Search Results for author: Hrvoje Bogunović

Found 32 papers, 13 papers with code

RetFiner: A Vision-Language Refinement Scheme for Retinal Foundation Models

no code implementations27 Jun 2025 Ronald Fecso, José Morano, Ursula Schmidt-Erfurth, Hrvoje Bogunović

To address this, we propose RetFiner, an SSL vision-language refinement scheme that improves the representations of existing FMs and enables their efficient and direct adaptation to specific populations for improved downstream performance.

PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image Analysis

1 code implementation12 Jun 2025 Marzieh Oghbaie, Teresa Araújoa, Hrvoje Bogunović

Background and Objective: Prototype-based methods improve interpretability by learning fine-grained part-prototypes; however, their visualization in the input pixel space is not always consistent with human-understandable biomarkers.

Contrastive Learning Diagnostic +2

MIRAGE: Multimodal foundation model and benchmark for comprehensive retinal OCT image analysis

1 code implementation10 Jun 2025 José Morano, Botond Fazekas, Emese Sükei, Ronald Fecso, Taha Emre, Markus Gumpinger, Georg Faustmann, Marzieh Oghbaie, Ursula Schmidt-Erfurth, Hrvoje Bogunović

Artificial intelligence (AI) has become a fundamental tool for assisting clinicians in analyzing ophthalmic images, such as optical coherence tomography (OCT).

Segmentation

Automatic detection and prediction of nAMD activity change in retinal OCT using Siamese networks and Wasserstein Distance for ordinality

1 code implementation24 Jan 2025 Taha Emre, Teresa Araújo, Marzieh Oghbaie, Dmitrii Lachinov, Guilherme Aresta, Hrvoje Bogunović

In this work, we proposed deep learning models for the two tasks of the public MARIO Challenge at MICCAI 2024, designed to detect and forecast changes in nAMD severity with longitudinal retinal OCT. For the first task, we employ a Vision Transformer (ViT) based Siamese Network to detect changes in AMD severity by comparing scan embeddings of a patient from different time points.

Action Detection Activity Detection +1

Comparative Analysis of Data Augmentation for Retinal OCT Biomarker Segmentation

no code implementations20 Sep 2024 Markus Unterdechler, Botond Fazekas, Guilherme Aresta, Hrvoje Bogunović

Data augmentation plays a crucial role in addressing the challenge of limited expert-annotated datasets in deep learning applications for retinal Optical Coherence Tomography (OCT) scans.

Data Augmentation

Specialist vision-language models for clinical ophthalmology

1 code implementation11 Jul 2024 Robbie Holland, Thomas R. P. Taylor, Christopher Holmes, Sophie Riedl, Julia Mai, Maria Patsiamanidi, Dimitra Mitsopoulou, Paul Hager, Philip Müller, Hendrik P. N. Scholl, Hrvoje Bogunović, Ursula Schmidt-Erfurth, Daniel Rueckert, Sobha Sivaprasad, Andrew J. Lotery, Martin J. Menten

The resulting model, RetinaVLM, can be instructed to write reports that significantly outperform those written by leading foundation medical VLMs in disease staging (F1 score of 0. 63 vs. 0. 11) and patient referral (0. 67 vs. 0. 39), and approaches the diagnostic performance of junior ophthalmologists (who achieve 0. 77 and 0. 78 on the respective tasks).

Diagnostic

Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations

1 code implementation15 May 2024 Taha Emre, Arunava Chakravarty, Dmitrii Lachinov, Antoine Rivail, Ursula Schmidt-Erfurth, Hrvoje Bogunović

Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously preventing representational collapse.

Contrastive Learning

Spatiotemporal Representation Learning for Short and Long Medical Image Time Series

1 code implementation12 Mar 2024 Chengzhi Shen, Martin J. Menten, Hrvoje Bogunović, Ursula Schmidt-Erfurth, Hendrik Scholl, Sobha Sivaprasad, Andrew Lotery, Daniel Rueckert, Paul Hager, Robbie Holland

Moreover, tracking longer term developments that occur over months or years in evolving processes, such as age-related macular degeneration (AMD), is essential for accurate prognosis.

Contrastive Learning Decision Making +4

RRWNet: Recursive Refinement Network for effective retinal artery/vein segmentation and classification

1 code implementation5 Feb 2024 José Morano, Guilherme Aresta, Hrvoje Bogunović

The framework consists of a fully convolutional neural network that recursively refines semantic segmentation maps, correcting manifest classification errors and thus improving topological consistency.

Artery/Veins Retinal Vessel Segmentation Classification +2

SAMedOCT: Adapting Segment Anything Model (SAM) for Retinal OCT

no code implementations18 Aug 2023 Botond Fazekas, José Morano, Dmitrii Lachinov, Guilherme Aresta, Hrvoje Bogunović

The Segment Anything Model (SAM) has gained significant attention in the field of image segmentation due to its impressive capabilities and prompt-based interface.

Image Segmentation Segmentation +1

Self-supervised learning via inter-modal reconstruction and feature projection networks for label-efficient 3D-to-2D segmentation

1 code implementation6 Jul 2023 José Morano, Guilherme Aresta, Dmitrii Lachinov, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunović

Moreover, the proposed SSL method allows further improvement of this performance by up to 23%, and we show that the SSL is beneficial regardless of the network architecture.

Decoder Image Segmentation +5

PALM: Open Fundus Photograph Dataset with Pathologic Myopia Recognition and Anatomical Structure Annotation

1 code implementation13 May 2023 Huihui Fang, Fei Li, Junde Wu, Huazhu Fu, Xu sun, José Ignacio Orlando, Hrvoje Bogunović, Xiulan Zhang, Yanwu Xu

Our databases comprises 1200 images with associated labels for the pathologic myopia category and manual annotations of the optic disc, the position of the fovea and delineations of lesions such as patchy retinal atrophy (including peripapillary atrophy) and retinal detachment.

Diagnostic

ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images

no code implementations16 Feb 2022 Huihui Fang, Fei Li, Huazhu Fu, Xu sun, Xingxing Cao, Fengbin Lin, Jaemin Son, Sunho Kim, Gwenole Quellec, Sarah Matta, Sharath M Shankaranarayana, Yi-Ting Chen, Chuen-heng Wang, Nisarg A. Shah, Chia-Yen Lee, Chih-Chung Hsu, Hai Xie, Baiying Lei, Ujjwal Baid, Shubham Innani, Kang Dang, Wenxiu Shi, Ravi Kamble, Nitin Singhal, Ching-Wei Wang, Shih-Chang Lo, José Ignacio Orlando, Hrvoje Bogunović, Xiulan Zhang, Yanwu Xu, iChallenge-AMD study group

The ADAM challenge consisted of four tasks which cover the main aspects of detecting and characterizing AMD from fundus images, including detection of AMD, detection and segmentation of optic disc, localization of fovea, and detection and segmentation of lesions.

Diagnostic

U-Net with spatial pyramid pooling for drusen segmentation in optical coherence tomography

no code implementations11 Dec 2019 Rhona Asgari, Sebastian Waldstein, Ferdinand Schlanitz, Magdalena Baratsits, Ursula Schmidt-Erfurth, Hrvoje Bogunović

In the second approach, the surrounding retinal layers (outer boundary retinal pigment epithelium (OBRPE) and Bruch's membrane (BM)) are segmented and the remaining space between these two layers is extracted as drusen.

Binary Classification Management +1

Modeling Disease Progression In Retinal OCTs With Longitudinal Self-Supervised Learning

no code implementations21 Oct 2019 Antoine Rivail, Ursula Schmidt-Erfurth, Wolf-Dieter Vogl, Sebastian M. Waldstein, Sophie Riedl, Christoph Grechenig, Zhichao Wu, Hrvoje Bogunović

Longitudinal imaging is capable of capturing the static ana\-to\-mi\-cal structures and the dynamic changes of the morphology resulting from aging or disease progression.

Self-Supervised Learning

An amplified-target loss approach for photoreceptor layer segmentation in pathological OCT scans

no code implementations2 Aug 2019 José Ignacio Orlando, Anna Breger, Hrvoje Bogunović, Sophie Riedl, Bianca S. Gerendas, Martin Ehler, Ursula Schmidt-Erfurth

Supervised deep learning models trained with standard loss functions are usually able to characterize only the most common disease appeareance from a training set, resulting in suboptimal performance and poor generalization when dealing with unseen lesions.

Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT

no code implementations29 May 2019 Philipp Seeböck, José Ignacio Orlando, Thomas Schlegl, Sebastian M. Waldstein, Hrvoje Bogunović, Sophie Klimscha, Georg Langs, Ursula Schmidt-Erfurth

We propose to take advantage of this property using bayesian deep learning, based on the assumption that epistemic uncertainties will correlate with anatomical deviations from a normal training set.

Anatomy Anomaly Detection

Using CycleGANs for effectively reducing image variability across OCT devices and improving retinal fluid segmentation

no code implementations24 Jan 2019 Philipp Seeböck, David Romo-Bucheli, Sebastian Waldstein, Hrvoje Bogunović, José Ignacio Orlando, Bianca S. Gerendas, Georg Langs, Ursula Schmidt-Erfurth

Among the several sources of variability the ML models have to deal with, a major factor is the acquisition device, which can limit the ML model's generalizability.

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