1 code implementation • 25 Nov 2024 • Mischa Dombrowski, Weitong Zhang, Sarah Cechnicka, Hadrien Reynaud, Bernhard Kainz
Evaluation reveals that current diffusion models converge to limited subsets of the real distribution, with no current state-of-the-art models superpassing 77% of the diversity of the training data.
no code implementations • 7 Nov 2024 • Mischa Dombrowski, Hadrien Reynaud, Bernhard Kainz
Our findings indicate that only up to 30. 8% of the training videos are learned in latent video diffusion models, which could explain the lack of performance when training downstream tasks on synthetic data.
no code implementations • 5 Oct 2024 • Muhammad Haaris Khan, Hadrien Reynaud, Bernhard Kainz
Furthermore, an exploration of the VAE embedding used for latent diffusion models is performed, resulting in interesting theoretical insights such as a method for human-interpretable latent spaces.
no code implementations • 1 Oct 2024 • Weitong Zhang, Chengqi Zang, Bernhard Kainz
Large Language Models (LLMs) often produce outputs that -- though plausible -- can lack consistency and reliability, particularly in ambiguous or complex scenarios.
no code implementations • 21 Sep 2024 • Hadrien Reynaud, Matthew Baugh, Mischa Dombrowski, Sarah Cechnicka, Qingjie Meng, Bernhard Kainz
We introduce the Joint Video-Image Diffusion model (JVID), a novel approach to generating high-quality and temporally coherent videos.
no code implementations • 15 Sep 2024 • Liu Li, Hanchun Wang, Matthew Baugh, Qiang Ma, Weitong Zhang, Cheng Ouyang, Daniel Rueckert, Bernhard Kainz
Directly training a post-processing model to mitigate topological errors often fails as such models tend to be biased towards the topological errors of a target segmentation network.
no code implementations • 5 Sep 2024 • Zhe Li, Weitong Zhang, Sarah Cechnicka, Bernhard Kainz
While deep learning techniques have proven successful in image-related tasks, the exponentially increased data storage and computation costs become a significant challenge.
1 code implementation • 18 Jul 2024 • Sarah Cechnicka, James Ball, Matthew Baugh, Hadrien Reynaud, Naomi Simmonds, Andrew P. T. Smith, Catherine Horsfield, Candice Roufosse, Bernhard Kainz
Diagnosing medical conditions from histopathology data requires a thorough analysis across the various resolutions of Whole Slide Images (WSI).
1 code implementation • 9 Jul 2024 • Sergio Naval Marimont, Vasilis Siomos, Matthew Baugh, Christos Tzelepis, Bernhard Kainz, Giacomo Tarroni
Unsupervised Anomaly Detection (UAD) methods aim to identify anomalies in test samples comparing them with a normative distribution learned from a dataset known to be anomaly-free.
no code implementations • 20 Jun 2024 • Johanna P. Müller, Bernhard Kainz
We introduce a fast Self-adapting Forward-Forward Network (SaFF-Net) for medical imaging analysis, mitigating power consumption and resource limitations, which currently primarily stem from the prevalent reliance on back-propagation for model training and fine-tuning.
no code implementations • 19 Jun 2024 • Weitong Zhang, Chengqi Zang, Liu Li, Sarah Cechnicka, Cheng Ouyang, Bernhard Kainz
We uncover several strategies that inherently enhance the stability and generalizability of diffusion models for inverse problems and introduce a novel score-based diffusion framework, the \textbf{D}ynamics-aware S\textbf{D}E \textbf{D}iffusion \textbf{G}enerative \textbf{M}odel (D$^3$GM).
1 code implementation • 19 Jun 2024 • Zhe Li, Bernhard Kainz
We train a latent diffusion model and construct a new distilled synthetic dataset with a small number of human readable synthetic images.
1 code implementation • 18 Jun 2024 • Qiang Ma, Liu Li, Emma C. Robinson, Bernhard Kainz, Daniel Rueckert
We also verify that CoSeg can extract high-quality cortical surfaces from fetal brain MRI on which traditional pipelines fail to produce acceptable results.
2 code implementations • 2 Jun 2024 • Hadrien Reynaud, Qingjie Meng, Mischa Dombrowski, Arijit Ghosh, Thomas Day, Alberto Gomez, Paul Leeson, Bernhard Kainz
To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imaging data.
1 code implementation • 14 May 2024 • Qiang Ma, Kaili Liang, Liu Li, Saga Masui, Yourong Guo, Chiara Nosarti, Emma C. Robinson, Bernhard Kainz, Daniel Rueckert
In this paper, we propose a fast deep learning (DL) based pipeline for dHCP neonatal cortical surface reconstruction, incorporating DL-based brain extraction, cortical surface reconstruction and spherical projection, as well as GPU-accelerated cortical surface inflation and cortical feature estimation.
no code implementations • 25 Mar 2024 • Sophie Starck, Vasiliki Sideri-Lampretsa, Bernhard Kainz, Martin Menten, Tamara Mueller, Daniel Rueckert
Anatomical atlases are widely used for population analysis.
no code implementations • 21 Mar 2024 • Mathias Öttl, Frauke Wilm, Jana Steenpass, Jingna Qiu, Matthias Rübner, Arndt Hartmann, Matthias Beckmann, Peter Fasching, Andreas Maier, Ramona Erber, Bernhard Kainz, Katharina Breininger
Specifically, we utilize 1) a style conditioning mechanism which allows to inject style information of previously unseen images during image generation and 2) a content conditioning which can be targeted to a downstream task, e. g., layout for segmentation.
2 code implementations • 18 Mar 2024 • Foivos Paraperas Papantoniou, Alexandros Lattas, Stylianos Moschoglou, Jiankang Deng, Bernhard Kainz, Stefanos Zafeiriou
This paper presents Arc2Face, an identity-conditioned face foundation model, which, given the ArcFace embedding of a person, can generate diverse photo-realistic images with an unparalleled degree of face similarity than existing models.
Ranked #1 on
Diffusion Personalization Tuning Free
on AgeDB
no code implementations • 2 Jan 2024 • Lorenzo Venturini, Samuel Budd, Alfonso Farruggia, Robert Wright, Jacqueline Matthew, Thomas G. Day, Bernhard Kainz, Reza Razavi, Jo V. Hajnal
We use a Bayesian method to estimate the true value of each biometric from a large number of measurements and probabilistically reject outliers.
1 code implementation • 2 Dec 2023 • Sarah Cechnicka, Hadrien Reynaud, James Ball, Naomi Simmonds, Catherine Horsfield, Andrew Smith, Candice Roufosse, Bernhard Kainz
Diagnoses from histopathology images rely on information from both high and low resolutions of Whole Slide Images.
no code implementations • 30 Nov 2023 • Franciskus Xaverius Erick, Mina Rezaei, Johanna Paula Müller, Bernhard Kainz
Motivated by this, we introduce a new stochastic vision transformer that integrates uncertainty and distance awareness into self-supervised learning (SSL) pipelines.
1 code implementation • 26 Nov 2023 • Sergio Naval Marimont, Matthew Baugh, Vasilis Siomos, Christos Tzelepis, Bernhard Kainz, Giacomo Tarroni
Such a score function is potentially relevant for UAD, since $\nabla_x \log p(x)$ is itself a pixel-wise anomaly score.
no code implementations • 2 Nov 2023 • Hadrien Reynaud, Bernhard Kainz
This work presents an extensive hyperparameter search on Image Diffusion Models for Echocardiogram generation.
1 code implementation • 6 Oct 2023 • Glejdis Shkëmbi, Johanna P. Müller, Zhe Li, Katharina Breininger, Peter Schüffler, Bernhard Kainz
Breast cancer is a major concern for women's health globally, with axillary lymph node (ALN) metastasis identification being critical for prognosis evaluation and treatment guidance.
no code implementations • 10 Sep 2023 • Sudarshan Sreeram, Bernhard Kainz
Leveraging ML advancements to augment healthcare systems can improve patient outcomes.
1 code implementation • 17 Aug 2023 • Berke Doga Basaran, Weitong Zhang, Mengyun Qiao, Bernhard Kainz, Paul M. Matthews, Wenjia Bai
Data augmentation has become a de facto component of deep learning-based medical image segmentation methods.
1 code implementation • 21 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.
1 code implementation • 3 Jul 2023 • Matthew Baugh, Jeremy Tan, Johanna P. Müller, Mischa Dombrowski, James Batten, Bernhard Kainz
There is a growing interest in single-class modelling and out-of-distribution detection as fully supervised machine learning models cannot reliably identify classes not included in their training.
no code implementations • 15 Jun 2023 • Matthew Baugh, James Batten, Johanna P. Müller, Bernhard Kainz
This technical report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge.
no code implementations • 2 Jun 2023 • Mischa Dombrowski, Bernhard Kainz
Recent advances in score-based generative models have led to a huge spike in the development of downstream applications using generative models ranging from data augmentation over image and video generation to anomaly detection.
no code implementations • 19 Apr 2023 • Sarah Cechnicka, James Ball, Hadrien Reynaud, Callum Arthurs, Candice Roufosse, Bernhard Kainz
Geometric image augmentation is commonly used to improve robustness for average case predictions and to enrich limited datasets.
1 code implementation • 31 Mar 2023 • Mischa Dombrowski, Hadrien Reynaud, Johanna P. Müller, Matthew Baugh, Bernhard Kainz
Recent advancements in diffusion models have significantly impacted the trajectory of generative machine learning research, with many adopting the strategy of fine-tuning pre-trained models using domain-specific text-to-image datasets.
1 code implementation • 23 Mar 2023 • Johanna P. Müller, Matthew Baugh, Jeremy Tan, Mischa Dombrowski, Bernhard Kainz
Universal anomaly detection still remains a challenging problem in machine learning and medical image analysis.
Medical Image Analysis
Out of Distribution (OOD) Detection
+2
1 code implementation • 22 Mar 2023 • Hadrien Reynaud, Mengyun Qiao, Mischa Dombrowski, Thomas Day, Reza Razavi, Alberto Gomez, Paul Leeson, Bernhard Kainz
So far, video generation has only been possible by providing input data that is as rich as the output data, e. g., image sequence plus conditioning in, video out.
no code implementations • 3 Feb 2023 • Annika Reinke, Minu D. Tizabi, Michael Baumgartner, Matthias Eisenmann, Doreen Heckmann-Nötzel, A. Emre Kavur, Tim Rädsch, Carole H. Sudre, Laura Acion, Michela Antonelli, Tal Arbel, Spyridon Bakas, Arriel Benis, Matthew Blaschko, Florian Buettner, M. Jorge Cardoso, Veronika Cheplygina, Jianxu Chen, Evangelia Christodoulou, Beth A. Cimini, Gary S. Collins, Keyvan Farahani, Luciana Ferrer, Adrian Galdran, Bram van Ginneken, Ben Glocker, Patrick Godau, Robert Haase, Daniel A. Hashimoto, Michael M. Hoffman, Merel Huisman, Fabian Isensee, Pierre Jannin, Charles E. Kahn, Dagmar Kainmueller, Bernhard Kainz, Alexandros Karargyris, Alan Karthikesalingam, Hannes Kenngott, Jens Kleesiek, Florian Kofler, Thijs Kooi, Annette Kopp-Schneider, Michal Kozubek, Anna Kreshuk, Tahsin Kurc, Bennett A. Landman, Geert Litjens, Amin Madani, Klaus Maier-Hein, Anne L. Martel, Peter Mattson, Erik Meijering, Bjoern Menze, Karel G. M. Moons, Henning Müller, Brennan Nichyporuk, Felix Nickel, Jens Petersen, Susanne M. Rafelski, Nasir Rajpoot, Mauricio Reyes, Michael A. Riegler, Nicola Rieke, Julio Saez-Rodriguez, Clara I. Sánchez, Shravya Shetty, Maarten van Smeden, Ronald M. Summers, Abdel A. Taha, Aleksei Tiulpin, Sotirios A. Tsaftaris, Ben van Calster, Gaël Varoquaux, Manuel Wiesenfarth, Ziv R. Yaniv, Paul F. Jäger, Lena Maier-Hein
Validation metrics are key for the reliable tracking of scientific progress and for bridging the current chasm between artificial intelligence (AI) research and its translation into practice.
1 code implementation • ICCV 2023 • Mischa Dombrowski, Hadrien Reynaud, Matthew Baugh, Bernhard Kainz
Curating datasets for object segmentation is a difficult task.
no code implementations • 29 Dec 2022 • Mischa Dombrowski, Hadrien Reynaud, Matthew Baugh, Bernhard Kainz
Curating datasets for object segmentation is a difficult task.
no code implementations • 10 Oct 2022 • Luca Schmidtke, Benjamin Hou, Athanasios Vlontzos, Bernhard Kainz
Inferring 3D human pose from 2D images is a challenging and long-standing problem in the field of computer vision with many applications including motion capture, virtual reality, surveillance or gait analysis for sports and medicine.
2 code implementations • 10 Oct 2022 • Andreas Hinterreiter, Christina Humer, Bernhard Kainz, Marc Streit
ParaDime is a framework for parametric dimensionality reduction (DR).
no code implementations • 25 Sep 2022 • Clara Lebbos, Jen Barcroft, Jeremy Tan, Johanna P. Muller, Matthew Baugh, Athanasios Vlontzos, Srdjan Saso, Bernhard Kainz
Ovarian cancer is the most lethal gynaecological malignancy.
1 code implementation • 2 Sep 2022 • Matthew Baugh, Jeremy Tan, Athanasios Vlontzos, Johanna P. Müller, Bernhard Kainz
It is also difficult to assess whether a task generalises well for universal anomaly detection, as they are often only tested on a limited range of anomalies.
1 code implementation • 4 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.
1 code implementation • 29 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.
no code implementations • 11 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.
no code implementations • 6 Jun 2022 • Athanasios Vlontzos, Hadrien Reynaud, Bernhard Kainz
Curating a large scale medical imaging dataset for machine learning applications is both time consuming and expensive.
1 code implementation • 3 Jun 2022 • Lena Maier-Hein, Annika Reinke, Patrick Godau, Minu D. Tizabi, Florian Buettner, Evangelia Christodoulou, Ben Glocker, Fabian Isensee, Jens Kleesiek, Michal Kozubek, Mauricio Reyes, Michael A. Riegler, Manuel Wiesenfarth, A. Emre Kavur, Carole H. Sudre, Michael Baumgartner, Matthias Eisenmann, Doreen Heckmann-Nötzel, Tim Rädsch, Laura Acion, Michela Antonelli, Tal Arbel, Spyridon Bakas, Arriel Benis, Matthew Blaschko, M. Jorge Cardoso, Veronika Cheplygina, Beth A. Cimini, Gary S. Collins, Keyvan Farahani, Luciana Ferrer, Adrian Galdran, Bram van Ginneken, Robert Haase, Daniel A. Hashimoto, Michael M. Hoffman, Merel Huisman, Pierre Jannin, Charles E. Kahn, Dagmar Kainmueller, Bernhard Kainz, Alexandros Karargyris, Alan Karthikesalingam, Hannes Kenngott, Florian Kofler, Annette Kopp-Schneider, Anna Kreshuk, Tahsin Kurc, Bennett A. Landman, Geert Litjens, Amin Madani, Klaus Maier-Hein, Anne L. Martel, Peter Mattson, Erik Meijering, Bjoern Menze, Karel G. M. Moons, Henning Müller, Brennan Nichyporuk, Felix Nickel, Jens Petersen, Nasir Rajpoot, Nicola Rieke, Julio Saez-Rodriguez, Clara I. Sánchez, Shravya Shetty, Maarten van Smeden, Ronald M. Summers, Abdel A. Taha, Aleksei Tiulpin, Sotirios A. Tsaftaris, Ben van Calster, Gaël Varoquaux, Paul F. Jäger
The framework was developed in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint - a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output.
1 code implementation • 3 Jun 2022 • Hadrien Reynaud, Athanasios Vlontzos, Mischa Dombrowski, Ciarán Lee, Arian Beqiri, Paul Leeson, Bernhard Kainz
Causally-enabled machine learning frameworks could help clinicians to identify the best course of treatments by answering counterfactual questions.
no code implementations • 17 May 2022 • Liu Li, Qiang Ma, Matthew Sinclair, Antonios Makropoulos, Joseph Hajnal, A. David Edwards, Bernhard Kainz, Daniel Rueckert, Amir Alansary
Fetal Magnetic Resonance Imaging (MRI) is used in prenatal diagnosis and to assess early brain development.
1 code implementation • 16 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.
1 code implementation • CVPR 2022 • Daniel Grzech, Mohammad Farid Azampour, Ben Glocker, Julia Schnabel, Nassir Navab, Bernhard Kainz, Loïc le Folgoc
We propose a novel variational Bayesian formulation for diffeomorphic non-rigid registration of medical images, which learns in an unsupervised way a data-specific similarity metric.
1 code implementation • 5 Nov 2021 • Cesare Magnetti, Hadrien Reynaud, Bernhard Kainz
This paper presents the use of Multi-Agent Reinforcement Learning (MARL) to perform navigation in 3D anatomical volumes from medical imaging.
Computed Tomography (CT)
Multi-agent Reinforcement Learning
+4
1 code implementation • 25 Oct 2021 • Daniel Grzech, Mohammad Farid Azampour, Huaqi Qiu, Ben Glocker, Bernhard Kainz, Loïc le Folgoc
We develop a new Bayesian model for non-rigid registration of three-dimensional medical images, with a focus on uncertainty quantification.
3 code implementations • 30 Sep 2021 • Hannah M. Schlüter, Jeremy Tan, Benjamin Hou, Bernhard Kainz
We introduce a simple and intuitive self-supervision task, Natural Synthetic Anomalies (NSA), for training an end-to-end model for anomaly detection and localization using only normal training data.
Ranked #5 on
Anomaly Classification
on GoodsAD
1 code implementation • 6 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).
no code implementations • 4 Sep 2021 • Athanasios Vlontzos, Bernhard Kainz, Ciaran M. Gilligan-Lee
To learn causal mechanisms satisfying these constraints, and perform counterfactual inference with them, we introduce deep twin networks.
no code implementations • 6 Aug 2021 • Agisilaos Chartsias, Shan Gao, Angela Mumith, Jorge Oliveira, Kanwal Bhatia, Bernhard Kainz, Arian Beqiri
Analysis of cardiac ultrasound images is commonly performed in routine clinical practice for quantification of cardiac function.
no code implementations • 30 Jul 2021 • Samuel Budd, Thomas Day, John Simpson, Karen Lloyd, Jacqueline Matthew, Emily Skelton, Reza Razavi, Bernhard Kainz
We study the time and cost implications of using novice annotators, the raw performance of novice annotators compared to gold-standard expert annotators, and the downstream effects on a trained Deep Learning segmentation model's performance for detecting a specific congenital heart disease (hypoplastic left heart syndrome) in fetal ultrasound imaging.
no code implementations • 6 Jul 2021 • Samuel Budd, Matthew Sinclair, Thomas Day, Athanasios Vlontzos, Jeremy Tan, Tianrui Liu, Jaqueline Matthew, Emily Skelton, John Simpson, Reza Razavi, Ben Glocker, Daniel Rueckert, Emma C. Robinson, Bernhard Kainz
Fetal ultrasound screening during pregnancy plays a vital role in the early detection of fetal malformations which have potential long-term health impacts.
1 code implementation • 6 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.
1 code implementation • 5 Jul 2021 • Benjamin Hou, Georgios Kaissis, Ronald Summers, Bernhard Kainz
Chest radiographs are one of the most common diagnostic modalities in clinical routine.
1 code implementation • 2 Jul 2021 • Hadrien Reynaud, Athanasios Vlontzos, Benjamin Hou, Arian Beqiri, Paul Leeson, Bernhard Kainz
We achieve an average frame distance of 3. 36 frames for the ES and 7. 17 frames for the ED on videos of arbitrary length.
no code implementations • 19 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.
2 code implementations • CVPR 2021 • Luca Schmidtke, Athanasios Vlontzos, Simon Ellershaw, Anna Lukens, Tomoki Arichi, Bernhard Kainz
Human pose estimation is a major computer vision problem with applications ranging from augmented reality and video capture to surveillance and movement tracking.
1 code implementation • 12 Apr 2021 • Annika Reinke, Minu D. Tizabi, Carole H. Sudre, Matthias Eisenmann, Tim Rädsch, Michael Baumgartner, Laura Acion, Michela Antonelli, Tal Arbel, Spyridon Bakas, Peter Bankhead, Arriel Benis, Matthew Blaschko, Florian Buettner, M. Jorge Cardoso, Jianxu Chen, Veronika Cheplygina, Evangelia Christodoulou, Beth Cimini, Gary S. Collins, Sandy Engelhardt, Keyvan Farahani, Luciana Ferrer, Adrian Galdran, Bram van Ginneken, Ben Glocker, Patrick Godau, Robert Haase, Fred Hamprecht, Daniel A. Hashimoto, Doreen Heckmann-Nötzel, Peter Hirsch, Michael M. Hoffman, Merel Huisman, Fabian Isensee, Pierre Jannin, Charles E. Kahn, Dagmar Kainmueller, Bernhard Kainz, Alexandros Karargyris, Alan Karthikesalingam, A. Emre Kavur, Hannes Kenngott, Jens Kleesiek, Andreas Kleppe, Sven Kohler, Florian Kofler, Annette Kopp-Schneider, Thijs Kooi, Michal Kozubek, Anna Kreshuk, Tahsin Kurc, Bennett A. Landman, Geert Litjens, Amin Madani, Klaus Maier-Hein, Anne L. Martel, Peter Mattson, Erik Meijering, Bjoern Menze, David Moher, Karel G. M. Moons, Henning Müller, Brennan Nichyporuk, Felix Nickel, M. Alican Noyan, Jens Petersen, Gorkem Polat, Susanne M. Rafelski, Nasir Rajpoot, Mauricio Reyes, Nicola Rieke, Michael Riegler, Hassan Rivaz, Julio Saez-Rodriguez, Clara I. Sánchez, Julien Schroeter, Anindo Saha, M. Alper Selver, Lalith Sharan, Shravya Shetty, Maarten van Smeden, Bram Stieltjes, Ronald M. Summers, Abdel A. Taha, Aleksei Tiulpin, Sotirios A. Tsaftaris, Ben van Calster, Gaël Varoquaux, Manuel Wiesenfarth, Ziv R. Yaniv, Paul Jäger, Lena Maier-Hein
While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation.
2 code implementations • 4 Apr 2021 • Yueqi Cao, Athanasios Vlontzos, Luca Schmidtke, Bernhard Kainz, Anthea Monod
Appropriately representing elements in a database so that queries may be accurately matched is a central task in information retrieval; recently, this has been achieved by embedding the graphical structure of the database into a manifold in a hierarchy-preserving manner using a variety of metrics.
no code implementations • 15 Nov 2020 • Elisa Chotzoglou, Thomas Day, Jeremy Tan, Jacqueline Matthew, David Lloyd, Reza Razavi, John Simpson, Bernhard Kainz
Congenital heart disease is considered as one the most common groups of congenital malformations which affects $6-11$ per $1000$ newborns.
1 code implementation • 9 Nov 2020 • Jeremy Tan, Benjamin Hou, James Batten, Huaqi Qiu, Bernhard Kainz
A wide residual encoder decoder is trained to give a pixel-wise prediction of the patch and its interpolation factor.
no code implementations • 30 Oct 2020 • Qingjie Meng, Jacqueline Matthew, Veronika A. Zimmer, Alberto Gomez, David F. A. Lloyd, Daniel Rueckert, Bernhard Kainz
To address this problem, we propose Mutual Information-based Disentangled Neural Networks (MIDNet), which extract generalizable categorical features to transfer knowledge to unseen categories in a target domain.
no code implementations • 4 Oct 2020 • Samuel Budd, Prachi Patkee, Ana Baburamani, Mary Rutherford, Emma C. Robinson, Bernhard Kainz
The cerebral cortex performs higher-order brain functions and is thus implicated in a range of cognitive disorders.
no code implementations • 20 Aug 2020 • Athanasios Vlontzos, Henrique Bergallo Rocha, Daniel Rueckert, Bernhard Kainz
In this paper we propose a novel theoretical framework to perform causal future prediction by embedding spatiotemporal information on a Minkowski space-time.
1 code implementation • 19 Aug 2020 • Qingjie Meng, Daniel Rueckert, Bernhard Kainz
The proposed MetFA method explicitly and directly learns the latent representation without using domain adversarial training.
no code implementations • 16 Aug 2020 • Jeremy Tan, Anselm Au, Qingjie Meng, Sandy FinesilverSmith, John Simpson, Daniel Rueckert, Reza Razavi, Thomas Day, David Lloyd, Bernhard Kainz
In this paper we discuss the potential for deep learning techniques to aid in the detection of congenital heart disease (CHD) in fetal ultrasound.
no code implementations • 23 Jun 2020 • Athanasios Vlontzos, Samuel Budd, Benjamin Hou, Daniel Rueckert, Bernhard Kainz
X-Ray imaging is quick, cheap and useful for front-line care assessment and intra-operative real-time imaging (e. g., C-Arm Fluoroscopy).
1 code implementation • 23 Jun 2020 • Andreas Hinterreiter, Marc Streit, Bernhard Kainz
We present Projective Latent Interventions (PLIs), a technique for retraining classifiers by back-propagating manual changes made to low-dimensional embeddings of the latent space.
1 code implementation • 19 May 2020 • Tianrui Liu, Qingjie Meng, Athanasios Vlontzos, Jeremy Tan, Daniel Rueckert, Bernhard Kainz
We show that our method is superior to alternative video summarization methods and that it preserves essential information required by clinical diagnostic standards.
no code implementations • 16 Apr 2020 • Jeremy Tan, Bernhard Kainz
We search for regions in the behavior space that the current archive cannot reach.
1 code implementation • ICLR 2019 • Nina Miolane, Alice Le Brigant, Johan Mathe, Benjamin Hou, Nicolas Guigui, Yann Thanwerdas, Stefan Heyder, Olivier Peltre, Niklas Koep, Hadi Zaatiti, Hatem Hajri, Yann Cabanes, Thomas Gerald, Paul Chauchat, Christian Shewmake, Bernhard Kainz, Claire Donnat, Susan Holmes, Xavier Pennec
We introduce Geomstats, an open-source Python toolbox for computations and statistics on nonlinear manifolds, such as hyperbolic spaces, spaces of symmetric positive definite matrices, Lie groups of transformations, and many more.
no code implementations • 29 Feb 2020 • Qingjie Meng, Daniel Rueckert, Bernhard Kainz
Deep learning models exhibit limited generalizability across different domains.
no code implementations • 7 Oct 2019 • Samuel Budd, Emma C. Robinson, Bernhard Kainz
Fully automatic deep learning has become the state-of-the-art technique for many tasks including image acquisition, analysis and interpretation, and for the extraction of clinically useful information for computer-aided detection, diagnosis, treatment planning, intervention and therapy.
no code implementations • 6 Oct 2019 • Giulio Jiang, Bernhard Kainz
Rendering realistic images with Global Illumination (GI) is a computationally demanding task and often requires dedicated hardware for feasible runtime.
Graphics
1 code implementation • 31 Aug 2019 • Robert Holland, Uday Patel, Phillip Lung, Elisa Chotzoglou, Bernhard Kainz
Crohn's disease, one of two inflammatory bowel diseases (IBD), affects 200, 000 people in the UK alone, or roughly one in every 500.
no code implementations • 30 Aug 2019 • Jeremy Tan, Anselm Au, Qingjie Meng, Bernhard Kainz
Semi-supervised learning methods have achieved excellent performance on standard benchmark datasets using very few labelled images.
no code implementations • 29 Aug 2019 • Benjamin Hou, Athanasios Vlontzos, Amir Alansary, Daniel Rueckert, Bernhard Kainz
Real-world settings often do not allow acquisition of high-resolution volumetric images for accurate morphological assessment and diagnostic.
1 code implementation • 21 Aug 2019 • Qingjie Meng, Nick Pawlowski, Daniel Rueckert, Bernhard Kainz
These entangled image properties lead to a semantically redundant feature encoding for the relevant task and thus lead to poor generalization of deep learning algorithms.
no code implementations • 7 Aug 2019 • Samuel Budd, Matthew Sinclair, Bishesh Khanal, Jacqueline Matthew, David Lloyd, Alberto Gomez, Nicolas Toussaint, Emma Robinson, Bernhard Kainz
Manual estimation of fetal Head Circumference (HC) from Ultrasound (US) is a key biometric for monitoring the healthy development of fetuses.
1 code implementation • 30 Jun 2019 • Athanasios Vlontzos, Amir Alansary, Konstantinos Kamnitsas, Daniel Rueckert, Bernhard Kainz
We compare our approach with state-of-the-art architectures and achieve significantly better accuracy by reducing the detection error by 50%, while requiring fewer computational resources and time to train compared to the naive approach of training K agents separately.
no code implementations • 5 Mar 2019 • Daniel Grzech, Loïc le Folgoc, Mattias P. Heinrich, Bishesh Khanal, Jakub Moll, Julia A. Schnabel, Ben Glocker, Bernhard Kainz
We present an implementation of a new approach to diffeomorphic non-rigid registration of medical images.
no code implementations • 27 Jan 2019 • Robert Robinson, Vanya V. Valindria, Wenjia Bai, Ozan Oktay, Bernhard Kainz, Hideaki Suzuki, Mihir M. Sanghvi, Nay Aung, Jos$é$ Miguel Paiva, Filip Zemrak, Kenneth Fung, Elena Lukaschuk, Aaron M. Lee, Valentina Carapella, Young Jin Kim, Stefan K. Piechnik, Stefan Neubauer, Steffen E. Petersen, Chris Page, Paul M. Matthews, Daniel Rueckert, Ben Glocker
Methods: To overcome this challenge, we explore an approach for predicting segmentation quality based on Reverse Classification Accuracy, which enables us to discriminate between successful and failed segmentations on a per-cases basis.
no code implementations • 20 Nov 2018 • Qingjie Meng, Matthew Sinclair, Veronika Zimmer, Benjamin Hou, Martin Rajchl, Nicolas Toussaint, Ozan Oktay, Jo Schlemper, Alberto Gomez, James Housden, Jacqueline Matthew, Daniel Rueckert, Julia Schnabel, Bernhard Kainz
Our method is more consistent than human annotation, and outperforms the state-of-the-art quantitatively in shadow segmentation and qualitatively in confidence estimation of shadow regions.
1 code implementation • ICLR 2019 • Daniel C. Castro, Jeremy Tan, Bernhard Kainz, Ender Konukoglu, Ben Glocker
Revealing latent structure in data is an active field of research, having introduced exciting technologies such as variational autoencoders and adversarial networks, and is essential to push machine learning towards unsupervised knowledge discovery.
2 code implementations • 22 Aug 2018 • Jo Schlemper, Ozan Oktay, Michiel Schaap, Mattias Heinrich, Bernhard Kainz, Ben Glocker, Daniel Rueckert
AGs can be easily integrated into standard CNN models such as VGG or U-Net architectures with minimal computational overhead while increasing the model sensitivity and prediction accuracy.
1 code implementation • 19 Jun 2018 • Yuanwei Li, Bishesh Khanal, Benjamin Hou, Amir Alansary, Juan J. Cerrolaza, Matthew Sinclair, Jacqueline Matthew, Chandni Gupta, Caroline Knight, Bernhard Kainz, Daniel Rueckert
We propose a new Iterative Transformation Network (ITN) for the automatic detection of standard planes in 3D volumes.
1 code implementation • 18 Jun 2018 • Yuanwei Li, Amir Alansary, Juan J. Cerrolaza, Bishesh Khanal, Matthew Sinclair, Jacqueline Matthew, Chandni Gupta, Caroline Knight, Bernhard Kainz, Daniel Rueckert
PIN is computationally efficient since the inference stage only selectively samples a small number of patches in an iterative fashion rather than a dense sampling at every location in the volume.
no code implementations • 16 Jun 2018 • Robert Robinson, Ozan Oktay, Wenjia Bai, Vanya Valindria, Mihir Sanghvi, Nay Aung, José Paiva, Filip Zemrak, Kenneth Fung, Elena Lukaschuk, Aaron Lee, Valentina Carapella, Young Jin Kim, Bernhard Kainz, Stefan Piechnik, Stefan Neubauer, Steffen Petersen, Chris Page, Daniel Rueckert, Ben Glocker
Recent advances in deep learning based image segmentation methods have enabled real-time performance with human-level accuracy.
no code implementations • 8 Jun 2018 • Amir Alansary, Loic Le Folgoc, Ghislain Vaillant, Ozan Oktay, Yuanwei Li, Wenjia Bai, Jonathan Passerat-Palmbach, Ricardo Guerrero, Konstantinos Kamnitsas, Benjamin Hou, Steven McDonagh, Ben Glocker, Bernhard Kainz, Daniel Rueckert
Navigating through target anatomy to find the required view plane is tedious and operator-dependent.
1 code implementation • 2 May 2018 • Benjamin Hou, Nina Miolane, Bishesh Khanal, Matthew C. H. Lee, Amir Alansary, Steven McDonagh, Jo V. Hajnal, Daniel Rueckert, Ben Glocker, Bernhard Kainz
In this paper, we propose a general Riemannian formulation of the pose estimation problem.
no code implementations • 24 Apr 2018 • Matthew Sinclair, Christian F. Baumgartner, Jacqueline Matthew, Wenjia Bai, Juan Cerrolaza Martinez, Yuanwei Li, Sandra Smith, Caroline L. Knight, Bernhard Kainz, Jo Hajnal, Andrew P. King, Daniel Rueckert
Measurement of head biometrics from fetal ultrasonography images is of key importance in monitoring the healthy development of fetuses.
6 code implementations • 15 Apr 2018 • Jo Schlemper, Ozan Oktay, Liang Chen, Jacqueline Matthew, Caroline Knight, Bernhard Kainz, Ben Glocker, Daniel Rueckert
We show that, when the base network has a high capacity, the incorporated attention mechanism can provide efficient object localisation while improving the overall performance.
37 code implementations • 11 Apr 2018 • Ozan Oktay, Jo Schlemper, Loic Le Folgoc, Matthew Lee, Mattias Heinrich, Kazunari Misawa, Kensaku Mori, Steven McDonagh, Nils Y. Hammerla, Bernhard Kainz, Ben Glocker, Daniel Rueckert
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes.
Ranked #1 on
Pancreas Segmentation
on CT-150
no code implementations • 5 Jan 2018 • Keyang Zhou, Bernhard Kainz
We believe that our work makes network introspection more feasible for debugging and understanding deep convolutional networks.
1 code implementation • 18 Nov 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.
no code implementations • 4 Nov 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.
1 code implementation • 25 Oct 2017 • 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
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.
no code implementations • 19 Sep 2017 • Benjamin Hou, Bishesh Khanal, Amir Alansary, Steven McDonagh, Alice Davidson, Mary Rutherford, Jo V. Hajnal, Daniel Rueckert, Ben Glocker, Bernhard Kainz
We extensively evaluate the effectiveness of our approach quantitatively on simulated Magnetic Resonance Imaging (MRI), fetal brain imagery with synthetic motion and further demonstrate qualitative results on real fetal MRI data where our method is integrated into a full reconstruction and motion compensation pipeline.
1 code implementation • 22 May 2017 • Ozan Oktay, Enzo Ferrante, Konstantinos Kamnitsas, Mattias Heinrich, Wenjia Bai, Jose Caballero, Stuart Cook, Antonio de Marvao, Timothy Dawes, Declan O'Regan, Bernhard Kainz, Ben Glocker, Daniel Rueckert
However, in most recent and promising techniques such as CNN based segmentation it is not obvious how to incorporate such prior knowledge.
1 code implementation • 28 Feb 2017 • Benjamin Hou, Amir Alansary, Steven McDonagh, Alice Davidson, Mary Rutherford, Jo V. Hajnal, Daniel Rueckert, Ben Glocker, Bernhard Kainz
Our approach is attractive in challenging imaging scenarios, where significant subject motion complicates reconstruction performance of 3D volumes from 2D slice data.
no code implementations • 28 Feb 2017 • Steven McDonagh, Benjamin Hou, Konstantinos Kamnitsas, Ozan Oktay, Amir Alansary, Mary Rutherford, Jo V. Hajnal, Bernhard Kainz
Fast imaging is required for targets that move to avoid motion artefacts.
2 code implementations • 16 Dec 2016 • Christian F. Baumgartner, Konstantinos Kamnitsas, Jacqueline Matthew, Tara P. Fletcher, Sandra Smith, Lisa M. Koch, Bernhard Kainz, Daniel Rueckert
In this paper, we propose a novel method based on convolutional neural networks which can automatically detect 13 fetal standard views in freehand 2D ultrasound data as well as provide a localisation of the fetal structures via a bounding box.
1 code implementation • 22 Nov 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.
no code implementations • 3 Jun 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.
no code implementations • 25 May 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.
no code implementations • 21 Oct 2015 • Jan Egger, Harald Busse, Philipp Brandmaier, Daniel Seider, Matthias Gawlitza, Steffen Strocka, Philip Voglreiter, Mark Dokter, Michael Hofmann, Bernhard Kainz, Alexander Hann, Xiaojun Chen, Tuomas Alhonnoro, Mika Pollari, Dieter Schmalstieg, Michael Moche
The visual feedback and interactivity make the proposed tool well suitable for the clinical workflow.