arXiv subjects

Raphael Sznitman

Publications and source records attributed to Raphael Sznitman.

At least 55 records · Page 3Linked to original sources

arXiv2022

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

Modern sky surveys are producing ever larger amounts of observational data, which makes the application of classical approaches for the classification and analysis of objects challenging and time-consuming. However, this issue may be significantly mitigated by the application of automatic machine and deep learning methods. We propose ULISSE, a new deep learning tool that, starting from a single prototype object, is capable of identifying objects sharing the same morphological and photometric properties, and hence of creating a list of candidate sosia. 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. Intended for the initial exploration of large sky surveys, ULISSE directly uses features extracted from the ImageNet dataset to perform a similarity search. The method is capable of rapidly identifying a list of candidates, starting from only a single image of a given prototype, without the need for any time-consuming neural network training. Our experiments show ULISSE is able to identify AGN candidates based on a combination of host galaxy morphology, color and the presence of a central nuclear source, with a retrieval efficiency ranging from 21% to 65% (including composite sources) depending on the prototype, where the random guess baseline is 12%. We find ULISSE to be most effective in retrieving AGN in early-type host galaxies, as opposed to prototypes with spiral- or late-type properties. Based on the results described in this work, ULISSE can be a promising tool for selecting different types of astrophysical objects in current and future wide-field surveys (e.g. Euclid, LSST etc.) that target millions of sources every single night.

astro-ph.IM↗

arXiv2022

Data Invariants to Understand Unsupervised Out-of-Distribution Detection

Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due its importance in mission-critical systems and broader applicability over its supervised counterpart. Despite this increase in attention, U-OOD methods suffer from important shortcomings. By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most popular state-of-the-art methods are unable to consistently outperform a simple anomaly detector based on pre-trained features and the Mahalanobis distance (MahaAD). A key reason for the inconsistencies of these methods is the lack of a formal description of U-OOD. Motivated by a simple thought experiment, we propose a characterization of U-OOD based on the invariants of the training dataset. We show how this characterization is unknowingly embodied in the top-scoring MahaAD method, thereby explaining its quality. Furthermore, our approach can be used to interpret predictions of U-OOD detectors and provides insights into good practices for evaluating future U-OOD methods.

cs.CV↗

arXiv2022

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

Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction. However, the varying issues in segmenting the different relevant structures in these surgeries make the designation of a unique network quite challenging. This paper proposes a semantic segmentation network, termed DeepPyramid, that can deal with these challenges using three novelties: (1) a Pyramid View Fusion module which provides a varying-angle global view of the surrounding region centering at each pixel position in the input convolutional feature map; (2) a Deformable Pyramid Reception module which enables a wide deformable receptive field that can adapt to geometric transformations in the object of interest; and (3) a dedicated Pyramid Loss that adaptively supervises multi-scale semantic feature maps. Combined, we show that these modules can effectively boost semantic segmentation performance, especially in the case of transparency, deformability, scalability, and blunt edges in objects. We demonstrate that our approach performs at a state-of-the-art level and outperforms a number of existing methods with a large margin (3.66% overall improvement in intersection over union compared to the best rival approach).

cs.CV↗

arXiv2022

Consistency-preserving Visual Question Answering in Medical Imaging

Visual Question Answering (VQA) models take an image and a natural-language question as input and infer the answer to the question. Recently, VQA systems in medical imaging have gained popularity thanks to potential advantages such as patient engagement and second opinions for clinicians. While most research efforts have been focused on improving architectures and overcoming data-related limitations, answer consistency has been overlooked even though it plays a critical role in establishing trustworthy models. In this work, we propose a novel loss function and corresponding training procedure that allows the inclusion of relations between questions into the training process. Specifically, we consider the case where implications between perception and reasoning questions are known a-priori. To show the benefits of our approach, we evaluate it on the clinically relevant task of Diabetic Macular Edema (DME) staging from fundus imaging. Our experiments show that our method outperforms state-of-the-art baselines, not only by improving model consistency, but also in terms of overall model accuracy. Our code and data are available at https://github.com/sergiotasconmorales/consistency_vqa.

cs.CV↗

arXiv2021

Surgical Data Science -- from Concepts toward Clinical Translation

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.

cs.CY↗

arXiv2021

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

The ability to quickly annotate medical imaging data plays a critical role in training deep learning frameworks for segmentation. Doing so for image volumes or video sequences is even more pressing as annotating these is particularly burdensome. To alleviate this problem, this work proposes a new method to efficiently segment medical imaging volumes or videos using point-wise annotations only. This allows annotations to be collected extremely quickly and remains applicable to numerous segmentation tasks. Our approach trains a deep learning model using an appropriate Positive/Unlabeled objective function using sparse point-wise annotations. 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. Our method iteratively estimates appropriate class priors and yields high segmentation quality for a variety of object types and imaging modalities. In addition, by leveraging a spatio-temporal tracking framework, we regularize our predictions by leveraging the complete data volume. We show experimentally that our approach outperforms state-of-the-art methods tailored to the same problem.

cs.CV↗

arXiv2021

CataNet: Predicting remaining cataract surgery duration

Cataract surgery is a sight saving surgery that is performed over 10 million times each year around the world. With such a large demand, the ability to organize surgical wards and operating rooms efficiently is critical to delivery this therapy in routine clinical care. In this context, estimating the remaining surgical duration (RSD) during procedures is one way to help streamline patient throughput and workflows. To this end, we propose CataNet, a method for cataract surgeries that predicts in real time the RSD jointly with two influential elements: the surgeon's experience, and the current phase of the surgery. We compare CataNet to state-of-the-art RSD estimation methods, showing that it outperforms them even when phase and experience are not considered. We investigate this improvement and show that a significant contributor is the way we integrate the elapsed time into CataNet's feature extractor.

eess.IV↗

arXiv2021

Stereo Correspondence and Reconstruction of Endoscopic Data Challenge

The stereo correspondence and reconstruction of endoscopic data sub-challenge was organized during the Endovis challenge at MICCAI 2019 in Shenzhen, China. The task was to perform dense depth estimation using 7 training datasets and 2 test sets of structured light data captured using porcine cadavers. These were provided by a team at Intuitive Surgical. 10 teams participated in the challenge day. This paper contains 3 additional methods which were submitted after the challenge finished as well as a supplemental section from these teams on issues they found with the dataset.

cs.CV↗

arXiv2020

Information content of JWST-NIRSPEC transmission spectra of warm Neptunes

Warm Neptunes offer a rich opportunity for understanding exo-atmospheric chemistry. With the upcoming James Webb Space Telescope (JWST), there is a need to elucidate the balance between investments in telescope time versus scientific yield. We use the supervised machine learning method of the random forest to perform an information content analysis on a 11-parameter model of transmission spectra from the various NIRSpec modes. The three bluest medium-resolution NIRSpec modes (0.7 - 1.27 microns, 0.97 - 1.84 microns, 1.66 - 3.07 microns) are insensitive to the presence of CO. The reddest medium-resolution mode (2.87 - 5.10 microns) is sensitive to all of the molecules assumed in our model: CO, CO2, CH4, C2H2, H2O, HCN and NH3. It competes effectively with the three bluest modes on the information encoded on cloud abundance and particle size. It is also competitive with the low-resolution prism mode (0.6 - 5.3 microns) on the inference of every parameter except for the temperature and ammonia abundance. We recommend astronomers to use the reddest medium-resolution NIRSpec mode for studying the atmospheric chemistry of 800-1200 K warm Neptunes; its corresponding high-resolution counterpart offers diminishing returns. We compare our findings to previous JWST information content analyses that favor the blue orders, and suggest that the reliance on chemical equilibrium could lead to biased outcomes if this assumption does not apply. A simple, pressure-independent diagnostic for identifying chemical disequilibrium is proposed based on measuring the abundances of H2O, CO and CO2.

astro-ph.EP↗

arXiv2020

Concept-Centric Visual Turing Tests for Method Validation

Recent advances in machine learning for medical imaging have led to impressive increases in model complexity and overall capabilities. However, the ability to discern the precise information a machine learning method is using to make decisions has lagged behind and it is often unclear how these performances are in fact achieved. Conventional evaluation metrics that reduce method performance to a single number or a curve only provide limited insights. Yet, systems used in clinical practice demand thorough validation that such crude characterizations miss. To this end, we present a framework to evaluate classification methods based on a number of interpretable concepts that are crucial for a clinical task. Our approach is inspired by the Turing Test concept and how to devise a test that adaptively questions a method for its ability to interpret medical images. 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. The results show that the probabilistic model is able to expose both the dataset's and the method's biases, and can be used to reduced the number of queries needed for confident performance evaluation.

cs.LG↗

arXiv2020

A Question-Centric Model for Visual Question Answering in Medical Imaging

Deep learning methods have proven extremely effective at performing a variety of medical image analysis tasks. With their potential use in clinical routine, their lack of transparency has however been one of their few weak points, raising concerns regarding their behavior and failure modes. While most research to infer model behavior has focused on indirect strategies that estimate prediction uncertainties and visualize model support in the input image space, the ability to explicitly query a prediction model regarding its image content offers a more direct way to determine the behavior of trained models. To this end, we present a novel Visual Question Answering approach that allows an image to be queried by means of a written question. Experiments on a variety of medical and natural image datasets show that by fusing image and question features in a novel way, the proposed approach achieves an equal or higher accuracy compared to current methods.

cs.CV↗

arXiv2020

Interpreting High-Resolution Spectroscopy of Exoplanets Using Cross-Correlations and Supervised Machine Learning

We present a new method for performing atmospheric retrieval on ground-based, high-resolution data of exoplanets. Our method combines cross-correlation functions with a random forest, a supervised machine learning technique, to overcome challenges associated with high-resolution data. A series of cross-correlation functions are concatenated to give a "CCF-sequence" for each model atmosphere, which reduces the dimensionality by a factor of ~100. The random forest, trained on our grid of ~65,000 models, provides a likelihood-free method of retrieval. The pre-computed grid spans 31 values of both temperature and metallicity, and incorporates a realistic noise model. We apply our method to HARPS-N observations of the ultra-hot Jupiter KELT-9b, and obtain a metallicity consistent with solar (logM = $-0.2\pm0.2$). Our retrieved transit chord temperature (T = $6000^{+0}_{-200}$K) is unreliable as the ion cross-correlations lie outside of the training set, which we interpret as being indicative of missing physics in our atmospheric model. We compare our method to traditional nested-sampling, as well as other machine learning techniques, such as Bayesian neural networks. We demonstrate that the likelihood-free aspect of the random forest makes it more robust than nested-sampling to different error distributions, and that the Bayesian neural network we tested is unable to reproduce complex posteriors. We also address the claim in Cobb et al. (2019) that our random forest retrieval technique can be over-confident but incorrect. We show that this is an artefact of the training set, rather than the machine learning method, and that the posteriors agree with those obtained using nested-sampling.

astro-ph.EP↗

arXiv2019

Supervised Machine Learning for Intercomparison of Model Grids of Brown Dwarfs: Application to GJ 570D and the Epsilon Indi B Binary System

Self-consistent model grids of brown dwarfs involve complex physics and chemistry, and are often computed using proprietary computer codes, making it challenging to identify the reasons for discrepancies between model and data as well as between the models produced by different research groups. In the current study, we demonstrate a novel method for analyzing brown dwarf spectra, which combines the use of the Sonora, AMES-Cond and HELIOS model grids with the supervised machine learning method of the random forest. Besides performing atmospheric retrieval, the random forest enables information content analysis of the three model grids as a natural outcome of the method, both individually on each grid and by comparing the grids against one another, via computing large suites of mock retrievals. Our analysis reveals that the different choices made in modelling the alkali line shapes hinder the use of the alkali lines as gravity indicators. Nevertheless, the spectrum longward of 1.2 micron encodes enough information on the surface gravity to allow its inference from retrieval. Temperature may be accurately and precisely inferred independent of the choice of model grid, but not the surface gravity. We apply random forest retrieval to three objects: the benchmark T7.5 brown dwarf GJ 570D; and Epsilon Indi Ba (T1.5 brown dwarf) and Bb (T6 brown dwarf), which are part of a binary system and have measured dynamical masses. For GJ 570D, the inferred effective temperature and surface gravity are consistent with previous studies. For Epsilon Indi Ba and Bb, the inferred surface gravities are broadly consistent with the values informed by the dynamical masses.

astro-ph.SR↗

arXiv2019

Fused Detection of Retinal Biomarkers in OCT Volumes

Optical Coherence Tomography (OCT) is the primary imaging modality for detecting pathological biomarkers associated to retinal diseases such as Age-Related Macular Degeneration. In practice, clinical diagnosis and treatment strategies are closely linked to biomarkers visible in OCT volumes and the ability to identify these plays an important role in the development of ophthalmic pharmaceutical products. 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. We do so by adding a bidirectional LSTM to fuse the outputs of a Convolutional Neural Network that predicts individual biomarkers. We thus avoid the need to use pixel-wise annotations to train our method, and instead provide fine-grained biomarker information regardless. On a dataset of 416 volumes, we show that our approach imposes coherence between biomarker predictions across volume slices and our predictions are superior to several existing approaches.

cs.CV↗

arXiv2019

Deep Multi Label Classification in Affine Subspaces

Multi-label classification (MLC) problems are becoming increasingly popular in the context of medical imaging. This has in part been driven by the fact that acquiring annotations for MLC is far less burdensome than for semantic segmentation and yet provides more expressiveness than multi-class classification. However, to train MLCs, most methods have resorted to similar objective functions as with traditional multi-class classification settings. We show in this work that such approaches are not optimal and instead propose a novel deep MLC classification method in affine subspace. At its core, the method attempts to pull features of class-labels towards different affine subspaces while maximizing the distance between them. We evaluate the method using two MLC medical imaging datasets and show a large performance increase compared to previous multi-label frameworks. This method can be seen as a plug-in replacement loss function and is trainable in an end-to-end fashion.

cs.CV↗

arXiv2019

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

We propose an active learning approach to image segmentation that exploits geometric priors to speed up and streamline the annotation process. It can be applied for both background-foreground and multi-class segmentation tasks in 2D images and 3D image volumes. 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. For multi-class settings, we additionally introduce two novel criteria for uncertainty. In the 3D case, we use the resulting uncertainty measure to select voxels lying on a planar patch, which makes batch annotation much more convenient for the end user compared to the setting where voxels are randomly distributed in a volume. The planar patch is found using a branch-and-bound algorithm that looks for a 2D patch in a 3D volume where the most informative instances are located. We evaluate our approach on Electron Microscopy and Magnetic Resonance image volumes, as well as on regular images of horses and faces. We demonstrate a substantial performance increase over other approaches thanks to the use of geometric priors.

cs.CV↗

arXiv2019

Discovering General-Purpose Active Learning Strategies

We propose a general-purpose approach to discovering active learning (AL) strategies from data. These strategies are transferable from one domain to another and can be used in conjunction with many machine learning models. To this end, we formalize the annotation process as a Markov decision process, design universal state and action spaces and introduce a new reward function that precisely model the AL objective of minimizing the annotation cost. We seek to find an optimal (non-myopic) AL strategy using reinforcement learning. We evaluate the learned strategies on multiple unrelated domains and show that they consistently outperform state-of-the-art baselines.

cs.LG↗

arXiv2018

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

Recent machine learning strategies for segmentation tasks have shown great ability when trained on large pixel-wise annotated image datasets. It remains a major challenge however to aggregate such datasets, as the time and monetary cost associated with collecting extensive annotations is extremely high. This is particularly the case for generating precise pixel-wise annotations in video and volumetric image data. To this end, this work presents a novel framework to produce pixel-wise segmentations using minimal supervision. Our method relies on 2D point supervision, whereby a single 2D location within an object of interest is provided on each image of the data. Our method then estimates the object appearance in a semi-supervised fashion by learning object-image-specific features and by using these in a semi-supervised learning framework. 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. In practice, we solve this optimally as a tracking problem using a K-shortest path approach. Both the object model and segmentation are then refined iteratively to further improve the final segmentation. We show that by collecting 2D locations using a gaze tracker, our approach can provide state-of-the-art segmentations on a range of objects and image modalities (video and 3D volumes), and that these can then be used to train supervised machine learning classifiers.

cs.CV↗