Portail HAL de Télécom Paris
Not a member yet
14191 research outputs found
Sort by
3D Imaging Contribution in Pediatric Surgical Oncology: A Multistakeholder Assessment Study
No full textInternational audienceIntroduction: Medical imaging is crucial for surgical planning, yet surgeons struggle with mental transformation of 2D images into 3D representations, particularly in complex pediatric pelvic anatomy. This study evaluated perceived benefits of 3D imaging with tractography compared to conventional 2D MRI in pediatric pelvic tumor surgery.Methods: A nationwide study assessed three groups: non-medical personnel (n=30), medical trainees (residents and fellows; primary analysis n=61, excluding 3 medical students), and senior pediatric surgeons (n=12). Using 3-Tesla MRI with specialized protocols including highresolution CoroT2cube and diffusion tensor imaging, participants evaluated five clinical cases in both 2D and 3D formats using 7-point Likert scales. Statistical analysis employed Wilcoxon paired tests with Bonferroni correction.Results: All groups showed significant improvements in perceived understanding with 3D imaging. Non-medical personnel scores increased from 4.24 (±0.69) to 6.27 (±0.28) (p<0.001), particularly in understanding disease and surgical objectives. Medical trainees improved from 5.08 (±0.61) to 6.42 (±0.49) (p<0.001), with enhanced understanding of surgical objectives and anatomical relationships. Senior surgeons' scores increased from 5.02 (±0.69) to 6.33 (±0.52) (p<0.001), showing significant improvements in preoperative planning and family communication. Effect sizes were substantial across groups (Cohen's d: 2.80, 1.90, and 1.52 respectively), though the within-subject design likely contributes to effect size inflation.Discussion: This study provides preliminary evidence for perceived 3D imaging value in pediatric pelvic tumor surgery. Improved anatomical comprehension among non-medical personnel may benefit informed consent, while enhanced visualization aids surgical education and planning. High surgeon acceptance (92%) suggests strong acceptability, though these exploratory findings require validation before implementation recommendations can be made.Prospective studies evaluating objective clinical outcomes, workflow integration and costeffectiveness require further study.</p
Statistical wave field theory: Anisotropic wave fields under Neumann's boundary condition
No full textInternational audienceThe statistical wave field theory mathematically establishes the statistical laws of the solutions to the wave equation in a bounded domain. It provides the closed-form expressions of the power distribution and the correlations of the wave field jointly over time, frequency, and space, which hold at high frequency and after many reflections, in terms of the geometry and the specific admittance of the boundary surface. This theory was originally developed in the particular case of mixing rooms, which are characterized by a diffuse wave field, based on the theory of dynamical billiards and on Weyl-like asymptotic laws. Then it was extended to the finite family of special polyhedra, where the wave field is anisotropic, based on a simpler geometric approach related to mathematical crystallography. In this paper, we introduce a unified version of the theory dedicated to a class of semi-mixing billiards. In the case of Neumann's boundary condition, we show that the wave field is stationary, but it is generally anisotropic. In particular, the correlation between two spatial positions at a given frequency is different from the well-known cardinal sine formula that characterizes diffuse acoustic fields
Unrolled Multiplicative Updates for Nonnegative Matrix Factorization applied to Hyperspectral Unmixing
No full textHyperSpectral Unmixing (HSU), the problem of separating mixed spectra of overlapping materials in a hyperspectral image, has motivated dedicated algorithmic developments in the last two decades. On the one hand, traditional model-based algorithms frequently guarantee interpretable results. On the other hand, deep-learning-based approaches are often faster at inference time and may obtain better empirical results. This work utilizes the strengths of both approaches by building on the deep unrolling paradigm. Our contribution is twofold. First, we propose two new algorithms based on deep unrolling of the well-known Multiplicative Updates. The first, coined Non-Adaptive Learned Multiplicative Updates (NALMU), adopts a simple element-wise multiplicative scheme. The second, called Recursive Adaptive Learned Multiplicative Updates (RALMU), has more flexible updates and better take into account the spatial correlations in the abundances. Second, we relate NALMU to the minimization of an explicit cost function under some assumptions. Such guarantees are unique in the HSU field. NALMU and RALMU are tested on astrophysics and remote sensing datasets. They outperform the other deep learning-based HSU algorithms and classical iterative schemes for the endmember estimates and obtain competitive results for the abundance estimates, even when trained in a self-supervised way. The code used in this paper will be made available upon publication
Bas les masques ! GAMM—Une Taxonomie des Mécanismes d'Attributs Manquants dans les Graphes
No full textInternational audienceExploring missing data in attributed graphs introduces unique challenges beyond those found in tabular datasets. In this work, we extend the taxonomy for missing data mechanisms to attributed graphs by proposing GAMM (Graph Attributes Missing Mechanisms), a framework that systematically links missingness probability to both node attributes and the underlying graph structure. Our taxonomy enriches the conventional definitions of masking mechanisms by introducing graph-specific dependencies. We empirically demonstrate that state-of-the-art imputation methods, while effective on traditional masks, significantly struggle when confronted with these more realistic graph-aware missingness scenarios
Los micro-trabajadores detrás de la inteligencia artificial: Explorando nuevos sujetos digitales y sus precariedades en el mundo laboral
No full textInternational audienceIn digital environments, value production involves not only computer developers and engineers, but a broader range of digital subjects – from users to data workers – whose contributions are often occluded from view. We break down their digital labour into its different forms: classification, monetisation and automation in the case of users; and preparation, verification and impersonation in the case of data workers. Far from a simple succession of predefined mechanical tasks, we show that all these forms of work are complex human activities that harness knowledge, skills, personal commitments, moral judgements, emotional elements and bodily dimensions. When we open the black box of AI, what emerges is a plurality of subjects who, through their digital interactions, reveal intimate aspects of their subjectivities and form an essential—though largely overlooked—part of the value chain that sustains this technology. Therefore, any critical reflection on the regulation of AI and its ethical and social implications must recognise the active role played by these digital subjects as co-producers of value and invisible protagonists of the ongoing technological transformation.En los entornos digitales, la producción de valor no solo involucra a desarrolladores e ingenieros informáticos, sino a una gama más amplia de sujetos digitales —desde usuarios hasta trabajadores de datos— cuyas contribuciones a menudo quedan ocultas a la vista. Descomponemos su trabajo digital en sus diferentes formas: clasificación, monetización y automatización en el caso de los usuarios; y preparación, verificación y suplantación en el caso de los trabajadores de datos. Lejos de ser una simple sucesión de tareas mecánicas predefinidas, demostramos que todas estas formas de trabajo son actividades humanas complejas que aprovechan conocimientos, habilidades, compromisos personales, juicios morales, elementos emocionales y dimensiones corporales. Al abrir la caja negra de la IA, lo que emerge es una pluralidad de sujetos que, a través de sus interacciones digitales, revelan aspectos íntimos de sus subjetividades y forman una parte esencial —aunque en gran medida ignorada— de la cadena de valor que sustenta esta tecnología. Por lo tanto, cualquier reflexión crítica sobre la regulación de la IA y sus implicaciones éticas y sociales debe reconocer el papel activo que desempeñan estos sujetos digitales como coproductores de valor y protagonistas invisibles de la transformación tecnológica
Random Stinespring superchannel: converting channel queries into dilation isometry queries
No full textThe recently introduced random purification channel, which converts copies of an arbitrary mixed quantum state into copies of the same uniformly random purification, has emerged as a powerful tool in quantum information theory. Motivated by this development, we introduce a channel-level analogue, which we call the random Stinespring superchannel. This consists in a procedure to transform parallel queries of an arbitrary quantum channel into parallel queries of the same uniformly random Stinespring isometry, via universal encoding and decoding operations that are efficiently implementable. When the channel is promised to have Choi rank at most , the procedure can be tailored to yield a Stinespring environment of dimension . As a consequence, quantum channel learning reduces to isometry learning, yielding a simple channel learning algorithm, based on existing isometry learning protocols, that matches the performance of the two recently proposed channel tomography algorithms. Complementarily, whereas the optimality of these algorithms had previously been established only up to a logarithmic factor in the dimension, we close this gap by removing this logarithmic factor from the lower bound. Taken together, our results fully establish the optimality of these recently introduced channel learning algorithms, showing that the optimal query complexity of learning a quantum channel with input dimension , output dimension , and Choi rank is
U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model
No full textInternational audienceThis paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually unsupervised, relying solely on reverberant signals and an acoustic model for training. Most of the existing deep learning approaches typically require paired dry and reverberant data, which are difficult to obtain in practice. We develop instead a sequential learning strategy motivated by a maximum-likelihood formulation of the dereverberation problem, wherein acoustic parameters and dry signals are estimated from reverberant inputs using deep neural networks, guided by a reverberation matching loss. Our most data-efficient variant requires only 100 reverberation-parameter-labeled samples to outperform an unsupervised baseline, demonstrating the effectiveness and practicality of the proposed method in low-resource scenarios
Analytical Logit Scaling for High-Resolution Sea Ice Topology Retrieval from Weakly Labeled SAR Imagery
No full textHigh-resolution sea ice mapping using Synthetic Aperture Radar (SAR) is crucial for Arctic navigation and climate monitoring. However, operational ice charts provide only coarse, region-level polygons (weak labels), forcing automated segmentation models to struggle with pixel-level accuracy and often yielding under-confident, blurred concentration maps. In this paper, we propose a weakly supervised deep learning pipeline that fuses Sentinel-1 SAR and AMSR-2 radiometry data using a U-Net architecture trained with a region-based loss. To overcome the severe under-confidence caused by weak labels, we introduce an Analytical Logit Scaling method applied post-inference. By dynamically calculating the temperature and bias based on the latent space percentiles (2% and 98%) of each scene, we force a physical binarization of the predictions. This adaptive scaling acts as a topological extractor, successfully revealing fine-grained sea ice fractures (leads) at a 40-meter resolution without requiring any manual pixel-level annotations. Our approach not only resolves local topology but also perfectly preserves regional macroscopic concentrations, achieving a 78% accuracy on highly fragmented summer scenes, thereby bridging the gap between weakly supervised learning and high-resolution physical segmentation
A posteriori closure of turbulence models: Are symmetries preserved?
No full textInternational audienceTurbulence modeling remains a longstanding challenge in fluid dynamics. Recent advances in data-driven methods have led to a surge of novel approaches aimed at addressing this problem. Thiswork builds upon our recent work [Phys. Rev. Fluids 10, 044602 (2025)], where we introduced anew closure for a shell model of turbulence using an a posteriori (or solver-in-the-loop) approach.Unlike most deep learning-based models, our method explicitly incorporates physical equationsinto the neural network framework, ensuring that the closure remains constrained by the underlyingphysics benefiting from enhanced stability and generalizability. In this paper, we further analyze thelearned closure, probing its capabilities and limitations. In particular, we look at joint probabilitydensity functions between resolved and unresolved variables, as well as the scale invariance ofmultipliers (ratios between adjacent shells) within the inertial range. Although our model excels inreproducing high-order statistical moments, it breaks this known symmetry near the cutoff, indicatinga fundamental limitation. We discuss the implications of these findings for subgrid-scale modeling in3D turbulence and outline directions for future research