no code implementations • 23 Dec 2023 • Maolin Li, Giacomo Tarroni, Vasilis Siomos
Deep learning techniques have demonstrated remarkable success in the field of medical image analysis.
no code implementations • 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.
1 code implementation • 24 Nov 2023 • Vasilis Siomos, Sergio Naval-Marimont, Jonathan Passerat-Palmbach, Giacomo Tarroni
Federated Learning (FL) is a collaborative training paradigm that allows for privacy-preserving learning of cross-institutional models by eliminating the exchange of sensitive data and instead relying on the exchange of model parameters between the clients and a server.
1 code implementation • 2 Aug 2023 • Sergio Naval Marimont, Giacomo Tarroni
Our experiments and results in the latest MOOD challenge show that our simple yet effective approach can substantially improve the performance of Out-of-Distribution detection techniques which rely on synthetic anomalies.
no code implementations • 27 Jul 2023 • Sergio Naval Marimont, Vasilis Siomos, Giacomo Tarroni
Unsupervised Out-of-Distribution (OOD) detection consists in identifying anomalous regions in images leveraging only models trained on images of healthy anatomy.
no code implementations • 22 May 2023 • David Herron, Ernesto Jiménez-Ruiz, Giacomo Tarroni, Tillman Weyde
NeSy4VRD is a multifaceted resource designed to support the development of neurosymbolic AI (NeSy) research.
no code implementations • 30 Jun 2022 • Sergio Naval Marimont, Giacomo Tarroni
U-Net has been the go-to architecture for medical image segmentation tasks, however computational challenges arise when extending the U-Net architecture to 3D images.
1 code implementation • 7 Aug 2021 • Chen Chen, Chen Qin, Cheng Ouyang, Zeju Li, Shuo Wang, Huaqi Qiu, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert
The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training.
1 code implementation • 9 Jun 2021 • Sergio Naval Marimont, Giacomo Tarroni
In our approach, an auto-decoder feed-forward neural network learns the distribution of healthy images in the form of a mapping between spatial coordinates and probabilities over a proxy for tissue types.
no code implementations • 12 Dec 2020 • Sergio Naval Marimont, Giacomo Tarroni
The prior distribution of latent codes is then modelled using an Auto-Regressive (AR) model.
Out-of-Distribution Detection Unsupervised Anomaly Detection
1 code implementation • 23 Jun 2020 • Chen Chen, Chen Qin, Huaqi Qiu, Cheng Ouyang, Shuo Wang, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert
In this work, we propose an adversarial data augmentation method for training neural networks for medical image segmentation.
no code implementations • 23 Jun 2020 • Shuo Wang, Giacomo Tarroni, Chen Qin, Yuanhan Mo, Chengliang Dai, Chen Chen, Ben Glocker, Yike Guo, Daniel Rueckert, Wenjia Bai
Our approach provides a real-time and model-agnostic quality control for cardiac MRI segmentation, which has the potential to be integrated into clinical image analysis workflows.
1 code implementation • 11 Jun 2020 • Eric Guizzo, Tillman Weyde, Giacomo Tarroni
While transfer learning assumes that the learning process for a target task will benefit from re-using representations learned for another task, anti-transfer avoids the learning of representations that have been learned for an orthogonal task, i. e., one that is not relevant and potentially misleading for the target task, such as speaker identity for speech recognition or speech content for emotion recognition.
no code implementations • 9 Nov 2019 • Chen Chen, Chen Qin, Huaqi Qiu, Giacomo Tarroni, Jinming Duan, Wenjia Bai, Daniel Rueckert
Deep learning has become the most widely used approach for cardiac image segmentation in recent years.
no code implementations • 20 Aug 2019 • Chen Chen, Cheng Ouyang, Giacomo Tarroni, Jo Schlemper, Huaqi Qiu, Wenjia Bai, Daniel Rueckert
In this work, we present a fully automatic method to segment cardiac structures from late-gadolinium enhanced (LGE) images without using labelled LGE data for training, but instead by transferring the anatomical knowledge and features learned on annotated balanced steady-state free precession (bSSFP) images, which are easier to acquire.
no code implementations • 23 Jul 2019 • Chen Chen, Carlo Biffi, Giacomo Tarroni, Steffen Petersen, Wenjia Bai, Daniel Rueckert
Cardiac MR image segmentation is essential for the morphological and functional analysis of the heart.
no code implementations • 5 Jul 2019 • Wenjia Bai, Chen Chen, Giacomo Tarroni, Jinming Duan, Florian Guitton, Steffen E. Petersen, Yike Guo, Paul M. Matthews, Daniel Rueckert
In the recent years, convolutional neural networks have transformed the field of medical image analysis due to their capacity to learn discriminative image features for a variety of classification and regression tasks.
1 code implementation • 28 Jun 2019 • Carlo Biffi, Juan J. Cerrolaza, Giacomo Tarroni, Wenjia Bai, Antonio de Marvao, Ozan Oktay, Christian Ledig, Loic Le Folgoc, Konstantinos Kamnitsas, Georgia Doumou, Jinming Duan, Sanjay K. Prasad, Stuart A. Cook, Declan P. O'Regan, Daniel Rueckert
At the highest level of this hierarchy, a two-dimensional latent space is simultaneously optimised to discriminate distinct clinical conditions, enabling the direct visualisation of the classification space.
no code implementations • 28 Feb 2019 • Carlo Biffi, Juan J. Cerrolaza, Giacomo Tarroni, Antonio de Marvao, Stuart A. Cook, Declan P. O'Regan, Daniel Rueckert
Accurate segmentation of heart structures imaged by cardiac MR is key for the quantitative analysis of pathology.
no code implementations • 3 Oct 2018 • Giacomo Tarroni, Ozan Oktay, Matthew Sinclair, Wenjia Bai, Andreas Schuh, Hideaki Suzuki, Antonio de Marvao, Declan O'Regan, Stuart Cook, Daniel Rueckert
If long axis (LA) images are available, PSMs are generated for them and combined to create the target PSM; if not, the target PSM is produced from the same stack using a 3D model trained from motion-free stacks.
no code implementations • 1 Aug 2018 • Wenjia Bai, Hideaki Suzuki, Chen Qin, Giacomo Tarroni, Ozan Oktay, Paul M. Matthews, Daniel Rueckert
In this work, we propose an image sequence segmentation algorithm by combining a fully convolutional network with a recurrent neural network, which incorporates both spatial and temporal information into the segmentation task.
1 code implementation • 18 Jul 2018 • Carlo Biffi, Ozan Oktay, Giacomo Tarroni, Wenjia Bai, Antonio de Marvao, Georgia Doumou, Martin Rajchl, Reem Bedair, Sanjay Prasad, Stuart Cook, Declan O'Regan, Daniel Rueckert
However, current approaches to the diagnosis of cardiovascular diseases often rely on subjective human assessment as well as manual analysis of medical images.
no code implementations • 25 Mar 2018 • Giacomo Tarroni, Ozan Oktay, Wenjia Bai, Andreas Schuh, Hideaki Suzuki, Jonathan Passerat-Palmbach, Antonio de Marvao, Declan P. O'Regan, Stuart Cook, Ben Glocker, Paul M. Matthews, Daniel Rueckert
The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e. g. on UK Biobank, sensitivity and specificity respectively 88% and 99% for heart coverage estimation, 85% and 95% for motion detection), allowing their exclusion from the analysed dataset or the triggering of a new acquisition.
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 • 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.