Team Titans

.gitignore

@@ -0,0 +1 @@
+Apikey.py

README.md

@@ -9,18 +9,43 @@
 
 ## README.md must consist of the following information:
 
-#### Team Name -
-#### Problem Statement - 
-#### Team Leader Email -
+#### Team Name - Team Titans
+#### Problem Statement - Knee OsteoArtheritis AI Report WebApp
+#### Team Leader Email - [email protected]
 
 ## A Brief of the Prototype:
-  This section must include UML Diagrams and prototype description
+  Osteoarthritis is a joint disease impacting millions worldwide 
+WHO is 2019 said that there are 528 million people worldwide living.
+In India, about 150 million people have osteoarthritis,while 32.5 million in United states suffer from it. 
+They go through a lot of pain like Joint pain, morning stiffness, pain during movement, pain at rest 
+
+As Osteoarthritis can you detected through X-Rays it can be also caused due to many other factors. 
+The combination of X-rays and related factors such as obesity, age, height, bone density can help us detect 
+Product Solution (1-3 Slides)
+What the machine does it takes the X-ray input from the user and puts it through the model after that the model categories the X-ray as the severity of the patient 
+After the process id done it combines it with other factors like the weight, age, height, bone density which gives us end results also by using OpenAI we created a prompt where when user puts all this info it gives them suggestions about the Osteoarthritis. 
+Differentiations (USPs)
+Considering various factors that can also lead to Osteoarthritis and create accurate results.
+Higher accurate results 
+Prompt where you can get tailored solution according to the severity of Osteoarthritis
+
+User Interface => User Uploads the X-Rays => User gets seventy grading => User is asked with more details such as gender, age , weights  => all parameters along with it gets passed => a report is generated 
+
+
 
 ## Tech Stack: 
-   List Down all technologies used to Build the prototype
+  TensorFLow
+  Gradio
+  OpenAI
 
 ## Step-by-Step Code Execution Instructions:
-  This Section must contain a set of instructions required to clone and run the prototype so that it can be tested and deeply analyzed
+  Run the Model step by step no other thing needed
 
 ## What I Learned:
-   Write about the biggest learning you had while developing the prototype
+   There are many people who suffer with this and with this we can help people out also with medical we need to consider lots of aspects and overall view
+
+## Link to download the model:
+   https://drive.google.com/file/d/1t6XblfNhaDe4RskXoY_Apha6csvVReno/view?usp=sharing
+
+## Demo Video of the System
+   https://drive.google.com/file/d/1sm1Q5RLMmI3C8pt_nhR8-xKNEDvmaEba/view?usp=drive_link

model.py

@@ -0,0 +1,70 @@
+import numpy as np
+import pandas as pd
+import cv2 as cv
+import matplotlib.pyplot as plt
+import os
+import pickle
+import tensorflow as tf
+from tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, BatchNormalization
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau
+from keras.models import Model
+from sklearn.preprocessing import LabelBinarizer
+save_model = tf.keras.models.load_model("Best_DenseNet201.h5",compile=False)
+
+
+from PIL import Image
+import gradio as gr
+import numpy as np
+from skimage import transform
+from tensorflow.keras.utils import load_img, img_to_array
+from keras.preprocessing.image import ImageDataGenerator
+from keras.applications.vgg16 import preprocess_input
+
+def load(filename):
+    my_image = load_img(filename, target_size=(224, 224))
+
+    #preprocess the image
+    my_image = img_to_array(my_image)
+    my_image = my_image.reshape((1, my_image.shape[0], my_image.shape[1], my_image.shape[2]))
+    my_image = preprocess_input(my_image)
+
+    #make the prediction
+    prediction = save_model.predict(my_image)
+    print(prediction)
+    prediction = tf.argmax(tf.nn.softmax(prediction), 1)
+    return "Serverity grading:- " + str(int(tf.get_static_value(prediction).item()))
+
+
+import openai
+from Apikey import OPENAI_API_KEY
+
+def noob_wrapper(gender, obesity, severity_grading_score, age):
+
+    openai.api_key = OPENAI_API_KEY
+
+    prompt = "You are a arthritis doctor and your patient has osteoarthritis."
+
+    messages = [ {"role": "system", "content": 
+                prompt} ]
+    while True:
+        message = f"Severity grade my osteoarthritis is {severity_grading_score} and his gender is {gender} and his age is {age} and his obesity is {obesity}. Renerate a report on this."
+        if message:
+            messages.append(
+                {"role": "user", "content": message},
+            )
+            chat = openai.ChatCompletion.create(
+                model="gpt-3.5-turbo", messages=messages
+            )
+        reply = chat.choices[0].message.content
+        print(f"ChatGPT: {reply}")
+        return reply
+
+
+
+demo = gr.Interface(fn=noob_wrapper, inputs=[gr.Radio(["Male", "Female", "Undefined"], label="Gender"), gr.Radio(["Yes", "No"], label="Obesity"),gr.Textbox(placeholder="Enter Severity Grading Score"),gr.Textbox(placeholder="Enter Your Age")], outputs="text")
+gradio = gr.Interface(fn=load,inputs=gr.Image(type="filepath"),outputs=gr.Label())
+
+demo2 = gr.TabbedInterface([gradio, demo], ["Severity Grading", "Report Generation"])
+
+demo2.launch()