Search Results for author: Raphael Sznitman

Found 47 papers, 20 papers with code

Continual Unsupervised Out-of-Distribution Detection

no code implementations4 Jun 2024 Lars Doorenbos, Raphael Sznitman, Pablo Márquez-Neila

To tackle this new setting, we propose a method that starts from a U-OOD detector, which is agnostic to the OOD distribution, and slowly updates during deployment to account for the actual OOD distribution.

Out-of-Distribution Detection

Masked Image Modelling for retinal OCT understanding

no code implementations23 May 2024 Theodoros Pissas, Pablo Márquez-Neila, Sebastian Wolf, Martin Zinkernagel, Raphael Sznitman

To this end, we leverage Masked Autoencoders (MAE), a simple and scalable method for self-supervised learning, to obtain a powerful and general representation for OCT images by training on 700K OCT images from 41K patients collected under real world clinical settings.

Self-Supervised Learning

Cataract-1K: Cataract Surgery Dataset for Scene Segmentation, Phase Recognition, and Irregularity Detection

no code implementations11 Dec 2023 Negin Ghamsarian, Yosuf El-Shabrawi, Sahar Nasirihaghighi, Doris Putzgruber-Adamitsch, Martin Zinkernagel, Sebastian Wolf, Klaus Schoeffmann, Raphael Sznitman

Besides, we initiate the research on domain adaptation for instrument segmentation in cataract surgery by evaluating cross-domain instrument segmentation performance in cataract surgery videos.

Benchmarking Domain Adaptation +4

Predicting Postoperative Intraocular Lens Dislocation in Cataract Surgery via Deep Learning

no code implementations6 Dec 2023 Negin Ghamsarian, Doris Putzgruber-Adamitsch, Stephanie Sarny, Raphael Sznitman, Klaus Schoeffmann, Yosuf El-Shabrawi

The Pearson correlation and t-test results reveal significant correlations between lens unfolding delay and lens rotation and significant differences between the intra-operative rotations stability of four groups of lenses.

Correlation-aware active learning for surgery video segmentation

no code implementations15 Nov 2023 Fei Wu, Pablo Marquez-Neila, Mingyi Zheng, Hedyeh Rafii-Tari, Raphael Sznitman

Active Learning (AL) is a popular approach that can help to reduce this burden by iteratively selecting images for annotation to improve the model performance.

Active Learning Contrastive Learning +4

Learning Super-Resolution Ultrasound Localization Microscopy from Radio-Frequency Data

no code implementations7 Nov 2023 Christopher Hahne, Georges Chabouh, Olivier Couture, Raphael Sznitman

Ultrasound Localization Microscopy (ULM) enables imaging of vascular structures in the micrometer range by accumulating contrast agent particle locations over time.


RF-ULM: Ultrasound Localization Microscopy Learned from Radio-Frequency Wavefronts

1 code implementation2 Oct 2023 Christopher Hahne, Georges Chabouh, Arthur Chavignon, Olivier Couture, Raphael Sznitman

However, our study uncovers an enormous potential: The process of delay-and-sum beamforming leads to an irreversible reduction of Radio-Frequency (RF) channel data, while its implications for localization remain largely unexplored.


Hyperbolic Random Forests

1 code implementation25 Aug 2023 Lars Doorenbos, Pablo Márquez-Neila, Raphael Sznitman, Pascal Mettes

To make hyperbolic random forests work on multi-class data and imbalanced experiments, we furthermore outline a new method for combining classes based on their lowest common ancestor and a class-balanced version of the large-margin loss.

StofNet: Super-resolution Time of Flight Network

1 code implementation23 Aug 2023 Christopher Hahne, Michel Hayoz, Raphael Sznitman

Time of Flight (ToF) is a prevalent depth sensing technology in the fields of robotics, medical imaging, and non-destructive testing.


Domain Adaptation for Medical Image Segmentation using Transformation-Invariant Self-Training

1 code implementation31 Jul 2023 Negin Ghamsarian, Javier Gamazo Tejero, Pablo Márquez Neila, Sebastian Wolf, Martin Zinkernagel, Klaus Schoeffmann, Raphael Sznitman

However, the unreliability of pseudo labels can hinder the capability of self-training techniques to induce abstract representation from the unlabeled target dataset, especially in the case of large distribution gaps.

Domain Adaptation Image Segmentation +3

A reinforcement learning approach for VQA validation: an application to diabetic macular edema grading

no code implementations19 Jul 2023 Tatiana Fountoukidou, Raphael Sznitman

As such, validation of machine learning models represents an important aspect and yet, most methods are only validated in a limited way.

Question Answering Reinforcement Learning (RL) +1

Geometric Ultrasound Localization Microscopy

no code implementations27 Jun 2023 Christopher Hahne, Raphael Sznitman

Contrast-Enhanced Ultra-Sound (CEUS) has become a viable method for non-invasive, dynamic visualization in medical diagnostics, yet Ultrasound Localization Microscopy (ULM) has enabled a revolutionary breakthrough by offering ten times higher resolution.

Learning How To Robustly Estimate Camera Pose in Endoscopic Videos

2 code implementations17 Apr 2023 Michel Hayoz, Christopher Hahne, Mathias Gallardo, Daniel Candinas, Thomas Kurmann, Maximilian Allan, Raphael Sznitman

Purpose: Surgical scene understanding plays a critical role in the technology stack of tomorrow's intervention-assisting systems in endoscopic surgeries.

3D Reconstruction Optical Flow Estimation +3

Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery

1 code implementation11 Apr 2023 Alain Jungo, Lars Doorenbos, Tommaso Da Col, Maarten Beelen, Martin Zinkernagel, Pablo Márquez-Neila, Raphael Sznitman

Detecting so-called out-of-distribution (OoD) samples is crucial in safety-critical applications such as robotically guided retinal microsurgery, where distances between the instrument and the retina are derived from sequences of 1D images that are acquired by an instrument-integrated optical coherence tomography (iiOCT) probe.

Out-of-Distribution Detection

Full or Weak annotations? An adaptive strategy for budget-constrained annotation campaigns

no code implementations CVPR 2023 Javier Gamazo Tejero, Martin S. Zinkernagel, Sebastian Wolf, Raphael Sznitman, Pablo Márquez Neila

However, for any new domain application looking to use weak supervision, the dataset builder still needs to define a strategy to distribute full segmentation and other weak annotations.

Segmentation Transfer Learning

Logical Implications for Visual Question Answering Consistency

1 code implementation CVPR 2023 Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman

Despite considerable recent progress in Visual Question Answering (VQA) models, inconsistent or contradictory answers continue to cast doubt on their true reasoning capabilities.

Language Modelling Question Answering +1

Stochastic Segmentation with Conditional Categorical Diffusion Models

1 code implementation ICCV 2023 Lukas Zbinden, Lars Doorenbos, Theodoros Pissas, Adrian Thomas Huber, Raphael Sznitman, Pablo Márquez-Neila

Semantic segmentation has made significant progress in recent years thanks to deep neural networks, but the common objective of generating a single segmentation output that accurately matches the image's content may not be suitable for safety-critical domains such as medical diagnostics and autonomous driving.

Autonomous Driving Denoising +2

ULISSE: A Tool for One-shot Sky Exploration and its Application to Active Galactic Nuclei Detection

1 code implementation23 Aug 2022 Lars Doorenbos, Olena Torbaniuk, Stefano Cavuoti, Maurizio Paolillo, Giuseppe Longo, Massimo Brescia, Raphael Sznitman, Pablo Márquez-Neila

In this work, we focus on applying our method to the detection of AGN candidates in a Sloan Digital Sky Survey galaxy sample, since the identification and classification of Active Galactic Nuclei (AGN) in the optical band still remains a challenging task in extragalactic astronomy.

Astronomy Retrieval

DeepPyramid: Enabling Pyramid View and Deformable Pyramid Reception for Semantic Segmentation in Cataract Surgery Videos

1 code implementation4 Jul 2022 Negin Ghamsarian, Mario Taschwer, Raphael Sznitman, Klaus Schoeffmann

Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction.

Segmentation Semantic Segmentation

Consistency-preserving Visual Question Answering in Medical Imaging

1 code implementation27 Jun 2022 Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman

Visual Question Answering (VQA) models take an image and a natural-language question as input and infer the answer to the question.

Question Answering Visual Question Answering

Data Invariants to Understand Unsupervised Out-of-Distribution Detection

no code implementations26 Nov 2021 Lars Doorenbos, Raphael Sznitman, Pablo Márquez-Neila

Motivated by a simple thought experiment, we propose a characterization of U-OOD based on the invariants of the training dataset.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

A Positive/Unlabeled Approach for the Segmentation of Medical Sequences using Point-Wise Supervision

1 code implementation18 Jul 2021 Laurent Lejeune, Raphael Sznitman

While most methods of this kind assume that the proportion of positive samples in the data is known a-priori, we introduce a novel self-supervised method to estimate this prior efficiently by combining a Bayesian estimation framework and new stopping criteria.


CataNet: Predicting remaining cataract surgery duration

1 code implementation21 Jun 2021 Andrés Marafioti, Michel Hayoz, Mathias Gallardo, Pablo Márquez Neila, Sebastian Wolf, Martin Zinkernagel, Raphael Sznitman

Cataract surgery is a sight saving surgery that is performed over 10 million times each year around the world.

Volumetric Quantitative Ablation Margins for Assessment of Ablation Completeness in Thermal Ablation of Liver Tumors

1 code implementation Frontiers in Oncology, Cancer Imaging and Image-directed interventions 2021 Raluca-Maria Sandu, Iwan Polucci, Simeon J. S. Ruiter, Raphael Sznitman, Koert P. de Jong, Jacob Freedman, Stefan Weber and Pascale Tinguely

For subcapsular tumors, the underestimation of tumor coverage by the ablation volume when applying an unadjusted QAM method was confirmed, supporting the benefits of using the proposed algorithm for QAM computation in these cases.

Decision Making

Fused Detection of Retinal Biomarkers in OCT Volumes

no code implementations16 Jul 2019 Thomas Kurmann, Pablo Márquez-Neila, Siqing Yu, Marion Munk, Sebastian Wolf, Raphael Sznitman

In this context, we present a method that automatically predicts the presence of biomarkers in OCT cross-sections by incorporating information from the entire volume.

Concept-Centric Visual Turing Tests for Method Validation

no code implementations15 Jul 2019 Tatiana Fountoukidou, Raphael Sznitman

To do this, we make use of a Twenty Questions paradigm whereby we use a probabilistic model to characterize the method's capacity to grasp task-specific concepts, and we introduce a strategy to sequentially query the method according to its previous answers.

BIG-bench Machine Learning

Deep Multi Label Classification in Affine Subspaces

no code implementations10 Jul 2019 Thomas Kurmann, Pablo Marquez Neila, Sebastian Wolf, Raphael Sznitman

We evaluate the method using two MLC medical imaging datasets and show a large performance increase compared to previous multi-label frameworks.

Classification General Classification +3

Iterative multi-path tracking for video and volume segmentation with sparse point supervision

no code implementations27 Aug 2018 Laurent Lejeune, Jan Grossrieder, Raphael Sznitman

Our object model is then used in a graph-based optimization problem that takes into account all provided locations and the image data in order to infer the complete pixel-wise segmentation.

BIG-bench Machine Learning Object +1

Supervised Machine Learning for Analysing Spectra of Exoplanetary Atmospheres

1 code implementation11 Jun 2018 Pablo Marquez-Neila, Chloe Fisher, Raphael Sznitman, Kevin Heng

Machine learning has previously been used to determine which molecules to include in the model, but the retrieval itself was still performed using standard methods.

Earth and Planetary Astrophysics Atmospheric and Oceanic Physics Data Analysis, Statistics and Probability

Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery

1 code implementation18 Oct 2017 Thomas Kurmann, Pablo Marquez Neila, Xiaofei Du, Pascal Fua, Danail Stoyanov, Sebastian Wolf, Raphael Sznitman

An additional advantage of our approach is that instrument detection at test time is achieved while avoiding the need for scale-dependent sliding window evaluation.

Pose Estimation

Expected exponential loss for gaze-based video and volume ground truth annotation

no code implementations16 Jul 2017 Laurent Lejeune, Mario Christoudias, Raphael Sznitman

Many recent machine learning approaches used in medical imaging are highly reliant on large amounts of image and ground truth data.

Object Semantic Segmentation

Pathological OCT Retinal Layer Segmentation using Branch Residual U-shape Networks

no code implementations16 Jul 2017 Stefanos Apostolopoulos, Sandro De Zanet, Carlos Ciller, Sebastian Wolf, Raphael Sznitman

The automatic segmentation of retinal layer structures enables clinically-relevant quantification and monitoring of eye disorders over time in OCT imaging.

RetiNet: Automatic AMD identification in OCT volumetric data

no code implementations12 Oct 2016 Stefanos Apostolopoulos, Carlos Ciller, Sandro I. De Zanet, Sebastian Wolf, Raphael Sznitman

In much the same way, acquiring ground truth information for each cross-section is expensive and time consuming.

Geometry in Active Learning for Binary and Multi-class Image Segmentation

no code implementations29 Jun 2016 Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

Our approach combines geometric smoothness priors in the image space with more traditional uncertainty measures to estimate which pixels or voxels are the most informative, and thus should to be annotated next.

Active Learning Image Segmentation +1

Active Learning for Delineation of Curvilinear Structures

no code implementations CVPR 2016 Agata Mosinska, Raphael Sznitman, Przemysław Głowacki, Pascal Fua

Many recent delineation techniques owe much of their increased effectiveness to path classification algorithms that make it possible to distinguish promising paths from others.

Active Learning General Classification

Introducing Geometry in Active Learning for Image Segmentation

no code implementations ICCV 2015 Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes.

Active Learning Image Segmentation +1

Reconstructing Evolving Tree Structures in Time Lapse Sequences

no code implementations CVPR 2014 Przemyslaw Glowacki, Miguel Amavel Pinheiro, Engin Turetken, Raphael Sznitman, Daniel Lebrecht, Jan Kybic, Anthony Holtmaat, Pascal Fua

We propose an approach to reconstructing tree structures that evolve over time in 2D images and 3D image stacks such as neuronal axons or plant branches.

Active Testing for Face Detection and Localization

no code implementations27 Mar 2010 Raphael Sznitman, Bruno Jedynak

We provide a novel search technique, which uses a hierarchical model and a mutual information gain heuristic to efficiently prune the search space when localizing faces in images.

Face Detection

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