Search Results for author: Giacomo Tarroni

Found 26 papers, 11 papers with code

Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection

1 code implementation9 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.

Unsupervised Anomaly Detection

Sample selection with noise rate estimation in noise learning of medical image analysis

no code implementations23 Dec 2023 Maolin Li, Giacomo Tarroni

Key words: noise-robust learning, medical image analysis, noise rate estimation, sample selection, sparse regularization

Image Classification Medical Image Classification

ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification

1 code implementation24 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.

Federated Learning Image Classification +2

Achieving state-of-the-art performance in the Medical Out-of-Distribution (MOOD) challenge using plausible synthetic anomalies

1 code implementation2 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.

Image Segmentation Medical Image Segmentation +3

MIM-OOD: Generative Masked Image Modelling for Out-of-Distribution Detection in Medical Images

no code implementations27 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.

Anatomy Out-of-Distribution Detection +1

Implicit U-Net for volumetric medical image segmentation

no code implementations30 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.

Image Segmentation Segmentation +2

Implicit field learning for unsupervised anomaly detection in medical images

1 code implementation9 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.

Decoder Out-of-Distribution Detection +1

Deep Generative Model-based Quality Control for Cardiac MRI Segmentation

no code implementations23 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.

Image Segmentation MRI segmentation +2

Realistic Adversarial Data Augmentation for MR Image Segmentation

1 code implementation23 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.

Data Augmentation Image Segmentation +3

Anti-Transfer Learning for Task Invariance in Convolutional Neural Networks for Speech Processing

1 code implementation11 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.

Emotion Recognition speech-recognition +2

Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation

no code implementations20 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.

Image Segmentation Segmentation +3

Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction

no code implementations5 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.

Image Segmentation Position +4

Explainable Anatomical Shape Analysis through Deep Hierarchical Generative Models

1 code implementation28 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.


A Comprehensive Approach for Learning-based Fully-Automated Inter-slice Motion Correction for Short-Axis Cine Cardiac MR Image Stacks

no code implementations3 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.

Motion Compensation

Recurrent neural networks for aortic image sequence segmentation with sparse annotations

no code implementations1 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.

Anatomy Segmentation

Learning-Based Quality Control for Cardiac MR Images

no code implementations25 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.

Motion Detection Specificity

Automated cardiovascular magnetic resonance image analysis with fully convolutional networks

1 code implementation25 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.