Search Results for author: Daniel Rueckert

Found 270 papers, 118 papers with code

Multi-Image Visual Question Answering for Unsupervised Anomaly Detection

no code implementations11 Apr 2024 Jun Li, Cosmin I. Bercea, Philip Müller, Lina Felsner, Suhwan Kim, Daniel Rueckert, Benedikt Wiestler, Julia A. Schnabel

To the best of our knowledge, we are the first to leverage a language model for unsupervised anomaly detection, for which we construct a dataset with different questions and answers.

Language Modelling Question Answering +2

Intensity-based 3D motion correction for cardiac MR images

1 code implementation31 Mar 2024 Nil Stolt-Ansó, Vasiliki Sideri-Lampretsa, Maik Dannecker, Daniel Rueckert

Cardiac magnetic resonance (CMR) image acquisition requires subjects to hold their breath while 2D cine images are acquired.

Anatomy Position

Topologically faithful multi-class segmentation in medical images

no code implementations16 Mar 2024 Alexander H. Berger, Nico Stucki, Laurin Lux, Vincent Buergin, Suprosanna Shit, Anna Banaszak, Daniel Rueckert, Ulrich Bauer, Johannes C. Paetzold

Topological accuracy in medical image segmentation is a highly important property for downstream applications such as network analysis and flow modeling in vessels or cell counting.

Image Segmentation Medical Image Segmentation +2

Diffusion Models with Implicit Guidance for Medical Anomaly Detection

1 code implementation13 Mar 2024 Cosmin I. Bercea, Benedikt Wiestler, Daniel Rueckert, Julia A. Schnabel

Diffusion models have advanced unsupervised anomaly detection by improving the transformation of pathological images into pseudo-healthy equivalents.

Specificity Unsupervised Anomaly Detection

CINA: Conditional Implicit Neural Atlas for Spatio-Temporal Representation of Fetal Brains

no code implementations13 Mar 2024 Maik Dannecker, Vanessa Kyriakopoulou, Lucilio Cordero-Grande, Anthony N. Price, Joseph V. Hajnal, Daniel Rueckert

We demonstrate CINA's capability to represent a fetal brain atlas that can be flexibly conditioned on GA and on anatomical variations like ventricular volume or degree of cortical folding, making it a suitable tool for modeling both neurotypical and pathological brains.

Spatiotemporal Representation Learning for Short and Long Medical Image Time Series

no code implementations12 Mar 2024 Chengzhi Shen, Martin J. Menten, Hrvoje Bogunović, Ursula Schmidt-Erfurth, Hendrik Scholl, Sobha Sivaprasad, Andrew Lotery, Daniel Rueckert, Paul Hager, Robbie Holland

Moreover, tracking longer term developments that occur over months or years in evolving processes, such as age-related macular degeneration (AMD), is essential for accurate prognosis.

Contrastive Learning Decision Making +3

Visual Privacy Auditing with Diffusion Models

no code implementations12 Mar 2024 Kristian Schwethelm, Johannes Kaiser, Moritz Knolle, Daniel Rueckert, Georgios Kaissis, Alexander Ziller

We propose a reconstruction attack based on diffusion models (DMs) that assumes adversary access to real-world image priors and assess its implications on privacy leakage under DP-SGD.

Image Reconstruction Reconstruction Attack

A Learnable Prior Improves Inverse Tumor Growth Modeling

no code implementations7 Mar 2024 Jonas Weidner, Ivan Ezhov, Michal Balcerak, Marie-Christin Metz, Sergey Litvinov, Sebastian Kaltenbach, Leonhard Feiner, Laurin Lux, Florian Kofler, Jana Lipkova, Jonas Latz, Daniel Rueckert, Bjoern Menze, Benedikt Wiestler

Biophysical modeling, particularly involving partial differential equations (PDEs), offers significant potential for tailoring disease treatment protocols to individual patients.

Motion-Corrected Moving Average: Including Post-Hoc Temporal Information for Improved Video Segmentation

no code implementations5 Mar 2024 Robert Mendel, Tobias Rueckert, Dirk Wilhelm, Daniel Rueckert, Christoph Palm

Using optical flow to estimate the movement between consecutive frames, we can shift the prior term in the moving-average calculation to align with the geometry of the current frame.

Optical Flow Estimation Segmentation +2

Bounding Reconstruction Attack Success of Adversaries Without Data Priors

no code implementations20 Feb 2024 Alexander Ziller, Anneliese Riess, Kristian Schwethelm, Tamara T. Mueller, Daniel Rueckert, Georgios Kaissis

When training ML models with differential privacy (DP), formal upper bounds on the success of such reconstruction attacks can be provided.

Reconstruction Attack

Weakly Supervised Object Detection in Chest X-Rays with Differentiable ROI Proposal Networks and Soft ROI Pooling

1 code implementation19 Feb 2024 Philip Müller, Felix Meissen, Georgios Kaissis, Daniel Rueckert

Weakly supervised object detection (WSup-OD) increases the usefulness and interpretability of image classification algorithms without requiring additional supervision.

Image Classification Multiple Instance Learning +2

Data and Physics driven Deep Learning Models for Fast MRI Reconstruction: Fundamentals and Methodologies

no code implementations29 Jan 2024 Jiahao Huang, Yinzhe Wu, Fanwen Wang, Yingying Fang, Yang Nan, Cagan Alkan, Lei Xu, Zhifan Gao, Weiwen Wu, Lei Zhu, Zhaolin Chen, Peter Lally, Neal Bangerter, Kawin Setsompop, Yike Guo, Daniel Rueckert, Ge Wang, Guang Yang

Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans.

Federated Learning MRI Reconstruction

Towards Universal Unsupervised Anomaly Detection in Medical Imaging

1 code implementation19 Jan 2024 Cosmin I. Bercea, Benedikt Wiestler, Daniel Rueckert, Julia A. Schnabel

Our unsupervised anomaly detection approach may enhance diagnostic accuracy in medical imaging by identifying a broader range of unknown pathologies.

Unsupervised Anomaly Detection

On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions

1 code implementation1 Jan 2024 Razieh Rezaei, Alireza Dizaji, Ashkan Khakzar, Anees Kazi, Nassir Navab, Daniel Rueckert

In this work, we assess attribution methods from a perspective not previously explored in the graph domain: retraining.

Graph Classification

TopCoW: Benchmarking Topology-Aware Anatomical Segmentation of the Circle of Willis (CoW) for CTA and MRA

1 code implementation29 Dec 2023 Kaiyuan Yang, Fabio Musio, Yihui Ma, Norman Juchler, Johannes C. Paetzold, Rami Al-Maskari, Luciano Höher, Hongwei Bran Li, Ibrahim Ethem Hamamci, Anjany Sekuboyina, Suprosanna Shit, Houjing Huang, Diana Waldmannstetter, Florian Kofler, Fernando Navarro, Martin Menten, Ivan Ezhov, Daniel Rueckert, Iris Vos, Ynte Ruigrok, Birgitta Velthuis, Hugo Kuijf, Julien Hämmerli, Catherine Wurster, Philippe Bijlenga, Laura Westphal, Jeroen Bisschop, Elisa Colombo, Hakim Baazaoui, Andrew Makmur, James Hallinan, Bene Wiestler, Jan S. Kirschke, Roland Wiest, Emmanuel Montagnon, Laurent Letourneau-Guillon, Adrian Galdran, Francesco Galati, Daniele Falcetta, Maria A. Zuluaga, Chaolong Lin, Haoran Zhao, Zehan Zhang, Sinyoung Ra, Jongyun Hwang, HyunJin Park, Junqiang Chen, Marek Wodzinski, Henning Müller, Pengcheng Shi, Wei Liu, Ting Ma, Cansu Yalçin, Rachika E. Hamadache, Joaquim Salvi, Xavier Llado, Uma Maria Lal-Trehan Estrada, Valeriia Abramova, Luca Giancardo, Arnau Oliver, Jialu Liu, Haibin Huang, Yue Cui, Zehang Lin, Yusheng Liu, Shunzhi Zhu, Tatsat R. Patel, Vincent M. Tutino, Maysam Orouskhani, Huayu Wang, Mahmud Mossa-Basha, Chengcheng Zhu, Maximilian R. Rokuss, Yannick Kirchhoff, Nico Disch, Julius Holzschuh, Fabian Isensee, Klaus Maier-Hein, Yuki Sato, Sven Hirsch, Susanne Wegener, Bjoern Menze

The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology.

Anatomy Benchmarking +1

How Low Can You Go? Surfacing Prototypical In-Distribution Samples for Unsupervised Anomaly Detection

no code implementations6 Dec 2023 Felix Meissen, Johannes Getzner, Alexander Ziller, Georgios Kaissis, Daniel Rueckert

Additionally, we show that the prototypical in-distribution samples identified by our proposed methods translate well to different models and other datasets and that using their characteristics as guidance allows for successful manual selection of small subsets of high-performing samples.

Pneumonia Detection Unsupervised Anomaly Detection

Reconciling AI Performance and Data Reconstruction Resilience for Medical Imaging

no code implementations5 Dec 2023 Alexander Ziller, Tamara T. Mueller, Simon Stieger, Leonhard Feiner, Johannes Brandt, Rickmer Braren, Daniel Rueckert, Georgios Kaissis

Although a lower budget decreases the risk of information leakage, it typically also reduces the performance of such models.

T1/T2 relaxation temporal modelling from accelerated acquisitions using a Latent Transformer

no code implementations28 Sep 2023 Fanwen Wang, Michael Tanzer, Mengyun Qiao, Wenjia Bai, Daniel Rueckert, Guang Yang, Sonia Nielles-Vallespin

Quantitative cardiac magnetic resonance T1 and T2 mapping enable myocardial tissue characterisation but the lengthy scan times restrict their widespread clinical application.

Propagation and Attribution of Uncertainty in Medical Imaging Pipelines

1 code implementation28 Sep 2023 Leonhard F. Feiner, Martin J. Menten, Kerstin Hammernik, Paul Hager, Wenqi Huang, Daniel Rueckert, Rickmer F. Braren, Georgios Kaissis

In this paper, we propose a method to propagate uncertainty through cascades of deep learning models in medical imaging pipelines.

A Comparative Study of Population-Graph Construction Methods and Graph Neural Networks for Brain Age Regression

1 code implementation26 Sep 2023 Kyriaki-Margarita Bintsi, Tamara T. Mueller, Sophie Starck, Vasileios Baltatzis, Alexander Hammers, Daniel Rueckert

We conclude that static graph construction approaches are potentially insufficient for the task of brain age estimation and make recommendations for alternative research directions.

Age Estimation Graph Attention +1

3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images

1 code implementation15 Sep 2023 Alina F. Dima, Veronika A. Zimmer, Martin J. Menten, Hongwei Bran Li, Markus Graf, Tristan Lemke, Philipp Raffler, Robert Graf, Jan S. Kirschke, Rickmer Braren, Daniel Rueckert

In this work, we propose a novel method to segment the 3D peripancreatic arteries solely from one annotated 2D projection per training image with depth supervision.


NISF: Neural Implicit Segmentation Functions

1 code implementation15 Sep 2023 Nil Stolt-Ansó, Julian McGinnis, Jiazhen Pan, Kerstin Hammernik, Daniel Rueckert

Approaches that rely on convolutional neural networks (CNNs) are limited to grid-like inputs and not easily applicable to sparse or partial measurements.

Cardiac Segmentation Image Segmentation +2

MAD: Modality Agnostic Distance Measure for Image Registration

no code implementations6 Sep 2023 Vasiliki Sideri-Lampretsa, Veronika A. Zimmer, Huaqi Qiu, Georgios Kaissis, Daniel Rueckert

The success of multi-modal image registration, whether it is conventional or learning based, is predicated upon the choice of an appropriate distance (or similarity) measure.

Image Registration

A skeletonization algorithm for gradient-based optimization

1 code implementation ICCV 2023 Martin J. Menten, Johannes C. Paetzold, Veronika A. Zimmer, Suprosanna Shit, Ivan Ezhov, Robbie Holland, Monika Probst, Julia A. Schnabel, Daniel Rueckert

Finally, we demonstrate the utility of our algorithm by integrating it with two medical image processing applications that use gradient-based optimization: deep-learning-based blood vessel segmentation, and multimodal registration of the mandible in computed tomography and magnetic resonance images.


Anatomy-Driven Pathology Detection on Chest X-rays

1 code implementation5 Sep 2023 Philip Müller, Felix Meissen, Johannes Brandt, Georgios Kaissis, Daniel Rueckert

Pathology detection and delineation enables the automatic interpretation of medical scans such as chest X-rays while providing a high level of explainability to support radiologists in making informed decisions.

Anatomy Multiple Instance Learning +2

Constructing Population-Specific Atlases from Whole Body MRI: Application to the UKBB

no code implementations28 Aug 2023 Sophie Starck, Vasiliki Sideri-Lampretsa, Jessica J. M. Ritter, Veronika A. Zimmer, Rickmer Braren, Tamara T. Mueller, Daniel Rueckert

We demonstrate different applications of these atlases, using the differences between subjects with medical conditions such as diabetes and cardiovascular diseases and healthy subjects from the atlas space.

Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD

no code implementations23 Aug 2023 Moritz Knolle, Robert Dorfman, Alexander Ziller, Daniel Rueckert, Georgios Kaissis

Differentially private SGD (DP-SGD) holds the promise of enabling the safe and responsible application of machine learning to sensitive datasets.

The Challenge of Fetal Cardiac MRI Reconstruction Using Deep Learning

no code implementations15 Aug 2023 Denis Prokopenko, Kerstin Hammernik, Thomas Roberts, David F A Lloyd, Daniel Rueckert, Joseph V Hajnal

We show that the best-performers recover a detailed depiction of the maternal anatomy on a large scale, but the dynamic properties of the fetal heart are under-represented.

Anatomy MRI Reconstruction

FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

no code implementations11 Aug 2023 Karim Lekadir, Aasa Feragen, Abdul Joseph Fofanah, Alejandro F Frangi, Alena Buyx, Anais Emelie, Andrea Lara, Antonio R Porras, An-Wen Chan, Arcadi Navarro, Ben Glocker, Benard O Botwe, Bishesh Khanal, Brigit Beger, Carol C Wu, Celia Cintas, Curtis P Langlotz, Daniel Rueckert, Deogratias Mzurikwao, Dimitrios I Fotiadis, Doszhan Zhussupov, Enzo Ferrante, Erik Meijering, Eva Weicken, Fabio A González, Folkert W Asselbergs, Fred Prior, Gabriel P Krestin, Gary Collins, Geletaw S Tegenaw, Georgios Kaissis, Gianluca Misuraca, Gianna Tsakou, Girish Dwivedi, Haridimos Kondylakis, Harsha Jayakody, Henry C Woodruf, Hugo JWL Aerts, Ian Walsh, Ioanna Chouvarda, Irène Buvat, Islem Rekik, James Duncan, Jayashree Kalpathy-Cramer, Jihad Zahir, Jinah Park, John Mongan, Judy W Gichoya, Julia A Schnabel, Kaisar Kushibar, Katrine Riklund, Kensaku MORI, Kostas Marias, Lameck M Amugongo, Lauren A Fromont, Lena Maier-Hein, Leonor Cerdá Alberich, Leticia Rittner, Lighton Phiri, Linda Marrakchi-Kacem, Lluís Donoso-Bach, Luis Martí-Bonmatí, M Jorge Cardoso, Maciej Bobowicz, Mahsa Shabani, Manolis Tsiknakis, Maria A Zuluaga, Maria Bielikova, Marie-Christine Fritzsche, Marius George Linguraru, Markus Wenzel, Marleen de Bruijne, Martin G Tolsgaard, Marzyeh Ghassemi, Md Ashrafuzzaman, Melanie Goisauf, Mohammad Yaqub, Mohammed Ammar, Mónica Cano Abadía, Mukhtar M E Mahmoud, Mustafa Elattar, Nicola Rieke, Nikolaos Papanikolaou, Noussair Lazrak, Oliver Díaz, Olivier Salvado, Oriol Pujol, Ousmane Sall, Pamela Guevara, Peter Gordebeke, Philippe Lambin, Pieta Brown, Purang Abolmaesumi, Qi Dou, Qinghua Lu, Richard Osuala, Rose Nakasi, S Kevin Zhou, Sandy Napel, Sara Colantonio, Shadi Albarqouni, Smriti Joshi, Stacy Carter, Stefan Klein, Steffen E Petersen, Susanna Aussó, Suyash Awate, Tammy Riklin Raviv, Tessa Cook, Tinashe E M Mutsvangwa, Wendy A Rogers, Wiro J Niessen, Xènia Puig-Bosch, Yi Zeng, Yunusa G Mohammed, Yves Saint James Aquino, Zohaib Salahuddin, Martijn P A Starmans

This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare.


Surface Masked AutoEncoder: Self-Supervision for Cortical Imaging Data

1 code implementation10 Aug 2023 Simon Dahan, Mariana da Silva, Daniel Rueckert, Emma C Robinson

By reconstructing surface data from a masked version of the input, the proposed method effectively models cortical structure to learn strong representations that translate to improved performance in downstream tasks.

Metrics to Quantify Global Consistency in Synthetic Medical Images

no code implementations1 Aug 2023 Daniel Scholz, Benedikt Wiestler, Daniel Rueckert, Martin J. Menten

In this work, we introduce two metrics that can measure the global consistency of synthetic images on a per-image basis.

Data Augmentation Image Generation

Conditional Temporal Attention Networks for Neonatal Cortical Surface Reconstruction

1 code implementation21 Jul 2023 Qiang Ma, Liu Li, Vanessa Kyriakopoulou, Joseph Hajnal, Emma C. Robinson, Bernhard Kainz, Daniel Rueckert

The importance of each SVF, which is estimated by learned attention maps, is conditioned on the age of the neonates and varies with the time step of integration.

Surface Reconstruction

Atlas-Based Interpretable Age Prediction In Whole-Body MR Images

no code implementations14 Jul 2023 Sophie Starck, Yadunandan Vivekanand Kini, Jessica Johanna Maria Ritter, Rickmer Braren, Daniel Rueckert, Tamara Mueller

We utilise the Grad-CAM interpretability method to determine the body areas most predictive of a person's age.

Extended Graph Assessment Metrics for Graph Neural Networks

no code implementations13 Jul 2023 Tamara T. Mueller, Sophie Starck, Leonhard F. Feiner, Kyriaki-Margarita Bintsi, Daniel Rueckert, Georgios Kaissis

In this work, we introduce extended graph assessment metrics (GAMs) for regression tasks and continuous adjacency matrices.


Interpretable 2D Vision Models for 3D Medical Images

1 code implementation13 Jul 2023 Alexander Ziller, Ayhan Can Erdur, Marwa Trigui, Alp Güvenir, Tamara T. Mueller, Philip Müller, Friederike Jungmann, Johannes Brandt, Jan Peeken, Rickmer Braren, Daniel Rueckert, Georgios Kaissis

Training Artificial Intelligence (AI) models on 3D images presents unique challenges compared to the 2D case: Firstly, the demand for computational resources is significantly higher, and secondly, the availability of large datasets for pre-training is often limited, impeding training success.

Body Fat Estimation from Surface Meshes using Graph Neural Networks

no code implementations13 Jul 2023 Tamara T. Mueller, Siyu Zhou, Sophie Starck, Friederike Jungmann, Alexander Ziller, Orhun Aksoy, Danylo Movchan, Rickmer Braren, Georgios Kaissis, Daniel Rueckert

Body fat volume and distribution can be a strong indication for a person's overall health and the risk for developing diseases like type 2 diabetes and cardiovascular diseases.

Multimodal brain age estimation using interpretable adaptive population-graph learning

1 code implementation10 Jul 2023 Kyriaki-Margarita Bintsi, Vasileios Baltatzis, Rolandos Alexandros Potamias, Alexander Hammers, Daniel Rueckert

We further show that the assigned attention scores indicate that there are both imaging and non-imaging phenotypes that are informative for brain age estimation and are in agreement with the relevant literature.

Age Estimation graph construction +1

Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy

no code implementations8 Jul 2023 Georgios Kaissis, Jamie Hayes, Alexander Ziller, Daniel Rueckert

We explore Reconstruction Robustness (ReRo), which was recently proposed as an upper bound on the success of data reconstruction attacks against machine learning models.

Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentation

no code implementations2 Jul 2023 Jingjie Guo, Weitong Zhang, Matthew Sinclair, Daniel Rueckert, Chen Chen

In addition, different from most existing TTA methods which restrict the adaptation to batch normalization blocks in the segmentation network only, we further exploit the use of channel and spatial attention blocks for improved adaptability at test time.

Image Segmentation Medical Image Segmentation +4

Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review

no code implementations11 May 2023 Veronika Spieker, Hannah Eichhorn, Kerstin Hammernik, Daniel Rueckert, Christine Preibisch, Dimitrios C. Karampinos, Julia A. Schnabel

To facilitate the transfer of ideas between different applications, this review provides a detailed overview of proposed methods for learning-based motion correction in MRI together with their common challenges and potentials.

Leveraging gradient-derived metrics for data selection and valuation in differentially private training

no code implementations4 May 2023 Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis

Obtaining high-quality data for collaborative training of machine learning models can be a challenging task due to A) the regulatory concerns and B) lack of incentive to participate.

Methods and datasets for segmentation of minimally invasive surgical instruments in endoscopic images and videos: A review of the state of the art

no code implementations25 Apr 2023 Tobias Rueckert, Daniel Rueckert, Christoph Palm

In the field of computer- and robot-assisted minimally invasive surgery, enormous progress has been made in recent years based on the recognition of surgical instruments in endoscopic images and videos.

Instance Segmentation Segmentation +1

Interactive and Explainable Region-guided Radiology Report Generation

1 code implementation CVPR 2023 Tim Tanida, Philip Müller, Georgios Kaissis, Daniel Rueckert

While previous methods generate reports without the possibility of human intervention and with limited explainability, our method opens up novel clinical use cases through additional interactive capabilities and introduces a high degree of transparency and explainability.

Medical Report Generation

Single-subject Multi-contrast MRI Super-resolution via Implicit Neural Representations

1 code implementation27 Mar 2023 Julian McGinnis, Suprosanna Shit, Hongwei Bran Li, Vasiliki Sideri-Lampretsa, Robert Graf, Maik Dannecker, Jiazhen Pan, Nil Stolt Ansó, Mark Mühlau, Jan S. Kirschke, Daniel Rueckert, Benedikt Wiestler

Clinical routine and retrospective cohorts commonly include multi-parametric Magnetic Resonance Imaging; however, they are mostly acquired in different anisotropic 2D views due to signal-to-noise-ratio and scan-time constraints.


Link Prediction for Flow-Driven Spatial Networks

1 code implementation25 Mar 2023 Bastian Wittmann, Johannes C. Paetzold, Chinmay Prabhakar, Daniel Rueckert, Bjoern Menze

In this work, we focus on link prediction for flow-driven spatial networks, which are embedded in a Euclidean space and relate to physical exchange and transportation processes (e. g., blood flow in vessels or traffic flow in road networks).

Link Prediction

Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data

1 code implementation CVPR 2023 Paul Hager, Martin J. Menten, Daniel Rueckert

Medical datasets and especially biobanks, often contain extensive tabular data with rich clinical information in addition to images.

Contrastive Learning

The Multiscale Surface Vision Transformer

1 code implementation21 Mar 2023 Simon Dahan, Abdulah Fawaz, Mohamed A. Suliman, Mariana da Silva, Logan Z. J. Williams, Daniel Rueckert, Emma C. Robinson

Surface meshes are a favoured domain for representing structural and functional information on the human cortex, but their complex topology and geometry pose significant challenges for deep learning analysis.

Physics-Aware Motion Simulation for T2*-Weighted Brain MRI

1 code implementation20 Mar 2023 Hannah Eichhorn, Kerstin Hammernik, Veronika Spieker, Samira M. Epp, Daniel Rueckert, Christine Preibisch, Julia A. Schnabel

As T2*-weighted MRI is highly sensitive to motion-related changes in magnetic field inhomogeneities, it is of utmost importance to include physics information in the simulation.

Line Detection

Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection

no code implementations15 Mar 2023 Cosmin I Bercea, Benedikt Wiestler, Daniel Rueckert, Julia A Schnabel

To overcome these limitations, we introduce a novel unsupervised approach, called PHANES (Pseudo Healthy generative networks for ANomaly Segmentation).

Anomaly Detection Management +1

Robust Detection Outcome: A Metric for Pathology Detection in Medical Images

1 code implementation3 Mar 2023 Felix Meissen, Philip Müller, Georgios Kaissis, Daniel Rueckert

To tackle this problem, we propose Robust Detection Outcome (RoDeO); a novel metric for evaluating algorithms for pathology detection in medical images, especially in chest X-rays.

object-detection Object Detection

Unsupervised Pathology Detection: A Deep Dive Into the State of the Art

1 code implementation1 Mar 2023 Ioannis Lagogiannis, Felix Meissen, Georgios Kaissis, Daniel Rueckert

Our experiments demonstrate that newly developed feature-modeling methods from the industrial and medical literature achieve increased performance compared to previous work and set the new SOTA in a variety of modalities and datasets.

Unsupervised Anomaly Detection

Reconstruction-driven motion estimation for motion-compensated MR CINE imaging

no code implementations5 Feb 2023 Jiazhen Pan, Wenqi Huang, Daniel Rueckert, Thomas Küstner, Kerstin Hammernik

Contrary to state-of-the-art (SOTA) MCMR methods which break the original problem into two sub-optimization problems, i. e. motion estimation and reconstruction, we formulate this problem as a single entity with one single optimization.

Motion Estimation

CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy

1 code implementation30 Jan 2023 Mengyun Qiao, Shuo Wang, Huaqi Qiu, Antonio de Marvao, Declan P. O'Regan, Daniel Rueckert, Wenjia Bai

Two key questions in cardiac image analysis are to assess the anatomy and motion of the heart from images; and to understand how they are associated with non-imaging clinical factors such as gender, age and diseases.

Anatomy Image Segmentation +1

Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models

1 code implementation30 Jan 2023 Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis

We achieve such sparsity by design by introducing equivariant convolutional networks for model training with Differential Privacy.

Image Classification with Differential Privacy

Identifying chromophore fingerprints of brain tumor tissue on hyperspectral imaging using principal component analysis

no code implementations12 Jan 2023 Ivan Ezhov, Luca Giannoni, Suprosanna Shit, Frederic Lange, Florian Kofler, Bjoern Menze, Ilias Tachtsidis, Daniel Rueckert

In this article, we perform a statistical analysis of the brain tumor patients' HSI scans from the HELICoiD dataset with the aim of identifying the correlation between reflectance spectra and absorption spectra of tissue chromophores.

Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imaging

no code implementations16 Dec 2022 Wenqi Huang, Hongwei Li, Jiazhen Pan, Gastao Cruz, Daniel Rueckert, Kerstin Hammernik

While existing methods bin acquired data from neighboring time points to reconstruct one phase of the cardiac motion, our framework allows for a continuous, binning-free, and subject-specific k-space representation. We assign a unique coordinate that consists of time, coil index, and frequency domain location to each sampled k-space point.

Image Reconstruction

A Domain-specific Perceptual Metric via Contrastive Self-supervised Representation: Applications on Natural and Medical Images

no code implementations3 Dec 2022 Hongwei Bran Li, Chinmay Prabhakar, Suprosanna Shit, Johannes Paetzold, Tamaz Amiranashvili, JianGuo Zhang, Daniel Rueckert, Juan Eugenio Iglesias, Benedikt Wiestler, Bjoern Menze

We find that in the natural image domain, CSR behaves on par with the supervised one on several perceptual tests as a metric, and in the medical domain, CSR better quantifies perceptual similarity concerning the experts' ratings.

Image Generation

How Do Input Attributes Impact the Privacy Loss in Differential Privacy?

no code implementations18 Nov 2022 Tamara T. Mueller, Stefan Kolek, Friederike Jungmann, Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Daniel Rueckert, Georgios Kaissis

Differential privacy (DP) is typically formulated as a worst-case privacy guarantee over all individuals in a database.

Exploiting segmentation labels and representation learning to forecast therapy response of PDAC patients

no code implementations8 Nov 2022 Alexander Ziller, Ayhan Can Erdur, Friederike Jungmann, Daniel Rueckert, Rickmer Braren, Georgios Kaissis

The prediction of pancreatic ductal adenocarcinoma therapy response is a clinically challenging and important task in this high-mortality tumour entity.

Representation Learning

Automated analysis of diabetic retinopathy using vessel segmentation maps as inductive bias

no code implementations28 Oct 2022 Linus Kreitner, Ivan Ezhov, Daniel Rueckert, Johannes C. Paetzold, Martin J. Menten

Recent studies suggest that early stages of diabetic retinopathy (DR) can be diagnosed by monitoring vascular changes in the deep vascular complex.

Image Quality Assessment Inductive Bias +2

Generalised Likelihood Ratio Testing Adversaries through the Differential Privacy Lens

no code implementations24 Oct 2022 Georgios Kaissis, Alexander Ziller, Stefan Kolek Martinez de Azagra, Daniel Rueckert

Differential Privacy (DP) provides tight upper bounds on the capabilities of optimal adversaries, but such adversaries are rarely encountered in practice.

Label Noise-Robust Learning using a Confidence-Based Sieving Strategy

no code implementations11 Oct 2022 Reihaneh Torkzadehmahani, Reza Nasirigerdeh, Daniel Rueckert, Georgios Kaissis

Identifying the samples with noisy labels and preventing the model from learning them is a promising approach to address this challenge.

Artificial Intelligence-Based Image Reconstruction in Cardiac Magnetic Resonance

no code implementations21 Sep 2022 Chen Qin, Daniel Rueckert

Artificial intelligence (AI) and Machine Learning (ML) have shown great potential in improving the medical imaging workflow, from image acquisition and reconstruction to disease diagnosis and treatment.

Computational Efficiency Image Reconstruction

Review of data types and model dimensionality for cardiac DTI SMS-related artefact removal

1 code implementation20 Sep 2022 Michael Tanzer, Sea Hee Yook, Guang Yang, Daniel Rueckert, Sonia Nielles-Vallespin

As diffusion tensor imaging (DTI) gains popularity in cardiac imaging due to its unique ability to non-invasively assess the cardiac microstructure, deep learning-based Artificial Intelligence is becoming a crucial tool in mitigating some of its drawbacks, such as the long scan times.

Bridging the Gap: Differentially Private Equivariant Deep Learning for Medical Image Analysis

no code implementations9 Sep 2022 Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis

Machine learning with formal privacy-preserving techniques like Differential Privacy (DP) allows one to derive valuable insights from sensitive medical imaging data while promising to protect patient privacy, but it usually comes at a sharp privacy-utility trade-off.

Privacy Preserving

Learning-based and unrolled motion-compensated reconstruction for cardiac MR CINE imaging

no code implementations8 Sep 2022 Jiazhen Pan, Daniel Rueckert, Thomas Küstner, Kerstin Hammernik

Motion-compensated MR reconstruction (MCMR) is a powerful concept with considerable potential, consisting of two coupled sub-problems: Motion estimation, assuming a known image, and image reconstruction, assuming known motion.

Image Reconstruction Motion Estimation

Mesh-based 3D Motion Tracking in Cardiac MRI using Deep Learning

no code implementations5 Sep 2022 Qingjie Meng, Wenjia Bai, Tianrui Liu, Declan P O'Regan, Daniel Rueckert

By developing a differentiable mesh-to-image rasterizer, the method is able to leverage the anatomical shape information from 2D multi-view CMR images for 3D motion estimation.

Motion Estimation

Generative Modelling of the Ageing Heart with Cross-Sectional Imaging and Clinical Data

1 code implementation28 Aug 2022 Mengyun Qiao, Berke Doga Basaran, Huaqi Qiu, Shuo Wang, Yi Guo, Yuanyuan Wang, Paul M. Matthews, Daniel Rueckert, Wenjia Bai

Understanding the morphological and functional changes of the heart during ageing is a key scientific question, the answer to which will help us define important risk factors of cardiovascular disease and monitor disease progression.


Unsupervised Anomaly Localization with Structural Feature-Autoencoders

1 code implementation23 Aug 2022 Felix Meissen, Johannes Paetzold, Georgios Kaissis, Daniel Rueckert

Most commonly, the anomaly detection model generates a "normal" version of an input image, and the pixel-wise $l^p$-difference of the two is used to localize anomalies.

Unsupervised Anomaly Detection

Improved post-hoc probability calibration for out-of-domain MRI segmentation

1 code implementation4 Aug 2022 Cheng Ouyang, Shuo Wang, Chen Chen, Zeju Li, Wenjia Bai, Bernhard Kainz, Daniel Rueckert

In image segmentation, well-calibrated probabilities allow radiologists to identify regions where model-predicted segmentations are unreliable.

Image Segmentation MRI segmentation +2

MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRI

no code implementations29 Jul 2022 Qingjie Meng, Chen Qin, Wenjia Bai, Tianrui Liu, Antonio de Marvao, Declan P O'Regan, Daniel Rueckert

To address this problem, we propose a novel multi-view motion estimation network (MulViMotion), which integrates 2D cine CMR images acquired in short-axis and long-axis planes to learn a consistent 3D motion field of the heart.

Motion Estimation

Physiology-based simulation of the retinal vasculature enables annotation-free segmentation of OCT angiographs

1 code implementation22 Jul 2022 Martin J. Menten, Johannes C. Paetzold, Alina Dima, Bjoern H. Menze, Benjamin Knier, Daniel Rueckert

Encouraged by our method's competitive quantitative and superior qualitative performance, we believe that it constitutes a versatile tool to advance the quantitative analysis of OCTA images.

Benchmarking Retinal Vessel Segmentation +2

Placenta Segmentation in Ultrasound Imaging: Addressing Sources of Uncertainty and Limited Field-of-View

1 code implementation29 Jun 2022 Veronika A. Zimmer, Alberto Gomez, Emily Skelton, Robert Wright, Gavin Wheeler, Shujie Deng, Nooshin Ghavami, Karen Lloyd, Jacqueline Matthew, Bernhard Kainz, Daniel Rueckert, Joseph V. Hajnal, Julia A. Schnabel

Automatic segmentation of the placenta in fetal ultrasound (US) is challenging due to the (i) high diversity of placenta appearance, (ii) the restricted quality in US resulting in highly variable reference annotations, and (iii) the limited field-of-view of US prohibiting whole placenta assessment at late gestation.

Image Segmentation Multi-Task Learning +3

Faster Diffusion Cardiac MRI with Deep Learning-based breath hold reduction

no code implementations21 Jun 2022 Michael Tanzer, Pedro Ferreira, Andrew Scott, Zohya Khalique, Maria Dwornik, Dudley Pennell, Guang Yang, Daniel Rueckert, Sonia Nielles-Vallespin

Diffusion Tensor Cardiac Magnetic Resonance (DT-CMR) enables us to probe the microstructural arrangement of cardiomyocytes within the myocardium in vivo and non-invasively, which no other imaging modality allows.

Ensemble Learning

A Review of Causality for Learning Algorithms in Medical Image Analysis

no code implementations11 Jun 2022 Athanasios Vlontzos, Daniel Rueckert, Bernhard Kainz

Medical image analysis is a vibrant research area that offers doctors and medical practitioners invaluable insight and the ability to accurately diagnose and monitor disease.

BIG-bench Machine Learning Translation

Generative Myocardial Motion Tracking via Latent Space Exploration with Biomechanics-informed Prior

1 code implementation8 Jun 2022 Chen Qin, Shuo Wang, Chen Chen, Wenjia Bai, Daniel Rueckert

In contrast to most existing approaches which impose explicit generic regularization such as smoothness, in this work we propose a novel method that can implicitly learn an application-specific biomechanics-informed prior and embed it into a neural network-parameterized transformation model.

Image Registration

What do we learn? Debunking the Myth of Unsupervised Outlier Detection

no code implementations8 Jun 2022 Cosmin I. Bercea, Daniel Rueckert, Julia A. Schnabel

We have found that state-of-the-art (SOTA) AEs are either unable to constrain the latent manifold and allow reconstruction of abnormal patterns, or they are failing to accurately restore the inputs from their latent distribution, resulting in blurred or misaligned reconstructions.

Outlier Detection Out of Distribution (OOD) Detection

MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation

1 code implementation2 Jun 2022 Chen Chen, Zeju Li, Cheng Ouyang, Matt Sinclair, Wenjia Bai, Daniel Rueckert

We propose a novel data augmentation framework called MaxStyle, which maximizes the effectiveness of style augmentation for model OOD performance.

Data Augmentation Image Segmentation +2

Surface Analysis with Vision Transformers

1 code implementation31 May 2022 Simon Dahan, Logan Z. J. Williams, Abdulah Fawaz, Daniel Rueckert, Emma C. Robinson

The extension of convolutional neural networks (CNNs) to non-Euclidean geometries has led to multiple frameworks for studying manifolds.

Kernel Normalized Convolutional Networks

1 code implementation20 May 2022 Reza Nasirigerdeh, Reihaneh Torkzadehmahani, Daniel Rueckert, Georgios Kaissis

Existing convolutional neural network architectures frequently rely upon batch normalization (BatchNorm) to effectively train the model.

Federated Learning Image Classification +1

SmoothNets: Optimizing CNN architecture design for differentially private deep learning

1 code implementation9 May 2022 Nicolas W. Remerscheid, Alexander Ziller, Daniel Rueckert, Georgios Kaissis

The arguably most widely employed algorithm to train deep neural networks with Differential Privacy is DPSGD, which requires clipping and noising of per-sample gradients.

Image Classification with Differential Privacy

Surface Vision Transformers: Flexible Attention-Based Modelling of Biomedical Surfaces

1 code implementation7 Apr 2022 Simon Dahan, Hao Xu, Logan Z. J. Williams, Abdulah Fawaz, Chunhui Yang, Timothy S. Coalson, Michelle C. Williams, David E. Newby, A. David Edwards, Matthew F. Glasser, Alistair A. Young, Daniel Rueckert, Emma C. Robinson

Results suggest that Surface Vision Transformers (SiT) demonstrate consistent improvement over geometric deep learning methods for brain age and fluid intelligence prediction and achieve comparable performance on calcium score classification to standard metrics used in clinical practice.

Classification Data Augmentation

Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and Methodologies from CNN, GAN to Attention and Transformers

no code implementations1 Apr 2022 Jiahao Huang, Yingying Fang, Yang Nan, Huanjun Wu, Yinzhe Wu, Zhifan Gao, Yang Li, Zidong Wang, Pietro Lio, Daniel Rueckert, Yonina C. Eldar, Guang Yang

Research studies have shown no qualms about using data driven deep learning models for downstream tasks in medical image analysis, e. g., anatomy segmentation and lesion detection, disease diagnosis and prognosis, and treatment planning.

Anatomy Explainable Models +3

Surface Vision Transformers: Attention-Based Modelling applied to Cortical Analysis

1 code implementation30 Mar 2022 Simon Dahan, Abdulah Fawaz, Logan Z. J. Williams, Chunhui Yang, Timothy S. Coalson, Matthew F. Glasser, A. David Edwards, Daniel Rueckert, Emma C. Robinson

Motivated by the success of attention-modelling in computer vision, we translate convolution-free vision transformer approaches to surface data, to introduce a domain-agnostic architecture to study any surface data projected onto a spherical manifold.

Physics-Driven Deep Learning for Computational Magnetic Resonance Imaging

no code implementations23 Mar 2022 Kerstin Hammernik, Thomas Küstner, Burhaneddin Yaman, Zhengnan Huang, Daniel Rueckert, Florian Knoll, Mehmet Akçakaya

We consider inverse problems with both linear and non-linear forward models for computational MRI, and review the classical approaches for solving these.

MRI Reconstruction

Differentially private training of residual networks with scale normalisation

no code implementations1 Mar 2022 Helena Klause, Alexander Ziller, Daniel Rueckert, Kerstin Hammernik, Georgios Kaissis

The training of neural networks with Differentially Private Stochastic Gradient Descent offers formal Differential Privacy guarantees but introduces accuracy trade-offs.

Beyond Gradients: Exploiting Adversarial Priors in Model Inversion Attacks

no code implementations1 Mar 2022 Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis

Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks.

Federated Learning

CortexODE: Learning Cortical Surface Reconstruction by Neural ODEs

1 code implementation16 Feb 2022 Qiang Ma, Liu Li, Emma C. Robinson, Bernhard Kainz, Daniel Rueckert, Amir Alansary

Following the isosurface extraction step, two CortexODE models are trained to deform the initial surface to white matter and pial surfaces respectively.

Surface Reconstruction

Multi-modal unsupervised brain image registration using edge maps

no code implementations9 Feb 2022 Vasiliki Sideri-Lampretsa, Georgios Kaissis, Daniel Rueckert

Diffeomorphic deformable multi-modal image registration is a challenging task which aims to bring images acquired by different modalities to the same coordinate space and at the same time to preserve the topology and the invertibility of the transformation.

Image Registration

On the Pitfalls of Using the Residual Error as Anomaly Score

1 code implementation8 Feb 2022 Felix Meissen, Benedikt Wiestler, Georgios Kaissis, Daniel Rueckert

Many current state-of-the-art methods for anomaly localization in medical images rely on calculating a residual image between a potentially anomalous input image and its "healthy" reconstruction.

Differentially Private Graph Classification with GNNs

1 code implementation5 Feb 2022 Tamara T. Mueller, Johannes C. Paetzold, Chinmay Prabhakar, Dmitrii Usynin, Daniel Rueckert, Georgios Kaissis

In this work, we introduce differential privacy for graph-level classification, one of the key applications of machine learning on graphs.

BIG-bench Machine Learning Graph Classification

AutoSeg -- Steering the Inductive Biases for Automatic Pathology Segmentation

1 code implementation24 Jan 2022 Felix Meissen, Georgios Kaissis, Daniel Rueckert

In medical imaging, un-, semi-, or self-supervised pathology detection is often approached with anomaly- or out-of-distribution detection methods, whose inductive biases are not intentionally directed towards detecting pathologies, and are therefore sub-optimal for this task.

Out-of-Distribution Detection

AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis

no code implementations23 Dec 2021 Yutong Chen, Carola-Bibiane Schönlieb, Pietro Liò, Tim Leiner, Pier Luigi Dragotti, Ge Wang, Daniel Rueckert, David Firmin, Guang Yang

Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process.

Distributed Machine Learning and the Semblance of Trust

no code implementations21 Dec 2021 Dmitrii Usynin, Alexander Ziller, Daniel Rueckert, Jonathan Passerat-Palmbach, Georgios Kaissis

The utilisation of large and diverse datasets for machine learning (ML) at scale is required to promote scientific insight into many meaningful problems.

BIG-bench Machine Learning Federated Learning +1

Embedding Gradient-based Optimization in Image Registration Networks

1 code implementation7 Dec 2021 Huaqi Qiu, Kerstin Hammernik, Chen Qin, Chen Chen, Daniel Rueckert

Deep learning (DL) image registration methods amortize the costly pair-wise iterative optimization by training deep neural networks to predict the optimal transformation in one fast forward-pass.

Image Reconstruction Image Registration

Joint Learning of Localized Representations from Medical Images and Reports

1 code implementation6 Dec 2021 Philip Müller, Georgios Kaissis, Congyu Zou, Daniel Rueckert

Contrastive learning has proven effective for pre-training image models on unlabeled data with promising results for tasks such as medical image classification.

Contrastive Learning Medical Image Classification +5

FedRAD: Federated Robust Adaptive Distillation

no code implementations2 Dec 2021 Stefán Páll Sturluson, Samuel Trew, Luis Muñoz-González, Matei Grama, Jonathan Passerat-Palmbach, Daniel Rueckert, Amir Alansary

The robustness of federated learning (FL) is vital for the distributed training of an accurate global model that is shared among large number of clients.

Federated Learning Knowledge Distillation +1

Causality-inspired Single-source Domain Generalization for Medical Image Segmentation

1 code implementation24 Nov 2021 Cheng Ouyang, Chen Chen, Surui Li, Zeju Li, Chen Qin, Wenjia Bai, Daniel Rueckert

In this work, we investigate the single-source domain generalization problem: training a deep network that is robust to unseen domains, under the condition that training data is only available from one source domain, which is common in medical imaging applications.

Data Augmentation Domain Generalization +4

DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization

no code implementations30 Sep 2021 Turkay Kart, Wenjia Bai, Ben Glocker, Daniel Rueckert

In recent years, the research landscape of machine learning in medical imaging has changed drastically from supervised to semi-, weakly- or unsupervised methods.

Clustering Deep Clustering +1

Partial sensitivity analysis in differential privacy

1 code implementation22 Sep 2021 Tamara T. Mueller, Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Friederike Jungmann, Daniel Rueckert, Georgios Kaissis

However, while techniques such as individual R\'enyi DP (RDP) allow for granular, per-person privacy accounting, few works have investigated the impact of each input feature on the individual's privacy loss.

Image Classification

An automatic differentiation system for the age of differential privacy

no code implementations22 Sep 2021 Dmitrii Usynin, Alexander Ziller, Moritz Knolle, Andrew Trask, Kritika Prakash, Daniel Rueckert, Georgios Kaissis

We introduce Tritium, an automatic differentiation-based sensitivity analysis framework for differentially private (DP) machine learning (ML).

BIG-bench Machine Learning

A unified interpretation of the Gaussian mechanism for differential privacy through the sensitivity index

no code implementations22 Sep 2021 Georgios Kaissis, Moritz Knolle, Friederike Jungmann, Alexander Ziller, Dmitrii Usynin, Daniel Rueckert

$\psi$ uniquely characterises the GM and its properties by encapsulating its two fundamental quantities: the sensitivity of the query and the magnitude of the noise perturbation.

Challenging Current Semi-Supervised Anomaly Segmentation Methods for Brain MRI

1 code implementation13 Sep 2021 Felix Meissen, Georgios Kaissis, Daniel Rueckert

In this work, we tackle the problem of Semi-Supervised Anomaly Segmentation (SAS) in Magnetic Resonance Images (MRI) of the brain, which is the task of automatically identifying pathologies in brain images.

Anomaly Detection Segmentation

Improving Phenotype Prediction using Long-Range Spatio-Temporal Dynamics of Functional Connectivity

1 code implementation7 Sep 2021 Simon Dahan, Logan Z. J. Williams, Daniel Rueckert, Emma C. Robinson

Results show a prediction accuracy of 94. 4% for sex classification (an increase of 6. 2% compared to other methods), and an improvement of correlation with fluid intelligence of 0. 325 vs 0. 144, relative to a baseline model that encodes space and time separately.

Action Recognition Skeleton Based Action Recognition

PialNN: A Fast Deep Learning Framework for Cortical Pial Surface Reconstruction

1 code implementation6 Sep 2021 Qiang Ma, Emma C. Robinson, Bernhard Kainz, Daniel Rueckert, Amir Alansary

Traditional cortical surface reconstruction is time consuming and limited by the resolution of brain Magnetic Resonance Imaging (MRI).

Surface Reconstruction

NeuralDP Differentially private neural networks by design

no code implementations30 Jul 2021 Moritz Knolle, Dmitrii Usynin, Alexander Ziller, Marcus R. Makowski, Daniel Rueckert, Georgios Kaissis

The application of differential privacy to the training of deep neural networks holds the promise of allowing large-scale (decentralized) use of sensitive data while providing rigorous privacy guarantees to the individual.

Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation

no code implementations9 Jul 2021 Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Kritika Prakash, Andrew Trask, Rickmer Braren, Marcus Makowski, Daniel Rueckert, Georgios Kaissis

Reconciling large-scale ML with the closed-form reasoning required for the principled analysis of individual privacy loss requires the introduction of new tools for automatic sensitivity analysis and for tracking an individual's data and their features through the flow of computation.

BIG-bench Machine Learning

Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation

no code implementations8 Jul 2021 Shuo Wang, Chen Qin, Nicolo Savioli, Chen Chen, Declan O'Regan, Stuart Cook, Yike Guo, Daniel Rueckert, Wenjia Bai

In cardiac magnetic resonance (CMR) imaging, a 3D high-resolution segmentation of the heart is essential for detailed description of its anatomical structures.

Anatomy Cardiac Segmentation +2

Differentially private federated deep learning for multi-site medical image segmentation

1 code implementation6 Jul 2021 Alexander Ziller, Dmitrii Usynin, Nicolas Remerscheid, Moritz Knolle, Marcus Makowski, Rickmer Braren, Daniel Rueckert, Georgios Kaissis

The application of PTs to FL in medical imaging and the trade-offs between privacy guarantees and model utility, the ramifications on training performance and the susceptibility of the final models to attacks have not yet been conclusively investigated.

Federated Learning Image Segmentation +4

Detecting Outliers with Poisson Image Interpolation

1 code implementation6 Jul 2021 Jeremy Tan, Benjamin Hou, Thomas Day, John Simpson, Daniel Rueckert, Bernhard Kainz

We propose an alternative to image reconstruction-based and image embedding-based methods and propose a new self-supervised method to tackle pathological anomaly detection.

Anomaly Detection Image Reconstruction

Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation

2 code implementations2 Jul 2021 Chen Chen, Kerstin Hammernik, Cheng Ouyang, Chen Qin, Wenjia Bai, Daniel Rueckert

In this paper, we present a cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples.

Data Augmentation Image Reconstruction +4

Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net

no code implementations19 Jun 2021 Tianrui Liu, Qingjie Meng, Jun-Jie Huang, Athanasios Vlontzos, Daniel Rueckert, Bernhard Kainz

Intelligent video summarization algorithms allow to quickly convey the most relevant information in videos through the identification of the most essential and explanatory content while removing redundant video frames.

reinforcement-learning Reinforcement Learning (RL) +1

Learning a Model-Driven Variational Network for Deformable Image Registration

no code implementations25 May 2021 Xi Jia, Alexander Thorley, Wei Chen, Huaqi Qiu, Linlin Shen, Iain B Styles, Hyung Jin Chang, Ales Leonardis, Antonio de Marvao, Declan P. O'Regan, Daniel Rueckert, Jinming Duan

We then propose two neural layers (i. e. warping layer and intensity consistency layer) to model the analytical solution and a residual U-Net to formulate the denoising problem (i. e. generalized denoising layer).

Denoising Image Registration

Automated Knee X-ray Report Generation

no code implementations22 May 2021 Aydan Gasimova, Giovanni Montana, Daniel Rueckert

Gathering manually annotated images for the purpose of training a predictive model is far more challenging in the medical domain than for natural images as it requires the expertise of qualified radiologists.

Text Generation