Bone Deformity Identification Using Machine Learning

Project Code :TCMAPY637


The main objective of the project is to identify the severity percentage in bone fracture.


Manual interpretation of the x-rays can sometimes make it difficult to determine whether it is fractured or not. These x-rays provide a clear picture of the damage, but the primary problem is that some doctors fail to spot the minor fractures that could later cause significant harm to the patient. Model that clearly analyses and categorises photos of fractures to the hand, leg, chest, fingers, and wrist. There are numerous alternative methods for spotting these fractures, and this research was shaped by various AI tools that used machine learning and deep learning methods. As it is a methodical procedure of picture analysis algorithm to forecast if the bone is broken or normal, this research explicitly studies several models depending on convolutional neural networks.

The field of life science and its reliance on technology are expanding daily. Alternative tools and computer-assisted medicine have significantly decreased the time-consuming and laborious manual diagnosis processes. However, the process for determining a bone fracture and diagnosing still uses manual review techniques. The technique uses XRAYS to create a partial XRAY image of the fractured area, which is then manually reviewed by the doctors to determine the type and location of the fracture. The old process is not only time-consuming, but also tiresome and might result in incorrect diagnosis due to human error. To determine and categorise the precise kind of fracture, accurate categorization requires extensive experience. The idea of bone fracture detection and classification in XRAY images victimisation machine learning is put out in this research. The XRAY images are fed into a neural network model that has been trained on a sizable coaching dataset corresponding to various sorts of fractures. To improve the categorization and identification of bone fractures using abstract thought, coaching data and input settings have been fine-tuned. Python is used to create a software system that can import the image to be identified and supply the model with abstract ideas about the fracture. Utilizing the same image data set and contrasting CNN and SVM models.

Keyword: Bone fracture, Deep Learning, Machine Learning, Fracture classification, CNN, SVM


NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Block Diagram


H/W Specifications:

  • Processor : I5/Intel Processor
  • RAM:  8GB (min)
  • Hard Disk :128 GB

S/W Specifications:

  • Operating System :   Windows 10
  • Server-side Script: Python 3.6
  • IDE : PyCharm, Jupyter notebook
  • Libraries Used: Numpy, IO, OS, Flask, Keras, pandas, tensorflow

Learning Outcomes

        Practical exposure to

·         Hardware and software tools

·         Solution providing for real time problems

·         Working with team/individual

·         Work on creative ideas

·         Testing techniques

·         Error correction mechanisms

·         What type of technology versions is used?

·         Working of Tensor Flow

·         Implementation of Deep Learning techniques

·         Working of CNN algorithm

·         Working of Transfer Learning methods

·         Building of model creations

·         Scope of project

·         Applications of the project

·         About Python language

·         About Deep Learning Frameworks

·         Use of Data Science

Demo Video

Request Video

Related Projects

Final year projects