22 citations · 37 across the 12 of their papers we have counts for
12 papers
Stochastic Siamese MAE Pretraining for Longitudinal Medical Images
Taha Emre, Arunava Chakravarty, Thomas Pinetz +9
Temporally aware image representations are crucial for capturing disease progression in 3D volumes of longitudinal medical datasets. However, recent state-of-the-art self-supervise…
GARD: Gamma-based Anatomical Restoration and Denoising for Retinal OCT
Botond Fazekas, Thomas Pinetz, Guilherme Aresta +2
Optical Coherence Tomography (OCT) is a vital imaging modality for diagnosing and monitoring retinal diseases. However, OCT images are inherently degraded by speckle noise, which o…
MIRAGE: Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis
José Morano, Botond Fazekas, Emese Sükei +7
Artificial intelligence (AI) has become a fundamental tool for assisting clinicians in analyzing ophthalmic images, such as optical coherence tomography (OCT). However, developing…
Deep Learning for Retinal Degeneration Assessment: A Comprehensive Analysis of the MARIO Challenge
Rachid Zeghlache, Ikram Brahim, Pierre-Henri Conze +47
The MARIO challenge, held at MICCAI 2024, focused on advancing the automated detection and monitoring of age-related macular degeneration (AMD) through the analysis of optical cohe…
Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality
Taha Emre, Teresa Araújo, Marzieh Oghbaie +3
Neovascular age-related macular degeneration (nAMD) is a leading cause of vision loss among older adults, where disease activity detection and progression prediction are critical f…
Forecasting Disease Progression with Parallel Hyperplanes in Longitudinal Retinal OCT
Arunava Chakravarty, Taha Emre, Dmitrii Lachinov +8
Predicting future disease progression risk from medical images is challenging due to patient heterogeneity, and subtle or unknown imaging biomarkers. Moreover, deep learning (DL) m…
Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations
Taha Emre, Arunava Chakravarty, Dmitrii Lachinov +3
Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse. E…
3DTINC: Time-Equivariant Non-Contrastive Learning for Predicting Disease Progression from Longitudinal OCTs
Taha Emre, Arunava Chakravarty, Antoine Rivail +10
Self-supervised learning (SSL) has emerged as a powerful technique for improving the efficiency and effectiveness of deep learning models. Contrastive methods are a prominent famil…
Pretrained Deep 2.5D Models for Efficient Predictive Modeling from Retinal OCT
Taha Emre, Marzieh Oghbaie, Arunava Chakravarty +9
In the field of medical imaging, 3D deep learning models play a crucial role in building powerful predictive models of disease progression. However, the size of these models presen…
Transformer-based end-to-end classification of variable-length volumetric data
Marzieh Oghbaie, Teresa Araujo, Taha Emre +2
The automatic classification of 3D medical data is memory-intensive. Also, variations in the number of slices between samples is common. Naïve solutions such as subsampling can sol…
Morph-SSL: Self-Supervision with Longitudinal Morphing to Predict AMD Progression from OCT
Arunava Chakravarty, Taha Emre, Oliver Leingang +8
The lack of reliable biomarkers makes predicting the conversion from intermediate to neovascular age-related macular degeneration (iAMD, nAMD) a challenging task. We develop a Deep…
TINC: Temporally Informed Non-Contrastive Learning for Disease Progression Modeling in Retinal OCT Volumes
Taha Emre, Arunava Chakravarty, Antoine Rivail +3
Recent contrastive learning methods achieved state-of-the-art in low label regimes. However, the training requires large batch sizes and heavy augmentations to create multiple view…