Assessing Knee OA Severity with CNN attention-based end-to-end architectures

Marc Górriz	Joseph Antony	Kevin McGuinness	Xavier Giro-i-Nieto	Noel E. O'Connor

A joint collaboration between:

Insight Centre for Data Analytics	Dublin City University (DCU)	UPC Image Processing Group

Abstract

This work proposes a novel end-to-end convolutional neural network (CNN) architecture to automatically quantify the severity of knee osteoarthritis (OA) using X-Ray images, which incorporates trainable attention modules acting as unsupervised fine-grained detectors of the region of interest (ROI). The proposed attention modules can be applied at different levels and scales across any CNN pipeline helping the network to learn relevant attention patterns over the most informative parts of the image at different resolutions. We test the proposed attention mechanism on existing state-of-the-art CNN architectures as our base models, achieving promising results on the benchmark knee OA datasets from the osteoarthritis initiative (OAI) and multicenter osteoarthritis study (MOST).

Publication

International Conference on Medical Imaging with Deep Learning (MIDL) 2019, London, United Kingdom. Find the pre-print version of our work on mlr.press.

Please cite with the following Bibtex code:

@inproceedings{gorriz2019assessing,
  title={Assessing Knee OA Severity with CNN attention-based end-to-end architectures},
  author={G{\'o}rriz, Marc and Antony, Joseph and McGuinness, Kevin and Gir{\'o}-i-Nieto, Xavier and O’Connor, Noel E},
  booktitle={International Conference on Medical Imaging with Deep Learning},
  pages={197--214},
  year={2019}
}

How to use

Dependencies

The model is implemented in Keras, which at its time is developed over TensorFlow. Also, this code should be compatible with Python 3.4.2.

pip install -r https://github.com/marc-gorriz/KneeOA-CNNAttention/blob/master/requeriments.txt

Launch an experiment

• Make a new configuration file based on the available templates and save it into the config directory. Make sure to launch all the processes over GPU. On this project there was used an NVIDIA GTX Titan X.

• To train a new model, run python train.py --config config/[config file].py.

Acknowledgements

We would like to especially thank Albert Gil Moreno from our technical support team at the Image Processing Group at the UPC.

Albert Gil

We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GeoForce GTX Titan X used in this work.
The Image ProcessingGroup at the UPC is a SGR14 Consolidated Research Group recognized and sponsored by the Catalan Government (Generalitat de Catalunya) through its AGAUR office.

Contact

If you have any general doubt about our work or code which may be of interest for other researchers, please use the public issues section on this github repo. Alternatively, drop us an e-mail at mailto:[email protected].