Cancer Guard: Fighting against Breast Cancer Detection Using DenseNet-201 and Deep Learning with Django and AWS Deployment

-20%

Cancer Guard: Fighting against Breast Cancer Detection Using DenseNet-201 and Deep Learning with Django and AWS Deployment

0 Orders 0 Wish listed

₹4,999.00

Qty

Total price:

₹4,999.00

Overview
Reviews

Detail Description

1. Abstract

Breast cancer is one of the most common and life-threatening diseases affecting women worldwide. Early and accurate detection plays a vital role in improving survival rates. Traditional diagnostic methods are time-consuming and depend heavily on expert analysis. Therefore, automated systems using artificial intelligence are becoming increasingly important in medical diagnosis.

This project focuses on developing a deep learning-based system for detecting breast cancer from histopathological (autopsy) images. The model classifies cancer as either benign or malignant. A pre-trained DenseNet-201 convolutional neural network is used and retrained using a breast cancer image dataset.

The dataset is preprocessed and augmented to improve model performance. Transfer learning techniques are applied to fine-tune the model for medical image classification. After training, the model is integrated into a web application developed using the Django framework. The application is hosted on AWS cloud servers using EC2 instances.

This system allows users to upload medical images and receive instant predictions. The project demonstrates how deep learning, web development, and cloud computing can be combined to create intelligent healthcare solutions.

2. Objectives

The main objectives of this project are:

To understand breast cancer classification using medical images.
To study convolutional neural networks and deep learning concepts.
To analyze the DenseNet-201 architecture.
To implement transfer learning for medical image classification.
To preprocess and augment histopathological images.
To train and evaluate a deep learning model for cancer detection.
To develop a web application using Django framework.
To integrate the trained model with the web application.
To deploy the application on AWS cloud platform.
To provide a user-friendly interface for medical diagnosis support.

3. Existing System

Traditional breast cancer detection systems rely mainly on manual examination and laboratory tests.

The limitations of existing systems include:

Diagnosis depends on experienced medical professionals.
Manual analysis is time-consuming.
High chances of human error.
Lack of automation in image analysis.
Expensive diagnostic equipment and facilities.
Limited availability of specialists in rural areas.

Due to these drawbacks, traditional systems are not efficient for large-scale and real-time diagnosis.

4. Proposed System

The proposed system uses deep learning and cloud-based deployment for automated breast cancer detection.

In this system:

• Histopathological images are used as input.

• DenseNet-201 extracts deep features.

• Transfer learning improves accuracy.

• The model classifies images as benign or malignant.

• Django framework provides web interface.

• AWS EC2 hosts the application.

This system offers fast, accurate, and accessible cancer detection.

5. Implementation Procedure

The project implementation follows these steps:

Step 1: Data Collection

Breast cancer histopathological image dataset is collected from public repositories.

Step 2: Data Preprocessing

Images are processed by:

• Resizing

• Normalization

• Noise reduction

• Data augmentation

Step 3: Model Selection

DenseNet-201 pre-trained model is selected for transfer learning.

Step 4: Model Development

The network is modified by:

• Removing final layers

• Adding custom classification layers

• Applying dropout

Step 5: Model Training

The model is trained using labeled images and optimized using backpropagation.

Step 6: Model Evaluation

Performance is measured using:

• Accuracy

• Precision

• Recall

• F1-score

Step 7: Web Application Development

A Django-based web application is developed with:

• Image upload feature

• Prediction display

• User interface

Step 8: Deployment

The application is deployed on AWS EC2 for global access.

6. Software Requirements

The software tools required are:

• Python – Programming language

• Jupyter Notebook / Google Colab – Development environment

• Django – Web framework

• TensorFlow / Keras – Deep learning framework

• OpenCV – Image processing

• NumPy – Numerical computation

• Pandas – Data handling

• Matplotlib / Seaborn – Visualization

• AWS EC2 – Cloud hosting

• Git – Version control

7. Hardware Requirements

The hardware requirements include:

• Processor: Intel i7 or higher

• RAM: 16 GB or higher

• Storage: 512 GB or higher

• System: Laptop/Desktop

• GPU (Recommended): NVIDIA GPU (CUDA supported)

• Internet Connection: High-speed

Optional:

• Cloud GPU servers for faster training

8. Advantages of the Project

Enables early detection of breast cancer.
Reduces dependency on manual diagnosis.
Provides high accuracy using deep learning.
Supports remote diagnosis through web access.
Saves time and medical costs.
Improves healthcare accessibility.
Can be used in hospitals and clinics.
Scalable using cloud infrastructure.
User-friendly interface.
Helps doctors in decision making.

No review given yet!

Fast Delivery all across the country

Safe Payment

7 Days Return Policy

100% Authentic Products

Shopping cart