Added Pneumonia Detection Gradio App

.gitattributes

@@ -1,27 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bin.* filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+pneumonia_detection_cnn_model.h5 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,37 +1,99 @@
----
-title: Pneumonia Detection
-emoji: 📊
-colorFrom: green
-colorTo: yellow
-sdk: gradio
-app_file: app.py
-pinned: false
----
+## Motivation
 
-# Configuration
+Pneumonia is a lung infection (🫁) that inflames the air sacs in one or both lungs. This infection arises when the air sacs get filled with fluid or pus (purulent material). It can be a bacterial or viral infection. The main symptoms are - cough with phlegm or pus, fever, chills, and breathing difficulty. 
 
-`title`: _string_  
-Display title for the Space
+This disease is responsible for over 15% of all deaths of children under five years old worldwide. This proves the severity of this disease and the need for accurate detection. 
 
-`emoji`: _string_  
-Space emoji (emoji-only character allowed)
+The most commonly used method to diagnose pneumonia is through chest radiograph or chest X-ray, which depicts the infection as an increased opacity in the lungs' specific area(s).
 
-`colorFrom`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+To increase the diagnosis procedure's efficacy and reach, we can leverage machine learning algorithms to identify abnormalities in the chest X-ray images. In this model, many chest X-ray images (both normal and pneumonia) are fed to build `Convolutional Neural Network (CNN)` model for fulfilling the purpose. 
 
-`colorTo`: _string_  
-Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
 
-`sdk`: _string_  
-Can be either `gradio` or `streamlit`
+## Requirements
 
-`sdk_version` : _string_  
-Only applicable for `streamlit` SDK.  
-See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+- Python 3.7.x
+- Tensorflow 2.4.1+
+- Keras 2.4.3+
+- scikit-learn 0.24.1+
+- matplotlib 3.3.3+
+- texttable 1.6.3+
+- gradio 1.5.3+
 
-`app_file`: _string_  
-Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
-Path is relative to the root of the repository.
+## Dataset
 
-`pinned`: _boolean_  
-Whether the Space stays on top of your list.
+You can download the dataset from [kaggle](https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia/). Use the underlying download link to download the dataset.
+
+### Instructions to follow
+
+* Extract the archive
+* You will find several directories in it
+* Copy the `chest-xray` directory contents (`train`, `test` and `val` subdirectories) to the `data` folder
+
+The number of images belonging to both classes (`Normal` and `Pneumonia`) in the `train`, `test` and `val` datasets are -
+
+<img width="326" alt="Screenshot 2021-02-07 at 16 40 00" src="https://user-images.githubusercontent.com/76659596/107151515-4083f280-6963-11eb-84c7-f2a23cc24134.png">
+
+
+## Installation
+
+* Clone the repository 
+
+`git clone https://github.com/baishalidutta/Pneumonia-Detection.git`
+
+* Install the required libraries
+
+`pip3 install -r requirements.txt`
+
+## Usage
+
+Enter into the `source` directory to execute the following source codes.
+
+* To generate the model on your own, run
+
+`python3 cnn_training_model.py` 
+
+* To evaluate any dataset using the pre-trained model (in the `model` directory), run
+
+`python3 cnn_model_evaluation.py`
+
+Note that, for evaluation, `cnn_model_evaluation.py` will use all the images contained inside both `test` and `val` subdirectories (inside `data` directory).
+
+Alternatively, you can find the whole analysis in the notebook inside the `notebook` directory. To open the notebook, use either `jupyter notebook` or `google colab` or any other IDE that supports notebook feature such as `PyCharm Professional`.
+
+## Evaluation 
+
+Our model is trained with 96% accuracy on the training dataset. The model's accuracy on the `test` and `val` datasets are 91% and 88% respectively. In both cases, the `f1-score` and `ROC_AUC Score` are relatively high, as shown below. 
+
+### On Test Dataset (624 images, 234 `Normal` and 390 `Pneumonia`)
+
+<p align="center">
+<img width="960" alt="Screenshot 2021-02-07 at 17 07 23" src="https://user-images.githubusercontent.com/76659596/107152321-93f83f80-6967-11eb-95b4-0bfb3ccae6d7.png">
+</p>
+
+### On Validation Dataset (16 images, 8 `Normal` and 8 `Pneumonia`)
+
+<p align="center">
+<img width="960" alt="Screenshot 2021-02-07 at 17 10 07" src="https://user-images.githubusercontent.com/76659596/107152360-ba1ddf80-6967-11eb-90cb-dfaeca31f275.png">
+</p>
+
+## Web Application
+
+To run the web application locally, go to the `webapp` directory and execute:
+
+`python3 web_app.py`
+
+This will start a local server that you can access in your browser. You can either upload/drag a new X-ray image or select any test X-ray images from the examples below.
+
+You can, alternatively, try out the hosted web application [here](https://gradio.app/g/baishalidutta/Pneumonia-Detection).
+
+## Developer
+
+Baishali Dutta (<a href='mailto:[email protected]'>[email protected]</a>)
+
+## Contribution [![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/baishalidutta/Pneumonia-Detection/issues)
+
+If you would like to contribute and improve the model further, check out the [Contribution Guide](https://github.com/baishalidutta/Pneumonia-Detection/blob/main/CONTRIBUTING.md)
+
+## License [![License](http://img.shields.io/badge/license-Apache-blue.svg)](https://www.apache.org/licenses/LICENSE-2.0)
+
+This project is licensed under Apache License Version 2.0

app.py

@@ -0,0 +1,55 @@
+__author__ = "Baishali Dutta"
+__copyright__ = "Copyright (C) 2021 Baishali Dutta"
+__license__ = "Apache License 2.0"
+__version__ = "0.1"
+
+# -------------------------------------------------------------------------
+#                           Importing the libraries
+# -------------------------------------------------------------------------
+import gradio as gr
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+
+# -------------------------------------------------------------------------
+#                               Configurations
+# -------------------------------------------------------------------------
+MODEL_LOC = 'pneumonia_detection_cnn_model.h5'
+
+# load the trained CNN model
+cnn_model = load_model(MODEL_LOC)
+
+
+def make_prediction(test_image):
+    test_image = test_image.name
+    test_image = image.load_img(test_image, target_size=(224, 224))
+    test_image = image.img_to_array(test_image) / 255.
+    test_image = np.expand_dims(test_image, axis=0)
+    result = cnn_model.predict(test_image)
+    return {"Normal": str(result[0][0]), "Pneumonia": str(result[0][1])}
+
+
+image_input = gr.inputs.Image(type="file")
+
+title = "Pneumonia Detection"
+description = "This application uses a Convolutional Neural Network (CNN) model to predict whether a chosen X-ray shows if " \
+              "the person has pneumonia disease or not. To check the model prediction, here are the true labels of the " \
+              "provided examples below: the first 4 images belong to normal whereas the last 4 images are of pneumonia " \
+              "category. More specifically, the 5th and 6th images are viral pneumonia infection in nature whereas " \
+              "the last 2 images are bacterial infection in nature."
+
+gr.Interface(fn=make_prediction,
+             inputs=image_input,
+             outputs="label",
+             examples=[["image1_normal.jpeg"],
+                       ["image2_normal.jpeg"],
+                       ["image3_normal.jpeg"],
+                       ["image4_normal.jpeg"],
+                       ["image1_pneumonia_virus.jpeg"],
+                       ["image2_pneumonia_virus.jpeg"],
+                       ["image1_pneumonia_bacteria.jpeg"],
+                       ["image2_pneumonia_bacteria.jpeg"]],
+             title=title,
+             description=description,
+             article="http://raw.githubusercontent.com/baishalidutta/Pneumonia-Detection/gradio/README.md") \
+    .launch(share=True)

pneumonia_detection_cnn_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48eb1a78829ddccc7bef7a1cfd01271200862b3aeb0fa6dbec310720274f54c4
+size 79865784

requirements.txt

@@ -0,0 +1,4 @@
+tensorflow>=2.4.1
+Keras>=2.4.3
+gradio>=1.5.3
+numpy>=1.19.5