Detecting Bone Fractures in X-Ray radiographs using Deep Learning

We are using capsule networks (introduced in 2017) latest model available in our FYP to detect bone fractures in human body. We will try to achieve human level accuracy, so the work load of a radiologist could be lessen.

Project Title

Detecting Bone Fractures in X-Ray radiographs using Deep Learning

Project Area of Specialization

Artificial Intelligence

Project Summary

We are using capsule networks (introduced in 2017) latest model available in our FYP to detect bone fractures in human body. We will try to achieve human level accuracy, so the work load of a radiologist could be lessen.

Project Objectives

Project objective is to provide a free website availble on internet which could be accessed throughout the world. And to lessen the work load of radiologist where the number of patients is more than 100.

Project Implementation Method

We have used Capsule Networks which is being implemented in keras and tensorflow is used as backend.

Benefits of the Project

1. Less Fatigue for a Radiologist.

2. Sickest patient will get treatment fast.

3. Shortage of Doctors (No problem this website will help them).

4. Reduces Error.

5. Automatic Detection.

Technical Details of Final Deliverable

1. Data distribution into train/valid/test set.

2. Preprocessing (Scaling image data, Denoising images, dealing with imbalanced data).

3. Capsule Network (Function:Squash function, Function:Dynamic routing, image size=(224, 224), number of routing=3).

4. Training (training batch size=8, validation batch size=8, epochs=10).

5. Website (JavaScript, Html, Tensorflow.js).

Final Deliverable of the Project

Software System

Core Industry

Medical

Other Industries

IT

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com