Zobrazeno 1 - 10
of 64
pro vyhledávání: '"Clough, James R"'
Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular CNN-based methods are optimised using pixel wise loss functions, ignora
Externí odkaz:
http://arxiv.org/abs/2107.12689
With respect to spatial overlap, CNN-based segmentation of short axis cardiovascular magnetic resonance (CMR) images has achieved a level of performance consistent with inter observer variation. However, conventional training procedures frequently de
Externí odkaz:
http://arxiv.org/abs/2008.09585
Autor:
Puyol-Antón, Esther, Chen, Chen, Clough, James R., Ruijsink, Bram, Sidhu, Baldeep S., Gould, Justin, Porter, Bradley, Elliott, Mark, Mehta, Vishal, Rueckert, Daniel, Rinaldi, Christopher A., King, Andrew P.
Advances in deep learning (DL) have resulted in impressive accuracy in some medical image classification tasks, but often deep models lack interpretability. The ability of these models to explain their decisions is important for fostering clinical tr
Externí odkaz:
http://arxiv.org/abs/2006.13811
Autor:
Oksuz, Ilkay, Clough, James R., Ruijsink, Bram, Anton, Esther Puyol, Bustin, Aurelien, Cruz, Gastao, Prieto, Claudia, King, Andrew P., Schnabel, Julia A.
Segmenting anatomical structures in medical images has been successfully addressed with deep learning methods for a range of applications. However, this success is heavily dependent on the quality of the image that is being segmented. A commonly negl
Externí odkaz:
http://arxiv.org/abs/1910.05370
Autor:
Clough, James R., Byrne, Nicholas, Oksuz, Ilkay, Zimmer, Veronika A., Schnabel, Julia A., King, Andrew P.
We introduce a method for training neural networks to perform image or volume segmentation in which prior knowledge about the topology of the segmented object can be explicitly provided and then incorporated into the training process. By using the di
Externí odkaz:
http://arxiv.org/abs/1910.01877
Autor:
Schlemper, Jo, Oksuz, Ilkay, Clough, James R., Duan, Jinming, King, Andrew P., Schnabel, Julia A., Hajnal, Joseph V., Rueckert, Daniel
AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the domain transformation of AUTOMAP, making the model scale linearly. We
Externí odkaz:
http://arxiv.org/abs/1909.10995
Autor:
Zhang, Tong, Jackson, Laurence H., Uus, Alena, Clough, James R., Story, Lisa, Rutherford, Mary A., Hajnal, Joseph V., Deprez, Maria
Accurately estimating and correcting the motion artifacts are crucial for 3D image reconstruction of the abdominal and in-utero magnetic resonance imaging (MRI). The state-of-art methods are based on slice-to-volume registration (SVR) where multiple
Externí odkaz:
http://arxiv.org/abs/1908.10842
Patient-specific 3D printing of congenital heart anatomy demands an accurate segmentation of the thin tissue interfaces which characterise these diagnoses. Even when a label set has a high spatial overlap with the ground truth, inaccurate delineation
Externí odkaz:
http://arxiv.org/abs/1908.08870
Autor:
Puyol-Antón, Esther, Ruijsink, Bram, Clough, James R., Oksuz, Ilkay, Rueckert, Daniel, Razavi, Reza, King, Andrew P.
Maintaining good cardiac function for as long as possible is a major concern for healthcare systems worldwide and there is much interest in learning more about the impact of different risk factors on cardiac health. The aim of this study is to analyz
Externí odkaz:
http://arxiv.org/abs/1908.04538
Autor:
Clough, James R., Oksuz, Ilkay, Puyol-Anton, Esther, Ruijsink, Bram, King, Andrew P., Schnabel, Julia A.
Deep learning methods for classifying medical images have demonstrated impressive accuracy in a wide range of tasks but often these models are hard to interpret, limiting their applicability in clinical practice. In this work we introduce a convoluti
Externí odkaz:
http://arxiv.org/abs/1906.06188