It is a system used to detect bone fractures. using techniques deep learning and image processing

Overview

MohammedHussiengadalla-Intelligent-Classification-System-for-Bone-Fractures

It is a system used to detect bone fractures. using techniques deep learning and image processing

Transfer learning is a very powerful and bleeding-edge tool to achieve high accuracies on classification tasks on images when the data and the computational power is in limited supply.

Here I attempted to create an Custom Deep Learning model using Deep Neural Networks with intermediate convolutional layers to classify X-ray images of humerus bone fracture from the ones that are not fractured.

As I pass an input image, an output is given as a “Positive” or “Negative” label. The input data is in the form of X Ray images of the Humerus bones. Hence, the effort is to train a Supervised Learning model with the data to give correct label to the input image inorder to predict a fracture. Some preprocessing of the data like converting RGB images to Grayscale, switching between channels_first & channels_last depending upon the backend Deep Learning engine that will be employed for computations will have to be done.

This repository contains a Keras implementation of a 121 layer Densenet Model on MURA dataset with additional 3 Densely Connected Layers at top.

I achieved an accuracy of about 79% after disconnecting the top 60 layers of the pre-trained model and let it train on the new dataset from a ground truth of no more than being a mere chance (i.e. 50%).

The accuracy improved to ~85% after playing aroung with different hyperparameters and got an understanding of what the model is learning by implementing Class Activation Maps on the gradients of intermediate convolution and activation layers.

Here, I trained the Densenet on XR_HUMERUS of the dataset for 40 epochs with a batch size of 16.

You can train the model by running train__humerus_fracture_detection_keras_model.ipynb Jupyter Notebook with necessary directory changes. You can load the trained model by running load_humerus_fracture_detection_keras_model.ipynb Jupyter Notebook. You can visualize model's learning at different intermediate layers by running visualize__humerus_fracture_detection_keras_model_cmap.ipynb Jupyter notebook.

Few visualizations are available in layer outputs directory.

The notebook can be used to implement other available pre-trained models from Tensorflow Keras for Transfer Learning.

Intelligent-Classification.mp4
Owner
Mohammed Hussien
Mohammed Hussien
Official PyTorch implementation of "Improving Face Recognition with Large AgeGaps by Learning to Distinguish Children" (BMVC 2021)

Inter-Prototype (BMVC 2021): Official Project Webpage This repository provides the official PyTorch implementation of the following paper: Improving F

Jungsoo Lee 16 Jun 30, 2022
Food recognition model using convolutional neural network & computer vision

Food recognition model using convolutional neural network & computer vision. The goal is to match or beat the DeepFood Research Paper

Hemanth Chandran 1 Jan 13, 2022
Code and models used in "MUSS Multilingual Unsupervised Sentence Simplification by Mining Paraphrases".

Multilingual Unsupervised Sentence Simplification Code and pretrained models to reproduce experiments in "MUSS: Multilingual Unsupervised Sentence Sim

Facebook Research 81 Dec 29, 2022
Overview of architecture and implementation of TEDS-Net, as described in MICCAI 2021: "TEDS-Net: Enforcing Diffeomorphisms in Spatial Transformers to Guarantee TopologyPreservation in Segmentations"

TEDS-Net Overview of architecture and implementation of TEDS-Net, as described in MICCAI 2021: "TEDS-Net: Enforcing Diffeomorphisms in Spatial Transfo

Madeleine K Wyburd 14 Jan 04, 2023
This is the code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".

HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields This is the code for "HyperNeRF: A Higher-Dimensional

Google 702 Jan 02, 2023
moving object detection for satellite videos.

DSFNet: Dynamic and Static Fusion Network for Moving Object Detection in Satellite Videos Algorithm Introduction DSFNet: Dynamic and Static Fusion Net

xiaochao 39 Dec 16, 2022
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

What's New Below we share, in reverse chronological order, the updates and new releases in VISSL. All VISSL releases are available here. [Oct 2021]: V

Meta Research 2.9k Jan 07, 2023
Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization'

pytorch-AdaIN This is an unofficial pytorch implementation of a paper, Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization [Hua

Naoto Inoue 873 Jan 06, 2023
Pytorch domain adaptation package

DomainAdaptation This package is created to tackle the problem of domain shifts when dealing with two domains of different feature distributions. In d

Institute of Computational Perception 7 Oct 22, 2022
generate-2D-quadrilateral-mesh-with-neural-networks-and-tree-search

generate-2D-quadrilateral-mesh-with-neural-networks-and-tree-search This repository contains single-threaded TreeMesh code. I'm Hua Tong, a senior stu

Hua Tong 18 Sep 21, 2022
September-Assistant - Open-source Windows Voice Assistant

September - Windows Assistant September is an open-source Windows personal assis

The Nithin Balaji 9 Nov 22, 2022
The fundamental package for scientific computing with Python.

NumPy is the fundamental package needed for scientific computing with Python. Website: https://www.numpy.org Documentation: https://numpy.org/doc Mail

NumPy 22.4k Jan 09, 2023
CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

CALVIN CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks Oier Mees, Lukas Hermann, Erick Rosete,

Oier Mees 107 Dec 26, 2022
💛 Code and Dataset for our EMNLP 2021 paper: "Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes"

Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes Official PyTorch implementation and EmoCause evaluatio

Hyunwoo Kim 51 Jan 06, 2023
ElasticFace: Elastic Margin Loss for Deep Face Recognition

This is the official repository of the paper: ElasticFace: Elastic Margin Loss for Deep Face Recognition Paper on arxiv: arxiv Model Log file Pretrain

Fadi Boutros 113 Dec 14, 2022
Pytorch library for end-to-end transformer models training and serving

Pytorch library for end-to-end transformer models training and serving

Mikhail Grankin 768 Jan 01, 2023
Official Pytorch implementation for Deep Contextual Video Compression, NeurIPS 2021

Introduction Official Pytorch implementation for Deep Contextual Video Compression, NeurIPS 2021 Prerequisites Python 3.8 and conda, get Conda CUDA 11

51 Dec 03, 2022
Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective Zhengzhuo Xu, Zenghao Chai, Chun Yuan This is the PyTorch implement

Sincere 16 Dec 15, 2022
Animal Sound Classification (Cats Vrs Dogs Audio Sentiment Classification)

this is a simple artificial neural network model using deep learning and torch-audio to classify cats and dog sounds.

crispengari 3 Dec 05, 2022
A model to classify a piece of news as REAL or FAKE

Fake_news_classification A model to classify a piece of news as REAL or FAKE. This python project of detecting fake news deals with fake and real news

Gokul Stark 1 Jan 29, 2022