project
Task 13 Documentation 4 30
SYSTEM DESIGN
• I - Input
• P - Procedure
• O - Output
• Input ( I )
• I = { brain Images }
• Where,
• Procedure ( P ),
• P={ I, Using I System perform operations and calculate the detection of disease.}
• Output ( O )
In a Data Flow Diagram (DFD), we depict the flow of data within a system. In DFD0, we
represent the basic DFD where rectangles represent inputs and outputs, and circles
represent the system itself. In DFD1, we illustrate the actual inputs and outputs of the
system. The inputs to our system can be in the form of text or images, and the output is
the detection of rumors. Similarly, in DFD2, we present the operations performed by both
users and administrators.
The Unified Modeling Language (UML) is a standard language for writing software
blueprints. It can be used to visualize, specify, construct, and document the artifacts of a
software-intensive system. UML is process-independent, although it is best suited for use
in a process that is use case driven, architecture-centric, iterative, and incremental. There
are several UML diagrams available that can be utilized to represent different aspects of
the system's structure and behavior.
OTHER SPECIFICATION
1. Detects Alzheimer's disease early, leading to timely treatment and better outcomes.
2. Saves time by automating the diagnosis process.
3. Reduces costs by minimizing the need for multiple appointments and tests.
4. Improves efficiency in detecting Alzheimer's disease.
5. Enhances patient care and improves quality of life.
5.2 Limitations
Our model, like other deep learning models, struggles to accurately estimate uncertainty.
It means that the model may have difficulty indicating how confident or unsure it is about
its predictions. However, if we combine statistical techniques with deep learning and use
active learning, we can potentially improve the model's performance in analyzing 3D
brain scans for Alzheimer's detection.
5.3 Applications
The system can be used in hospitals to help detect Alzheimer's patients. Early detection
of the disease can assist in receiving proper and timely treatment.
PROJECT IMPLEMENTATION
Algorithm:
1. Gather a dataset of brain images from patients with Alzheimer's disease and healthy
individuals.
2. Clean and preprocess the images, ensuring proper formatting and analysis readiness.
This includes resizing, normalization, and standardization.
5. Train a new model using the extracted features as inputs and the labels (Alzheimer's
or healthy) as outputs.
6. Validate the trained model on the testing set to ensure accurate prediction of
Alzheimer's disease in new, unseen brain images.
7. Evaluate the model's performance using various metrics such as accuracy, precision,
recall, and F1 score.
9. Deploy the trained model in a real-world scenario, where it can predict Alzheimer's
disease in patients based on their brain images.
10. Monitor and update the model over time to maintain its accuracy and effectiveness in
predicting Alzheimer's disease.
Welcome Page
Sign Up Page
Home Page
Image Pre-processing
In conclusion, our project uses a combination of CNN and MRI to detect Alzheimer's
disease. We achieved a high accuracy rate of 85% to 90% in identifying the disease from
MRI scans. This helps doctors diagnose Alzheimer's more accurately and provide timely
care. CNN technology helps us extract important features and classify MRI images
effectively. Our project contributes to a better understanding and management of
Alzheimer's disease, benefiting both patients and healthcare professionals.
In the future, we will focus on improving CNN models by training them on larger and
more diverse datasets. We aim to integrate additional biomarkers and clinical data with
MRI scans for more comprehensive diagnostics.
REFERENCES
2. Suk H., Lee S.W., Shen D., Latent Feature Representation with Stacked Auto-
encoder for AD/MCI Diagnosis, Brain Structure and Function, 2016.
3. Plis S., Hjelm D., Salakhutdinov R., Allen E., Alzheimer's Disease Neuroimaging
Initiative, Deep Learning for Neuroimaging: A Validation Study, Frontiers in
Neuroscience, 2014.
5. Zhang D., Shen D., Multi-modal multi-task learning for joint prediction of multiple
regression and classification variables in Alzheimer's disease, NeuroImage, 2012.
7. Liu M., Zhang D., et al., Fusion of Multimodal Neuroimaging Data via Sparse
Representation Based Classification for Alzheimer's Disease Diagnosis, Human
Brain Mapping, 2014.
8. Sarraf S., Ghafoorian M., et al., DeepAD: Alzheimer's Disease Classification via
Deep Convolutional Neural Networks using MRI and fMRI, Scientific Reports,
2019.
10. Pereira J., Xiong Z., et al., Deep Learning for Brain MRI Segmentation: State of the
Art and Future Directions, Journal of Digital Imaging, 2016.
11. Hou J., Samaras D., Multimodal Neuroimaging Feature Learning with Multimodal
Stacked Deep Polynomial Networks for Diagnosis of Alzheimer's Disease, IEEE
Journal of Biomedical and Health Informatics, 2016.
12. Liu M., Zhang D., et al., Multi-modal Discriminative Region Discovery for
Alzheimer's Disease Diagnosis, Neuroinformatics, 2016.
13. Anandhavelu S., Srinivasan K., Convolutional Neural Networks for MRI Brain
Image Classification using Hybrid Feature Selection and Data Augmentation
Techniques, Journal of Medical Systems, 2019.
14. Costa P., Garg A., et al., End-to-End Adversarial Attention Networks for Brain
Tumor Segmentation, Proceedings of the IEEE Conference on Computer Vision
and Pattern Recognition, 2017.
15. Liu M., Zhang D., et al., Multimodal Discriminative Region Discovery for
Alzheimer's Disease Diagnosis, IEEE Journal of Biomedical and Health
Informatics, 2018.
16. Amoroso N., Guaragnella C., et al., Multimodal brain tumor segmentation using
deep convolutional neural networks, International Journal of Computer Assisted
Radiology and Surgery, 2018.
18. Sarraf S., Tofighi G., et al., Ensemble Deep Learning for Alzheimer's Disease
Diagnosis Using MRI and fMRI Data, Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition Workshops, 2016.
19. Brosch T., Tang L., et al., Deep 3D Convolutional Encoder Networks with
Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion
Segmentation, Medical Image Analysis, 2016.
20. Suk H., Shen D., et al., Deep Sparse Multi-Modal Learning for Alzheimer's Disease
Diagnosis, International Conference on Medical Image Computing and Computer-
Assisted Intervention, 2013.
21. Anandhavelu S., Srinivasan K., Alzheimer's Disease Detection using Hybrid Deep
Convolutional Neural Networks with MRI Images, Journal of Medical Systems,
2020.
23. Jafari M., Anssari M., et al., Alzheimer's Disease Detection using Convolutional
Neural Networks and Magnetic Resonance Imaging, Journal of Medical Signals
and Sensors, 2020.
25. Bernal J., Tajerian M., et al., Multi-view Convolutional Neural Networks for 3D
Shape Classification, IEEE Transactions on Pattern Analysis and Machine
Intelligence, 2017.
• Gender - Female
• Mobile/Contact No - 7879338580
• Email - divyapatil336@gmail.com
• Gender - Female
• Mobile/Contact No - 8080423900
• Email – aishbharti145@gmail.com
• Placement Details - No
• Gender - Female
• Mobile/Contact No - 9307742626
• Email - vaishnavishelke7777@gmail.com
• Placement Details - No
• Gender - Female
• Mobile/Contact No - 9307083801
• Email - hemangiakhade3113@gmail.com
• Placement Details - No
RESEARCH PAPER