Antonio Criminisi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Antonio Criminisi has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Abigail Sellen
Microsoft Research, Cambridge, United Kingdom
1 shared publication - Andrew Blake
Clare Hall, University of Cambridge, Cambridge, U.K.
1 shared publication - Bernard M. J. Uitdehaag
MS Center Amsterdam, Department of Neurology, Vrije Universiteit Amsterdam, Amsterdam Neuroscience, Amsterdam UMC Location VUmc, Amsterdam, The Netherlands
1 shared publication - Cecily Morrison
Microsoft Research, Cambridge, United Kingdom
1 shared publication - Christian Philipp Kamm
Department of Neurology, Inselspital, University Hospital Bern and University of Bern, Bern, Switzerland; Neurocentre, Luzerner Kantonsspital, Lucerne, Switzerland
1 shared publication - Daniel C. Lee
Department of Radiology, Northwestern University Feinberg School of Medicine, 737 N Michigan Ave, Ste 1600, Chicago, IL 60611
1 shared publication
Latest Publications
- 13 August 2015
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 5 (5) , 339-349
Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition
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.
- 13 August 2015
- Published by Taylor & Francis in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
- Vol. 5 (5) , 339-349
Fine-tuned convolutional neural nets for cardiac MRI acquisition plane recognition
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.
- Open Access
- 24 June 2015
- Published by JMIR Publications Inc. in JMIR Human Factors
- Vol. 2 (1) , e11
Usability and Acceptability of ASSESS MS: Assessment of Motor Dysfunction in Multiple Sclerosis Using Depth-Sensing Computer Vision
JMIR Human Factors - a leading peer-reviewed ehealth journal
- 24 June 2015
- Published by JMIR Publications Inc. in JMIR Human Factors
- Vol. 2 (1) , e11
Open AccessUsability and Acceptability of ASSESS MS: Assessment of Motor Dysfunction in Multiple Sclerosis Using Depth-Sensing Computer Vision
JMIR Human Factors - a leading peer-reviewed ehealth journal
- 13 November 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10636919) , 342-349
The SPS algorithm: patching figural continuity and transparency by split-patch search
This paper describes a novel algorithm for the efficient synthesis of high-quality virtual views from only two input images. The emphasis is on the recovery of continuity of objects boundaries (figural continuity) with faithful synthesis of transparency effects. The contribution of this paper is two-fold: (i) the split-patch search (SPS) technique is introduced for dense stereo which handles transparency effects by assigning multiple disparities to mixed pixels; (ii) an efficient extension of exemplar-based image synthesis to the case of two-camera stereo is proposed. Furthermore, this paper presents an approximate but effective solution to the challenging problem of layer estimation and compositing in the case of small image patches. The effectiveness of the proposed technique is demonstrated on a number of stereo image pairs taken from two camera video-conferencing setups, where the quality of the synthesized talking heads is of paramount importance. Moreover the improvement in the quality of image synthesis is quantified by comparing the output of the SPS algorithm with thirteen ground-truth images.
- 13 November 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10636919) , 342-349
The SPS algorithm: patching figural continuity and transparency by split-patch search
This paper describes a novel algorithm for the efficient synthesis of high-quality virtual views from only two input images. The emphasis is on the recovery of continuity of objects boundaries (figural continuity) with faithful synthesis of transparency effects. The contribution of this paper is two-fold: (i) the split-patch search (SPS) technique is introduced for dense stereo which handles transparency effects by assigning multiple disparities to mixed pixels; (ii) an efficient extension of exemplar-based image synthesis to the case of two-camera stereo is proposed. Furthermore, this paper presents an approximate but effective solution to the challenging problem of layer estimation and compositing in the case of small image patches. The effectiveness of the proposed technique is demonstrated on a number of stereo image pairs taken from two camera video-conferencing setups, where the quality of the synthesized talking heads is of paramount importance. Moreover the improvement in the quality of image synthesis is quantified by comparing the output of the SPS algorithm with thirteen ground-truth images.