Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Pneumonia Detection using X-Ray Images #340

Merged
merged 1 commit into from
Aug 8, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions Pneumonia Detection using X-Ray Images/Dataset/Readme.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
# Pneumonia Detection using X-Ray images
## Detaset link: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

Large diffs are not rendered by default.

1,136 changes: 1,136 additions & 0 deletions Pneumonia Detection using X-Ray Images/Models/Pneumonia Detection via CNN.ipynb

Large diffs are not rendered by default.

91 changes: 91 additions & 0 deletions Pneumonia Detection using X-Ray Images/Readme.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@
# <p align = "center">Pneumonia Detection using X-Ray images </p>
## <p align = "center">Aim of the project: To detect the pneumonica of the patient using the X-Ray images dataset.</p>
## Libraries and Frameworks used:
#### 1. Pandas
#### 2. Numpy
#### 3. Matplotlib
#### 4. Tensorflow
#### 5. Keras
#### 6. OpenCV
#### 7. Imutils
#### 8. Pathlib

## Deep Learning Algotithms used:
#### 1. EfficientNet50
#### 2. MobileNetV2
#### 3. InceptionV3
#### 4. Normal Convolutional Neural Network

## Evaluation Metrics used:
#### 1. Mean Absolute Error

## Loss Functions Used:
#### 1. Softmax
#### 2. Rectified Linear Unit

## <p align = "center">Images</p>



### <p align = "center">Visualization Phase using Matplotlib</p>

![Grayscale visuals](https://github.com/PiyushBL45t/DL-Simplified/assets/75735209/72b48b73-0e39-45a1-a42a-573ba954f99e)


![Matshow Image](https://github.com/PiyushBL45t/DL-Simplified/assets/75735209/5b8751c5-3584-4d60-b181-875735236d97)





## Loss and Accuracy Statistics
<p align = "center">Loss and Accuracy Graphs for EfficientNEt50 Algorithm</p>

#### Loss Graph
![Loss Graph EfficientNet50](https://github.com/PiyushBL45t/DL-Simplified/assets/75735209/69e94b4e-5b48-4a3d-a340-d92d72441534)

#### Accuracy Graph
![Accuracy Graph Efficientnet50](https://github.com/PiyushBL45t/DL-Simplified/assets/75735209/8a86826b-5dff-4e84-b679-092ecb122f70)


<p align = "center">Loss and Accuracy Graphs for CNN Algorithm</p>

#### Loss Graph

![Loss Graph CNN](https://github.com/PiyushBL45t/DL-Simplified/assets/75735209/23a28c42-5abe-4e29-9837-7e487f07b8ff)


#### Accuracy Graph

![Accuracy Graph CNN](https://github.com/PiyushBL45t/DL-Simplified/assets/75735209/2c3d878e-bb68-4e7c-875d-f426ecf6d531)


## <p align = "center">Results</p>

<div align = "center">

![CNN Result](https://github.com/PiyushBL45t/DL-Simplified/assets/75735209/4b2462bf-760a-48bb-960f-90dce1525307)

</div>

## Accuracy and training time comparison of all the Deep Learning Algorithms
| | Normal CNN | EfficientNet50 | InceptionV3 | MobileNetV2 |
|-------------|------------|----------------|-------------|-------------|
|Accuracy | 97% | 77% | 86% | 93% |
|Eval Metrics | None | MAE | MAE | None |
|Train Time | 15 mins | 20 mins | 20 mins | 20 mins |
|Epochs | 10 | 10 | 10 | 10 |


## Techniques used for data preprocssing:
1. Image Prepreocssing
2. Data Preprocessing
3. Image visualizations
4. Setting up the path for defective and non defective images
5. Data Labellling and annotations
6. Building the CNN model
7. Using the pretrained models and fine tuning them
8. Converting the image data to numpy arrays
9. Checking the loss and accuracy graphs for each DL algorithm used