Следене
Mélanie Roschewitz (née Bernhardt)
Mélanie Roschewitz (née Bernhardt)
Други именаMelanie Bernhardt, Mélanie Bernhardt, Melanie Roschewitz
Imperial College London
Потвърден имейл адрес: ic.ac.uk - Начална страница
Заглавие
Позовавания
Позовавания
Година
Active label cleaning for improved dataset quality under resource constraints
M Bernhardt, DC Castro, R Tanno, A Schwaighofer, KC Tezcan, ...
Nature communications 13 (1), 1161, 2022
1002022
Algorithmic encoding of protected characteristics in chest X-ray disease detection models
B Glocker, C Jones, M Bernhardt, S Winzeck
EBioMedicine 89, 2023
71*2023
Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms
M Bernhardt, C Jones, B Glocker
Nature Medicine 28 (6), 1157-1158, 2022
57*2022
Risk of Bias in Chest Radiography Deep Learning Foundation Models
B Glocker, C Jones, M Roschewitz, S Winzeck
Radiology: Artificial Intelligence, e230060, 2023
48*2023
Training Variational Networks With Multidomain Simulations: Speed-of-Sound Image Reconstruction
M Bernhardt, V Vishnevskiy, R Rau, O Goksel
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control 67 …, 2020
322020
Automatic correction of performance drift under acquisition shift in medical image classification
M Roschewitz, G Khara, J Yearsley, N Sharma, JJ James, É Ambrózay, ...
Nature Communications 14 (1), 6608, 2023
192023
The Role of Subgroup Separability in Group-Fair Medical Image Classification
C Jones, M Roschewitz, B Glocker
International Conference on Medical Image Computing and Computer-Assisted …, 2023
102023
Failure detection in medical image classification: A reality check and benchmarking testbed
M Bernhardt, FDS Ribeiro, B Glocker
Transactions on Machine Learning Research, 2022
82022
Robust semi-supervised segmentation with timestep ensembling diffusion models
M Rosnati, M Roschewitz, B Glocker
Machine Learning for Health (ML4H), 512-527, 2023
52023
Hierarchical Analysis of Visual COVID-19 Features from Chest Radiographs
S Bannur, O Oktay, M Bernhardt, A Schwaighofer, R Jena, B Nushi, ...
arXiv preprint arXiv:2107.06618, 2021
32021
Counterfactual contrastive learning: robust representations via causal image synthesis
M Roschewitz, F de Sousa Ribeiro, T Xia, G Khara, B Glocker
MICCAI Workshop on Data Engineering in Medical Imaging, 22-32, 2024
22024
Automatic dataset shift identification to support root cause analysis of AI performance drift
M Roschewitz, R Mehta, C Jones, B Glocker
arXiv preprint arXiv:2411.07940, 2024
12024
Mitigating attribute amplification in counterfactual image generation
T Xia, M Roschewitz, F De Sousa Ribeiro, C Jones, B Glocker
International Conference on Medical Image Computing and Computer-Assisted …, 2024
12024
Distance Matters For Improving Performance Estimation Under Covariate Shift
M Roschewitz, B Glocker
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW …, 2023
12023
Rethinking Fair Representation Learning for Performance-Sensitive Tasks
C Jones, FS Ribeiro, M Roschewitz, DC Castro, B Glocker
arXiv preprint arXiv:2410.04120, 2024
2024
Radio-opaque artefacts in digital mammography: automatic detection and analysis of downstream effects
A Schueppert, B Glocker, M Roschewitz
Accepted at ISBI 2025, 2024
2024
Robust image representations with counterfactual contrastive learning
M Roschewitz, FDS Ribeiro, T Xia, G Khara, B Glocker
arXiv preprint arXiv:2409.10365, 2024
2024
Generating reports from scanned images
O Oktay, JA Valle, M Bernhardt, DC DE CASTRO, S Bannur, ...
US Patent App. 17/484,882, 2023
2023
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–18