Models, code, and papers for "Martin Rajchl":

Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging

Jun 14, 2018
Xiaoran Chen, Nick Pawlowski, Martin Rajchl, Ben Glocker, Ender Konukoglu

Recent advances in deep learning led to novel generative modeling techniques that achieve unprecedented quality in generated samples and performance in learning complex distributions in imaging data. These new models in medical image computing have important applications that form clinically relevant and very challenging unsupervised learning problems. In this paper, we explore the feasibility of using state-of-the-art auto-encoder-based deep generative models, such as variational and adversarial auto-encoders, for one such task: abnormality detection in medical imaging. We utilize typical, publicly available datasets with brain scans from healthy subjects and patients with stroke lesions and brain tumors. We use the data from healthy subjects to train different auto-encoder based models to learn the distribution of healthy images and detect pathologies as outliers. Models that can better learn the data distribution should be able to detect outliers more accurately. We evaluate the detection performance of deep generative models and compare them with non-deep learning based approaches to provide a benchmark of the current state of research. We conclude that abnormality detection is a challenging task for deep generative models and large room exists for improvement. In order to facilitate further research, we aim to provide carefully pre-processed imaging data available to the research community.

* 10 pages. 3 figures 

  Click for Model/Code and Paper
NeuroNet: Fast and Robust Reproduction of Multiple Brain Image Segmentation Pipelines

Jun 11, 2018
Martin Rajchl, Nick Pawlowski, Daniel Rueckert, Paul M. Matthews, Ben Glocker

NeuroNet is a deep convolutional neural network mimicking multiple popular and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM. The network is trained on 5,000 T1-weighted brain MRI scans from the UK Biobank Imaging Study that have been automatically segmented into brain tissue and cortical and sub-cortical structures using the standard neuroimaging pipelines. Training a single model from these complementary and partially overlapping label maps yields a new powerful "all-in-one", multi-output segmentation tool. The processing time for a single subject is reduced by an order of magnitude compared to running each individual software package. We demonstrate very good reproducibility of the original outputs while increasing robustness to variations in the input data. We believe NeuroNet could be an important tool in large-scale population imaging studies and serve as a new standard in neuroscience by reducing the risk of introducing bias when choosing a specific software package.

* International conference on Medical Imaging with Deep Learning (MIDL) 2018 

  Click for Model/Code and Paper
A Proximal Bregman Projection Approach to Continuous Max-Flow Problems Using Entropic Distances

Jan 30, 2015
John S. H. Baxter, Martin Rajchl, Jing Yuan, Terry M. Peters

One issue limiting the adaption of large-scale multi-region segmentation is the sometimes prohibitive memory requirements. This is especially troubling considering advances in massively parallel computing and commercial graphics processing units because of their already limited memory compared to the current random access memory used in more traditional computation. To address this issue in the field of continuous max-flow segmentation, we have developed a \textit{pseudo-flow} framework using the theory of Bregman proximal projections and entropic distances which implicitly represents flow variables between labels and designated source and sink nodes. This reduces the memory requirements for max-flow segmentation by approximately 20\% for Potts models and approximately 30\% for hierarchical max-flow (HMF) and directed acyclic graph max-flow (DAGMF) models. This represents a great improvement in the state-of-the-art in max-flow segmentation, allowing for much larger problems to be addressed and accelerated using commercially available graphics processing hardware.

* 10 pages 

  Click for Model/Code and Paper
A Continuous Max-Flow Approach to Multi-Labeling Problems under Arbitrary Region Regularization

Jun 05, 2014
John S. H. Baxter, Martin Rajchl, Jing Yuan, Terry M. Peters

The incorporation of region regularization into max-flow segmentation has traditionally focused on ordering and part-whole relationships. A side effect of the development of such models is that it constrained regularization only to those cases, rather than allowing for arbitrary region regularization. Directed Acyclic Graphical Max-Flow (DAGMF) segmentation overcomes these limitations by allowing for the algorithm designer to specify an arbitrary directed acyclic graph to structure a max-flow segmentation. This allows for individual 'parts' to be a member of multiple distinct 'wholes.'

* 10 pages, 2 figures, 3 algorithms - v2: Fixed typos / grammatical errors and mathematical errors in the primal/dual formulation. Extended methods for weighted DAGs rather than DAGs with edge multiplicity 

  Click for Model/Code and Paper
A Continuous Max-Flow Approach to General Hierarchical Multi-Labeling Problems

Jun 05, 2014
John S. H. Baxter, Martin Rajchl, Jing Yuan, Terry M. Peters

Multi-region segmentation algorithms often have the onus of incorporating complex anatomical knowledge representing spatial or geometric relationships between objects, and general-purpose methods of addressing this knowledge in an optimization-based manner have thus been lacking. This paper presents Generalized Hierarchical Max-Flow (GHMF) segmentation, which captures simple anatomical part-whole relationships in the form of an unconstrained hierarchy. Regularization can then be applied to both parts and wholes independently, allowing for spatial grouping and clustering of labels in a globally optimal convex optimization framework. For the purposes of ready integration into a variety of segmentation tasks, the hierarchies can be presented in run-time, allowing for the segmentation problem to be readily specified and alternatives explored without undue programming effort or recompilation.

* 11 pages, 1 figure, 3 algorithms -v2: Fixed typos / grammatical errors 

  Click for Model/Code and Paper
Implicit Weight Uncertainty in Neural Networks

May 25, 2018
Nick Pawlowski, Andrew Brock, Matthew C. H. Lee, Martin Rajchl, Ben Glocker

Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such as Bayes by Backprop or Multiplicative Normalising Flows). However, current approaches have limitations regarding flexibility and scalability. We introduce Bayes by Hypernet (BbH), a new method of variational approximation that interprets hypernetworks as implicit distributions. It naturally uses neural networks to model arbitrarily complex distributions and scales to modern deep learning architectures. In our experiments, we demonstrate that our method achieves competitive accuracies and predictive uncertainties on MNIST and a CIFAR5 task, while being the most robust against adversarial attacks.

* Submitted to NIPS 2018, under review 

  Click for Model/Code and Paper
Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks

Jun 14, 2017
Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, Matthew Lee, Ben Glocker, Daniel Rueckert

Evaluating similarity between graphs is of major importance in several computer vision and pattern recognition problems, where graph representations are often used to model objects or interactions between elements. The choice of a distance or similarity metric is, however, not trivial and can be highly dependent on the application at hand. In this work, we propose a novel metric learning method to evaluate distance between graphs that leverages the power of convolutional neural networks, while exploiting concepts from spectral graph theory to allow these operations on irregular graphs. We demonstrate the potential of our method in the field of connectomics, where neuronal pathways or functional connections between brain regions are commonly modelled as graphs. In this problem, the definition of an appropriate graph similarity function is critical to unveil patterns of disruptions associated with certain brain disorders. Experimental results on the ABIDE dataset show that our method can learn a graph similarity metric tailored for a clinical application, improving the performance of a simple k-nn classifier by 11.9% compared to a traditional distance metric.

* International Conference on Medical Image Computing and Computer-Assisted Interventions (MICCAI) 2017 

  Click for Model/Code and Paper
Employing Weak Annotations for Medical Image Analysis Problems

Aug 21, 2017
Martin Rajchl, Lisa M. Koch, Christian Ledig, Jonathan Passerat-Palmbach, Kazunari Misawa, Kensaku Mori, Daniel Rueckert

To efficiently establish training databases for machine learning methods, collaborative and crowdsourcing platforms have been investigated to collectively tackle the annotation effort. However, when this concept is ported to the medical imaging domain, reading expertise will have a direct impact on the annotation accuracy. In this study, we examine the impact of expertise and the amount of available annotations on the accuracy outcome of a liver segmentation problem in an abdominal computed tomography (CT) image database. In controlled experiments, we study this impact for different types of weak annotations. To address the decrease in accuracy associated with lower expertise, we propose a method for outlier correction making use of a weakly labelled atlas. Using this approach, we demonstrate that weak annotations subject to high error rates can achieve a similarly high accuracy as state-of-the-art multi-atlas segmentation approaches relying on a large amount of expert manual segmentations. Annotations of this nature can realistically be obtained from a non-expert crowd and can potentially enable crowdsourcing of weak annotation tasks for medical image analysis.


  Click for Model/Code and Paper
DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images

Nov 18, 2017
Nick Pawlowski, Sofia Ira Ktena, Matthew C. H. Lee, Bernhard Kainz, Daniel Rueckert, Ben Glocker, Martin Rajchl

We present DLTK, a toolkit providing baseline implementations for efficient experimentation with deep learning methods on biomedical images. It builds on top of TensorFlow and its high modularity and easy-to-use examples allow for a low-threshold access to state-of-the-art implementations for typical medical imaging problems. A comparison of DLTK's reference implementations of popular network architectures for image segmentation demonstrates new top performance on the publicly available challenge data "Multi-Atlas Labeling Beyond the Cranial Vault". The average test Dice similarity coefficient of $81.5$ exceeds the previously best performing CNN ($75.7$) and the accuracy of the challenge winning method ($79.0$).

* Submitted to Medical Imaging Meets NIPS 2017, Code at https://github.com/DLTK/DLTK 

  Click for Model/Code and Paper
Multi-Atlas Segmentation using Partially Annotated Data: Methods and Annotation Strategies

Apr 29, 2016
Lisa M. Koch, Martin Rajchl, Wenjia Bai, Christian F. Baumgartner, Tong Tong, Jonathan Passerat-Palmbach, Paul Aljabar, Daniel Rueckert

Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets. However, the availability of fully annotated atlas images for training is limited due to the time required for the labelling task. Segmentation methods requiring only a proportion of each atlas image to be labelled could therefore reduce the workload on expert raters tasked with annotating atlas images. To address this issue, we first re-examine the labelling problem common in many existing approaches and formulate its solution in terms of a Markov Random Field energy minimisation problem on a graph connecting atlases and the target image. This provides a unifying framework for multi-atlas segmentation. We then show how modifications in the graph configuration of the proposed framework enable the use of partially annotated atlas images and investigate different partial annotation strategies. The proposed method was evaluated on two Magnetic Resonance Imaging (MRI) datasets for hippocampal and cardiac segmentation. Experiments were performed aimed at (1) recreating existing segmentation techniques with the proposed framework and (2) demonstrating the potential of employing sparsely annotated atlas data for multi-atlas segmentation.


  Click for Model/Code and Paper
RANCOR: Non-Linear Image Registration with Total Variation Regularization

Apr 09, 2014
Martin Rajchl, John S. H. Baxter, Wu Qiu, Ali R. Khan, Aaron Fenster, Terry M. Peters, Jing Yuan

Optimization techniques have been widely used in deformable registration, allowing for the incorporation of similarity metrics with regularization mechanisms. These regularization mechanisms are designed to mitigate the effects of trivial solutions to ill-posed registration problems and to otherwise ensure the resulting deformation fields are well-behaved. This paper introduces a novel deformable registration algorithm, RANCOR, which uses iterative convexification to address deformable registration problems under total-variation regularization. Initial comparative results against four state-of-the-art registration algorithms are presented using the Internet Brain Segmentation Repository (IBSR) database.

* 9 pages, 1 figure, technical note 

  Click for Model/Code and Paper
Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation

Nov 04, 2017
Konstantinos Kamnitsas, Wenjia Bai, Enzo Ferrante, Steven McDonagh, Matthew Sinclair, Nick Pawlowski, Martin Rajchl, Matthew Lee, Bernhard Kainz, Daniel Rueckert, Ben Glocker

Deep learning approaches such as convolutional neural nets have consistently outperformed previous methods on challenging tasks such as dense, semantic segmentation. However, the various proposed networks perform differently, with behaviour largely influenced by architectural choices and training settings. This paper explores Ensembles of Multiple Models and Architectures (EMMA) for robust performance through aggregation of predictions from a wide range of methods. The approach reduces the influence of the meta-parameters of individual models and the risk of overfitting the configuration to a particular database. EMMA can be seen as an unbiased, generic deep learning model which is shown to yield excellent performance, winning the first position in the BRATS 2017 competition among 50+ participating teams.

* The method won the 1st-place in the Brain Tumour Segmentation (BRATS) 2017 competition (segmentation task) 

  Click for Model/Code and Paper
Weakly Supervised Estimation of Shadow Confidence Maps in Ultrasound Imaging

Nov 21, 2018
Qingjie Meng, Matthew Sinclair, Veronika Zimmer, Benjamin Hou, Martin Rajchl, Nicolas Toussaint, Alberto Gomez, James Housden, Jacqueline Matthew, Daniel Rueckert, Julia Schnabel, Bernhard Kainz

Detecting acoustic shadows in ultrasound images is important in many clinical and engineering applications. Real-time feedback of acoustic shadows can guide sonographers to a standardized diagnostic viewing plane with minimal artifacts and can provide additional information for other automatic image analysis algorithms. However, automatically detecting shadow regions is challenging because pixel-wise annotation of acoustic shadows is subjective and time consuming. In this paper we propose a weakly supervised method for automatic confidence estimation of acoustic shadow regions, which is able to generate a dense shadow-focused confidence map. During training, a multi-task module for shadow segmentation is built to learn general shadow features according based image-level annotations as well as a small number of coarse pixel-wise shadow annotations. A transfer function is then established to extend the binary shadow segmentation to a reference confidence map. In addition, a confidence estimation network is proposed to learn the mapping between input images and the reference confidence maps. This confidence estimation network is able to predict shadow confidence maps directly from input images during inference. We evaluate DICE, soft DICE, recall, precision, mean squared error and inter-class correlation to verify the effectiveness of our method. Our method outperforms the state-of-the-art qualitatively and quantitatively. We further demonstrate the applicability of our method by integrating shadow confidence maps into tasks such as ultrasound image classification, multi-view image fusion and automated biometric measurements.


  Click for Model/Code and Paper
Learning under Distributed Weak Supervision

Jun 03, 2016
Martin Rajchl, Matthew C. H. Lee, Franklin Schrans, Alice Davidson, Jonathan Passerat-Palmbach, Giacomo Tarroni, Amir Alansary, Ozan Oktay, Bernhard Kainz, Daniel Rueckert

The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods. While typically established by a clinical expert rater, the increase in acquired imaging data renders traditional pixel-wise segmentations less feasible. In this paper, we examine the use of a crowdsourcing platform for the distribution of super-pixel weak annotation tasks and collect such annotations from a crowd of non-expert raters. The crowd annotations are subsequently used for training a fully convolutional neural network to address the problem of fetal brain segmentation in T2-weighted MR images. Using this approach we report encouraging results compared to highly targeted, fully supervised methods and potentially address a frequent problem impeding image analysis research.


  Click for Model/Code and Paper
Learning Interpretable Anatomical Features Through Deep Generative Models: Application to Cardiac Remodeling

Jul 18, 2018
Carlo Biffi, Ozan Oktay, Giacomo Tarroni, Wenjia Bai, Antonio De Marvao, Georgia Doumou, Martin Rajchl, Reem Bedair, Sanjay Prasad, Stuart Cook, Declan O'Regan, Daniel Rueckert

Alterations in the geometry and function of the heart define well-established causes of cardiovascular disease. However, current approaches to the diagnosis of cardiovascular diseases often rely on subjective human assessment as well as manual analysis of medical images. Both factors limit the sensitivity in quantifying complex structural and functional phenotypes. Deep learning approaches have recently achieved success for tasks such as classification or segmentation of medical images, but lack interpretability in the feature extraction and decision processes, limiting their value in clinical diagnosis. In this work, we propose a 3D convolutional generative model for automatic classification of images from patients with cardiac diseases associated with structural remodeling. The model leverages interpretable task-specific anatomic patterns learned from 3D segmentations. It further allows to visualise and quantify the learned pathology-specific remodeling patterns in the original input space of the images. This approach yields high accuracy in the categorization of healthy and hypertrophic cardiomyopathy subjects when tested on unseen MR images from our own multi-centre dataset (100%) as well on the ACDC MICCAI 2017 dataset (90%). We believe that the proposed deep learning approach is a promising step towards the development of interpretable classifiers for the medical imaging domain, which may help clinicians to improve diagnostic accuracy and enhance patient risk-stratification.

* Accepted at MICCAI 2018 

  Click for Model/Code and Paper
PVR: Patch-to-Volume Reconstruction for Large Area Motion Correction of Fetal MRI

Nov 25, 2016
Amir Alansary, Bernhard Kainz, Martin Rajchl, Maria Murgasova, Mellisa Damodaram, David F. A. Lloyd, Alice Davidson, Steven G. McDonagh, Mary Rutherford, Joseph V. Hajnal, Daniel Rueckert

In this paper we present a novel method for the correction of motion artifacts that are present in fetal Magnetic Resonance Imaging (MRI) scans of the whole uterus. Contrary to current slice-to-volume registration (SVR) methods, requiring an inflexible anatomical enclosure of a single investigated organ, the proposed patch-to-volume reconstruction (PVR) approach is able to reconstruct a large field of view of non-rigidly deforming structures. It relaxes rigid motion assumptions by introducing a specific amount of redundant information that is exploited with parallelized patch-wise optimization, super-resolution, and automatic outlier rejection. We further describe and provide an efficient parallel implementation of PVR allowing its execution within reasonable time on commercially available graphics processing units (GPU), enabling its use in the clinical practice. We evaluate PVR's computational overhead compared to standard methods and observe improved reconstruction accuracy in presence of affine motion artifacts of approximately 30% compared to conventional SVR in synthetic experiments. Furthermore, we have evaluated our method qualitatively and quantitatively on real fetal MRI data subject to maternal breathing and sudden fetal movements. We evaluate peak-signal-to-noise ratio (PSNR), structural similarity index (SSIM), and cross correlation (CC) with respect to the originally acquired data and provide a method for visual inspection of reconstruction uncertainty. With these experiments we demonstrate successful application of PVR motion compensation to the whole uterus, the human fetus, and the human placenta.

* 10 pages, 13 figures, submitted to IEEE Transactions on Medical Imaging. v2: wadded funders acknowledgements to preprint 

  Click for Model/Code and Paper
DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks

Jun 05, 2016
Martin Rajchl, Matthew C. H. Lee, Ozan Oktay, Konstantinos Kamnitsas, Jonathan Passerat-Palmbach, Wenjia Bai, Mellisa Damodaram, Mary A. Rutherford, Joseph V. Hajnal, Bernhard Kainz, Daniel Rueckert

In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naive approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.


  Click for Model/Code and Paper
Automated cardiovascular magnetic resonance image analysis with fully convolutional networks

May 22, 2018
Wenjia Bai, Matthew Sinclair, Giacomo Tarroni, Ozan Oktay, Martin Rajchl, Ghislain Vaillant, Aaron M. Lee, Nay Aung, Elena Lukaschuk, Mihir M. Sanghvi, Filip Zemrak, Kenneth Fung, Jose Miguel Paiva, Valentina Carapella, Young Jin Kim, Hideaki Suzuki, Bernhard Kainz, Paul M. Matthews, Steffen E. Petersen, Stefan K. Piechnik, Stefan Neubauer, Ben Glocker, Daniel Rueckert

Cardiovascular magnetic resonance (CMR) imaging is a standard imaging modality for assessing cardiovascular diseases (CVDs), the leading cause of death globally. CMR enables accurate quantification of the cardiac chamber volume, ejection fraction and myocardial mass, providing information for diagnosis and monitoring of CVDs. However, for years, clinicians have been relying on manual approaches for CMR image analysis, which is time consuming and prone to subjective errors. It is a major clinical challenge to automatically derive quantitative and clinically relevant information from CMR images. Deep neural networks have shown a great potential in image pattern recognition and segmentation for a variety of tasks. Here we demonstrate an automated analysis method for CMR images, which is based on a fully convolutional network (FCN). The network is trained and evaluated on a large-scale dataset from the UK Biobank, consisting of 4,875 subjects with 93,500 pixelwise annotated images. The performance of the method has been evaluated using a number of technical metrics, including the Dice metric, mean contour distance and Hausdorff distance, as well as clinically relevant measures, including left ventricle (LV) end-diastolic volume (LVEDV) and end-systolic volume (LVESV), LV mass (LVM); right ventricle (RV) end-diastolic volume (RVEDV) and end-systolic volume (RVESV). By combining FCN with a large-scale annotated dataset, the proposed automated method achieves a high performance on par with human experts in segmenting the LV and RV on short-axis CMR images and the left atrium (LA) and right atrium (RA) on long-axis CMR images.

* Accepted for publication by Journal of Cardiovascular Magnetic Resonance 

  Click for Model/Code and Paper