GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → desimone → Musculoskeletal-Radiographs-Abnormality-Classifier

desimone / Musculoskeletal-Radiographs-Abnormality-Classifier

Licence: MIT license
An implementation of MURA Dataset Towards Radiologist-Level Abnormality Detection in Musculoskeletal Radiographs

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language
shell
77523 projects

Labels

deep-learningkeraspytorchmedical-imaging

Projects that are alternatives of or similar to Musculoskeletal-Radiographs-Abnormality-Classifier

medSeg
Medical Image Segmentation Toolkit based on PaddlePaddle - 基于paddle的医学影像分割框架
Stars: ✭ 88 (+137.84%)
Mutual labels:  medical-imaging
clara-dicom-adapter
DICOM Adapter is a component of the Clara Deploy SDK which facilitates integration with DICOM compliant systems, enables ingestion of imaging data, helps triggering of jobs with configurable rules and offers pushing the output of jobs to PACS systems.
Stars: ✭ 31 (-16.22%)
Mutual labels:  medical-imaging
MONAILabel
MONAI Label is an intelligent open source image labeling and learning tool.
Stars: ✭ 249 (+572.97%)
Mutual labels:  medical-imaging
survey-computer-vision-2021
2021年计算机视觉技术综述分类汇总
Stars: ✭ 54 (+45.95%)
Mutual labels:  medical-imaging
dwv-vue
Medical image viewer using DWV (DICOM Web Viewer) and Vue.js.
Stars: ✭ 66 (+78.38%)
Mutual labels:  medical-imaging
VNet
Prostate MR Image Segmentation 2012
Stars: ✭ 54 (+45.95%)
Mutual labels:  medical-imaging
ITKSphinxExamples
Cookbook examples for the Insight Toolkit documented with Sphinx
Stars: ✭ 48 (+29.73%)
Mutual labels:  medical-imaging
LibAUC
An End-to-End Machine Learning Library to Optimize AUC (AUROC, AUPRC).
Stars: ✭ 115 (+210.81%)
Mutual labels:  medical-imaging
angiodysplasia-segmentation
Wining solution and its further development for MICCAI 2017 Endoscopic Vision Challenge Angiodysplasia Detection and Localization
Stars: ✭ 76 (+105.41%)
Mutual labels:  medical-imaging
cuda spatial deform
A fast tool to do image augmentation on GPU(especially elastic_deform), can be helpful to research on Medical Image.
Stars: ✭ 115 (+210.81%)
Mutual labels:  medical-imaging
fuse-med-ml
A python framework accelerating ML based discovery in the medical field by encouraging code reuse. Batteries included :)
Stars: ✭ 66 (+78.38%)
Mutual labels:  medical-imaging
Brain-MRI-Segmentation
Smart India Hackathon 2019 project given by the Department of Atomic Energy
Stars: ✭ 29 (-21.62%)
Mutual labels:  medical-imaging
Fundus Review
Official website of our paper: Applications of Deep Learning in Fundus Images: A Review. Newly-released datasets and recently-published papers will be updated regularly.
Stars: ✭ 64 (+72.97%)
Mutual labels:  medical-imaging
GMIC
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
Stars: ✭ 106 (+186.49%)
Mutual labels:  medical-imaging
dwv-jqmobile
Medical image viewer using DWV (DICOM Web Viewer) and jQuery Mobile.
Stars: ✭ 25 (-32.43%)
Mutual labels:  medical-imaging
FAIR.m
Flexible Algorithms for Image Registration
Stars: ✭ 103 (+178.38%)
Mutual labels:  medical-imaging
modelhub
A collection of deep learning models with a unified API.
Stars: ✭ 59 (+59.46%)
Mutual labels:  medical-imaging
PETPVC
Partial Volume Correction in PET
Stars: ✭ 29 (-21.62%)
Mutual labels:  medical-imaging
Improved-Wasserstein-GAN-application-on-MRI-images
Improved Wasserstein GAN (WGAN-GP) application on medical (MRI) images
Stars: ✭ 23 (-37.84%)
Mutual labels:  medical-imaging
medical image segmentation
Medical image segmentation ( Eye vessel segmentation)
Stars: ✭ 90 (+143.24%)
Mutual labels:  medical-imaging
View All Similar Projects ➔

Musculoskeletal Radiographs Abnormality Classifier

Experiments

Network Accuracy (encounter) Precision (encounter) Recall (encounter) F1 (encounter) Kappa (encounter)
DenseNet169 (baseline) .83 (.84) .82 (.82) .87 (.90) .84 (.86) .65 (.65)
MobileNet .81 (.83) .80 (.82) .85 (.89) .82 (.85) .62 (.62)
NASNetMobile .82 (.83) .78 (.80) .89 (.92) .83 (.86) .63 (.63)

Also, ResNet50 in pytorch which achieved equivalent results.

The Mura Dataset

@misc{1712.06957,
Author = {Pranav Rajpurkar and Jeremy Irvin and Aarti Bagul and Daisy Ding and Tony Duan and Hershel Mehta and Brandon Yang and Kaylie Zhu and Dillon Laird and Robyn L. Ball and Curtis Langlotz and Katie Shpanskaya and Matthew P. Lungren and Andrew Ng},
Title = {MURA Dataset: Towards Radiologist-Level Abnormality Detection in Musculoskeletal Radiographs},
Year = {2017},
Eprint = {arXiv:1712.06957},}
Study Normal Abnormal Total
Elbow 1,203 768 1,971
Finger 1,389 753 2,142
Forearm 677 380 1,057
Hand 1,613 602 2,215
Humerus 411 367 778
Shoulder 1,479 1,594 3,073
Wrist 2,295 1,451 3,746
Total 9,067 5,915 14,982
  • Each study contains 1-N views (images)
  • 40,895 multi-view radiographic images

Their results (DenseNet169)

Radiologists (95% CI) Model (95% CI)
Elbow 0.858 (0.707, 0.959) 0.848 (0.691, 0.955)
Finger 0.781 (0.638, 0.871) 0.792 (0.588, 0.933)
Forearm 0.899 (0.804, 0.960) 0.814 (0.633, 0.942)
Hand 0.854 (0.676, 0.958) 0.858 (0.658, 0.978)
Humerus 0.895 (0.774, 0.976) 0.862 (0.709, 0.968)
Shoulder 0.925 (0.811, 0.989) 0.857 (0.667, 0.974)
Wrist 0.958 (0.908, 0.988) 0.968 (0.889, 1.000)
Aggregate F1 0.884 (0.843, 0.918) 0.859 (0.804, 0.905)
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].