no code implementations • 19 Nov 2021 • Ashkan Pakzad, Wing Keung Cheung, Kin Quan, Nesrin Mogulkoc, Coline H. M. Van Moorsel, Brian J. Bartholmai, Hendrik W. Van Es, Alper Ezircan, Frouke Van Beek, Marcel Veltkamp, Ronald Karwoski, Tobias Peikert, Ryan D. Clay, Finbar Foley, Cassandra Braun, Recep Savas, Carole Sudre, Tom Doel, Daniel C. Alexander, Peter Wijeratne, David Hawkes, Yipeng Hu, John R Hurst, Joseph Jacob
AirQuant is an open-source pipeline that avoids limitations of existing airway quantification algorithms and has clinical interpretability.
Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes.
no code implementations • 12 Oct 2021 • Ester Bonmati, Yipeng Hu, Alexander Grimwood, Gavin J. Johnson, George Goodchild, Margaret G. Keane, Kurinchi Gurusamy, Brian Davidson, Matthew J. Clarkson, Stephen P. Pereira, Dean C. Barratt
In this work, we propose a multi-modal convolutional neural network (CNN) architecture that labels endoscopic ultrasound (EUS) images from raw verbal comments provided by a clinician during the procedure.
Consisting of two modules, a global feature extraction module and a point transformation module, FPT does not assume explicit constraints based on point vicinity, thereby overcoming a common requirement of previous learning-based point-set registration methods.
no code implementations • 6 Aug 2021 • Harry Mason, Lorenzo Cristoni, Andrew Walden, Roberto Lazzari, Thomas Pulimood, Louis Grandjean, Claudia AM Gandini Wheeler-Kingshott, Yipeng Hu, Zachary MC Baum
Furthermore, we offer a possible explanation that correlates the segmentation performance to label consistency and data domain diversity in this point-of-care lung ultrasound application.
1 code implementation • 31 Jul 2021 • Shaheer U. Saeed, Yunguan Fu, Vasilis Stavrinides, Zachary M. C. Baum, Qianye Yang, Mirabela Rusu, Richard E. Fan, Geoffrey A. Sonn, J. Alison Noble, Dean C. Barratt, Yipeng Hu
Using 6644 clinical ultrasound images from 249 prostate cancer patients, our results for image classification and segmentation tasks show that the proposed IQA method can be adapted using data with as few as respective 19. 7% and 29. 6% expert-reviewed consensus labels and still achieve comparable IQA and task performance, which would otherwise require a training dataset with 100% expert labels.
1 code implementation • 28 Jul 2021 • Liam F Chalcroft, Jiongqi Qu, Sophie A Martin, Iani JMB Gayo, Giulio V Minore, Imraj RD Singh, Shaheer U Saeed, Qianye Yang, Zachary MC Baum, Andre Altmann, Yipeng Hu
When developing deep neural networks for segmenting intraoperative ultrasound images, several practical issues are encountered frequently, such as the presence of ultrasound frames that do not contain regions of interest and the high variance in ground-truth labels.
Prostate cancer (PCa) is one of the leading causes of death for men worldwide.
Accurate multi-class segmentation is a long-standing challenge in medical imaging, especially in scenarios where classes share strong similarity.
In this paper, we consider a type of image quality assessment as a task-specific measurement, which can be used to select images that are more amenable to a given target task, such as image classification or segmentation.
Organ morphology is a key indicator for prostate disease diagnosis and prognosis.
1 code implementation • 4 Nov 2020 • Yunguan Fu, Nina Montaña Brown, Shaheer U. Saeed, Adrià Casamitjana, Zachary M. C. Baum, Rémi Delaunay, Qianye Yang, Alexander Grimwood, Zhe Min, Stefano B. Blumberg, Juan Eugenio Iglesias, Dean C. Barratt, Ester Bonmati, Daniel C. Alexander, Matthew J. Clarkson, Tom Vercauteren, Yipeng Hu
DeepReg (https://github. com/DeepRegNet/DeepReg) is a community-supported open-source toolkit for research and education in medical image registration using deep learning.
For images with unanimous consensus between observers, anatomical classification accuracy was 97. 2% and probe adjustment accuracy was 94. 9%.
Morphological analysis of longitudinal MR images plays a key role in monitoring disease progression for prostate cancer patients, who are placed under an active surveillance program.
no code implementations • 20 Aug 2020 • Zachary M. C. Baum, Ester Bonmati, Lorenzo Cristoni, Andrew Walden, Ferran Prados, Baris Kanber, Dean C. Barratt, David J. Hawkes, Geoffrey J M Parker, Claudia A M Gandini Wheeler-Kingshott, Yipeng Hu
The diagnosis assistance module can then be trained with data that are deemed of sufficient quality, guaranteed by the closed-loop feedback mechanism from the quality assessment module.
We describe a point-set registration algorithm based on a novel free point transformer (FPT) network, designed for points extracted from multimodal biomedical images for registration tasks, such as those frequently encountered in ultrasound-guided interventional procedures.
Based on 160, 000 nonlinear FE simulations on clinical imaging data from 320 patients, we demonstrate that the trained networks generalise to unstructured point sets sampled directly from holdout patient segmentation, yielding a near real-time inference and an expected error of 0. 017 mm in predicted nodal displacement.
The COVID-19 pandemic, caused by the severe acute respiratory syndrome coronavirus 2, emerged into a world being rapidly transformed by artificial intelligence (AI) based on big data, computational power and neural networks.
Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most clinical applications.
Classical pairwise image registration methods search for a spatial transformation that optimises a numerical measure that indicates how well a pair of moving and fixed images are aligned.
no code implementations • 9 Jul 2018 • Yipeng Hu, Marc Modat, Eli Gibson, Wenqi Li, Nooshin Ghavami, Ester Bonmati, Guotai Wang, Steven Bandula, Caroline M. Moore, Mark Emberton, Sébastien Ourselin, J. Alison Noble, Dean C. Barratt, Tom Vercauteren
A median target registration error of 3. 6 mm on landmark centroids and a median Dice of 0. 87 on prostate glands are achieved from cross-validation experiments, in which 108 pairs of multimodal images from 76 patients were tested with high-quality anatomical labels.
During training, the registration network simultaneously aims to maximize similarity between anatomical labels that drives image alignment and to minimize an adversarial generator loss that measures divergence between the predicted- and simulated deformation.
Results show a median Dice similarity coefficient of 0. 90 with an interquartile range of 0. 08, with equivalent performance to the three operators (with a Williams' index of 1. 03), and outperforming a U-Net architecture without the need for batch normalisation.
Spatially aligning medical images from different modalities remains a challenging task, especially for intraoperative applications that require fast and robust algorithms.
10 code implementations • 11 Sep 2017 • Eli Gibson, Wenqi Li, Carole Sudre, Lucas Fidon, Dzhoshkun I. Shakir, Guotai Wang, Zach Eaton-Rosen, Robert Gray, Tom Doel, Yipeng Hu, Tom Whyntie, Parashkev Nachev, Marc Modat, Dean C. Barratt, Sébastien Ourselin, M. Jorge Cardoso, Tom Vercauteren
NiftyNet provides a modular deep-learning pipeline for a range of medical imaging applications including segmentation, regression, image generation and representation learning applications.
In this paper, we describe how a patient-specific, ultrasound-probe-induced prostate motion model can be directly generated from a single preoperative MR image.
Sonography synthesis has a wide range of applications, including medical procedure simulation, clinical training and multimodality image registration.