Bone Fracture Detection App using Python

1) Background/ Problem Statement

The bone is a major component of the

human
body. Bone provides the ability to move
the body. The bone
fractures are common in the human body.
The doctors use the
X-ray image to diagnose the fractured
bone. The manual
fracture detection technique is time
consuming and also error
probability chance is high. Therefore, an
automated system
needs to develop to diagnose the fractured
bone. The Deep
Neural Network (DNN) is widely used for
the modeling of the
power electronic devices. In the present
study, a deep neural
network model has been developed to
classify the fracture and
healthy bone. The deep learning model
gets over fitted on the
small data set. Therefore, data
augmentation techniques have
been used to increase the size of the data
set. The three
experiments have been performed to
evaluate the performance
of the model using softmax and Adam
optimizer. The
classification accuracy of the proposed
model is 92.44% for the
healthy and the fractured bone using 5 fold
cross validation.
The accuracy on 10% and 20% of the test
data is more than
95% and 93% respectively. The proposed
model performs
much better than [1] of the 84.7% and 86%
of the [2].
The bone is a major component of the
human
body. Bone provides the ability to move
the body. The bone
fractures are common in the human body.
The doctors use the
X-ray image to diagnose the fractured
bone. The manual
fracture detection technique is time
consuming and also error
probability chance is high. Therefore, an
automated system
needs to develop to diagnose the fractured
bone. The Deep
Neural Network (DNN) is widely used for
the modeling of the
power electronic devices. In the present
study, a deep neural
network model has been developed to
classify the fracture and
healthy bone. The deep learning model
gets over fitted on the
small data set. Therefore, data
augmentation techniques have
been used to increase the size of the data
set. The three
experiments have been performed to
evaluate the performance
of the model using softmax and Adam
optimizer. The
classification accuracy of the proposed
model is 92.44% for the
healthy and the fractured bone using 5 fold
cross validation.
The accuracy on 10% and 20% of the test
data is more than
95% and 93% respectively. The proposed
model performs
much better than [1] of the 84.7% and 86%
of the [2].
The human body contains a lot of bone. The ability to move the body is
provided by bone. The human body frequently experiences bone
fractures. The X-ray image is used by the doctors to identify the
fractured bone. The manual fracture detection method takes a long
time and has a high chance of error. Therefore, it is necessary to create
The bone
an automated system to identify the fractured bone.
is a major component of the human
body. Bone provides the ability to move
the body. The bone
fractures are common in the human body.
The doctors use the
X-ray image to diagnose the fractured
bone. The manual
fracture detection technique is time
consuming and also error
probability chance is high. Therefore, an
automated system
needs to develop to diagnose the fractured
bone. The Deep
Neural Network (DNN) is widely used for
the modeling of the
power electronic devices. In the present
study, a deep neural
network model has been developed to
classify the fracture and
healthy bone. The deep learning model
gets over fitted on the
small data set. Therefore, data
augmentation techniques have
been used to increase the size of the data
set. The three
experiments have been performed to
evaluate the performance
of the model using softmax and Adam
optimizer. The
classification accuracy of the proposed
model is 92.44% for the
healthy and the fractured bone using 5 fold
cross validation.
The accuracy on 10% and 20% of the test
data is more than
95% and 93% respectively. The proposed
model performs
much better than [1] of the 84.7% and 86%
of the [2].
The bone is a major component of the
human
body. Bone provides the ability to move
the body. The bone
fractures are common in the human body.
The doctors use the
X-ray image to diagnose the fractured
bone. The manual
fracture detection technique is time
consuming and also error
probability chance is high. Therefore, an
automated system
needs to develop to diagnose the fractured
bone. The Deep
Neural Network (DNN) is widely used for
the modeling of the
power electronic devices. In the present
study, a deep neural
network model has been developed to
classify the fracture and
healthy bone. The deep learning model
gets over fitted on the
small data set. Therefore, data
augmentation techniques have
been used to increase the size of the data
set. The three
experiments have been performed to
evaluate the performance
of the model using softmax and Adam
optimizer. The
classification accuracy of the proposed
model is 92.44% for the
healthy and the fractured bone using 5 fold
cross validation.
The accuracy on 10% and 20% of the test
data is more than
95% and 93% respectively. The proposed
model performs
much better than [1] of the 84.7% and 86%
of the [2].
The bone is a major component of the
human
body. Bone provides the ability to move
the body. The bone
fractures are common in the human body.
The doctors use the
X-ray image to diagnose the fractured
bone. The manual
fracture detection technique is time
consuming and also error
probability chance is high. Therefore, an
automated system
needs to develop to diagnose the fractured
bone. The Deep
Neural Network (DNN) is widely used for
the modeling of the
power electronic devices. In the present
study, a deep neural
network model has been developed to
classify the fracture and
healthy bone. The deep learning model
gets over fitted on the
small data set. Therefore, data
augmentation techniques have
been used to increase the size of the data
set. The three
experiments have been performed to
evaluate the performance
of the model using softmax and Adam
optimizer. The
classification accuracy of the proposed
model is 92.44% for the
healthy and the fractured bone using 5 fold
cross validation.
The accuracy on 10% and 20% of the test
data is more than
95% and 93% respectively. The proposed
model performs
much better than [1] of the 84.7% and 86%
of the [2].
The human body contains a lot of bone. The ability to move the body is
provided by bone. The human body frequently experiences bone
fractures. The X-ray image is used by the doctors to identify the
fractured bone.
The normal technique takes time and requires expertise. Patients suffer
terrible consequences when a fracture is missed.
The manual fracture detection method takes a long time and has a high
chance of error. Therefore, it is necessary to create an automated
system to identify the fractured bone.
This project was written in Python using the Decto-Python library,
which makes use of the PyTorch model. With the help of the Python
package Detecto.
The system can identify major and minor bone fractures. Based on the
type of fracture, this system involves fracture detection.
 2) Working of the Project

Nowadays, bone fracture is a common issue brought on by traffic

accidents, an unhealthy lifestyle, and numerous other factors. The
human body depends on bones to move and take on shape. A minor
bone fracture impairs the bone's ability to function normally, which has
an impact on the person's ability to move freely.

Human bones commonly fracture. There are numerous methods to find

out shatters. If there is a suspicion X-rays are the main method used to
determine whether a patient has a fracture when they present to
emergency rooms. X-ray recognition economical fracture treatment.

Here, the user uploads the image file and the system will show a
fractured area as highlighted. The user can view the hospital to consult
an Orthopedic surgeon.

The admin can view all the users and manage bone fracture hospitals by
adding, updating, and deleting patients.
3) Advantages
- Efficient use of image processing.
- Automated Fracture Detection.
- This system will ease the work of orthopaedics.
 4) System Description
The system comprises 2 major module with their sub-modules as
follows:

1.User:
 Registration (Name, Age, Gender, Username, Password)
 Login (Username, Password)
 Detection – The upload image file will show the fractured area as
highlighted
 View Hospitals

2. Admin:
 Login
 View Users
 Manage Hospitals of Bone Fracture (Add, Update, Delete)
 5) Project Life Cycle

The waterfall model is a classical model used in the system

development life cycle to create a system with a linear and sequential
approach. It is termed a waterfall because the model develops
systematically from one phase to another in a downward fashion. The
waterfall approach does not define the process to go back to the
previous phase to handle changes in requirements. The waterfall
approach is the earliest approach that was used for software
development.
6) System Requirements

I. Hardware Requirement

i. Laptop or PC
 Windows 7 or higher
 I3 processor system or higher
 4 GB RAM or higher
 100 GB ROM or higher

II. Software Requirement

ii. Laptop or PC
 Python
 Sublime text Editor
 XAMP Server
7) Limitation/Disadvantages
- Not entirely accurate.

8) Application – This system is capable of fracture detection based

on the type of fracture.

9) Reference

- https://ijcrt.org/papers/IJCRT2105699.pdf
- https://www.researchgate.net/publication/
341248451_Bone_Fracture_Detection_and_Classification_using_Dee
p_Learning_Approach
- https://ijcrt.org/papers/IJCRT2105699.pdf
- https://www.researchgate.net/publication/
341248451_Bone_Fracture_Detection_and_Classification_using_Dee
p_Learning_Approach