Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition

Abstract : In this paper, we propose a convolutional neural network-based method to automatically retrieve missing or noisy cardiac acquisition plane information from magnetic resonance imaging and predict the five most common cardiac views. We fine-tune a convolutional neural network (CNN) initially trained on a large natural image recognition data-set (Imagenet ILSVRC2012) and transfer the learnt feature representations to cardiac view recognition. We contrast this approach with a previously introduced method using classification forests and an augmented set of image miniatures, with prediction using off the shelf CNN features, and with CNNs learnt from scratch. We validate this algorithm on two different cardiac studies with 200 patients and 15 healthy volunteers, respectively. We show that there is value in fine-tuning a model trained for natural images to transfer it to medical images. Our approach achieves an average F1 score of 97.66% and significantly improves the state-of-the-art of image-based cardiac view recognition. This is an important building block to organise and filter large collections of cardiac data prior to further analysis. It allows us to merge studies from multiple centres, to perform smarter image filtering, to select the most appropriate image processing algorithm, and to enhance visualisation of cardiac data-sets in content-based image retrieval.
Type de document :
Article dans une revue
Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, Taylor & Francis, 2015, 〈10.1080/21681163.2015.1061448〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01162880
Contributeur : Jan Margeta <>
Soumis le : vendredi 9 septembre 2016 - 13:02:52
Dernière modification le : jeudi 12 avril 2018 - 11:26:02

Fichier

author_version.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

Collections

Citation

Jan Margeta, Antonio Criminisi, Rocio Cabrera Lozoya, Daniel C. Lee, Nicholas Ayache. Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, Taylor & Francis, 2015, 〈10.1080/21681163.2015.1061448〉. 〈hal-01162880v2〉

Partager

Métriques

Consultations de la notice

510

Téléchargements de fichiers

413