JBJules Bonnard

Jules Bonnard

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jules Bonnard has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Machine learning for fetal ultrasound image analysis using privileged information

    by Jules Bonnard

    Machine learning pour l'analyse d'échographies fœtales avec l'utilisation d'information privilégiée: L'obstétrique et la gynécologie (OB/GYN) sont des domaines de la médecine qui se spécialisent dans les soins aux femmes pendant la grossesse et l'accouchement, ainsi que dans le diagnostic des maladies du système reproducteur féminin. La numérisation par ultrasons est devenue cruciale en obstétrique et gynécologie afin de mieux traiter les anomalies congénitales et les grossesses ectopiques, par exemple. Cependant, cette tâche est complexe en raison de nombreuses maladies rares et d'un nombre encore plus important de signes. Ma thèse fait partie du projet européen SUOG (Smart Ultrasound for Obstetrics and Gynecology), qui vise à construire un appareil à ultrasons intelligent pour aider l'échographiste en temps réel à identifier la prochaine acquisition échographique pertinente ou à poser le bon diagnostic. Dans ce sens, deux tâches ont été identifiées : la reconnaissance du plan de coupe et la similarité d'image. Pour traiter ces tâches, l'ontologie SUOG a été établie par des experts de 9 centres de médecine fœtale en Europe, avec des milliers de nœuds. Quelques milliers d'images ont été richement annotées avec des étiquettes extraites de l'ontologie susmentionnée, et 294 images ont été segmentées en 10 zones qui ne se chevauchent pas. Des tâches telles que la reconnaissance du plan de coupe ou la similarité d'image pour l'imagerie médicale ont déjà été traitées avec des techniques de vision par ordinateur avec un succès relatif. Nous décidons donc de résoudre ces problèmes en utilisant des approches basées sur l'apprentissage profond. Cependant, la plupart de ces méthodes reposent sur de grands ensembles de données annotées. Nous avons donc l'intention d'intégrer les données supplémentaires (cartes de segmentation et annotations structurées riches) pour améliorer les capacités prédictives du réseau. Tout d'abord, nous introduisons la Prior-Guided Attribution (PGA), une méthode qui exploite les informations spatiales pour guider le réseau vers les zones les plus importantes de l'image d'entrée. Pour ce faire, nous contraignons l'attribution du réseau vers des cartes de chaleur d'informations spatiales soigneusement choisies. Nous démontrons que cette méthode fonctionne bien sur plusieurs tâches OB/GYN et une tâche d'analyse faciale. Deuxièmement, nous intégrons les annotations hiérarchiques structurées pour améliorer la disposition du modèle à coder des relations sémantiques riches. Nous introduisons la Semantic Abstraction Loss (SAL), conçue pour pousser les méta-représentations à encoder les informations des annotations de niveau supérieur. Nous proposons également d'intégrer les informations sémantiques extraites des annotations hiérarchiques sous forme de langage naturel. Pour ce faire, nous utilisons un guidage par le langage avec des légendes riches, et introduisons par ailleurs un Ontology Language Guidance (OLG), visant à guider les méta-représentations susmentionnées pour mieux représenter les distances inter-classes. Les expériences sur un jeu de données de classification d'oiseaux et le jeu de données de reconnaissance du plan de coupe SUOG ont montré que les méthodes proposées présentent donc un intérêt pour les tâches d'imagerie OB/GYN afin d'intégrer des informations sémantiques fortes grâce à des annotations hiérarchiques. Cependant, elles n'offrent une amélioration conséquente que lorsque le modèle de langage est capable de fournir un contexte sémantique dans le domaine d'entrée spécifique.

  • Ontology-Guided Deep Metric Learning and Applications to Obstetrics

    by Jules Bonnard, Arnaud Dapogny, Ferdinand Dhombres, Kévin Bailly

  • Prior-Guided Attribution of Deep Neural Networks for Obstetrics and Gynecology

    by Jules Bonnard, Arnaud Dapogny, Richard Zsamboki, Lucrezia De Braud, Davor Jurkovic, Kévin Bailly, Ferdinand Dhombres

    Obstetrics and gynecology (OB/GYN) are areas of medicine that specialize in the care of women during pregnancy and childbirth and in the diagnosis of diseases of the female reproductive system. Ultrasound scanning has become ubiquitous in these branches of medicine, as breast or fetal ultrasound images can lead the sonographer and guide him through his diagnosis. However, ultrasound scan images require a lot of resources to annotate and are often unavailable for training purposes because of confidentiality reasons, which explains why deep learning methods are still not as commonly used to solve OB/GYN tasks as in other computer vision tasks. In order to tackle this lack of data for training deep neural networks in this context, we propose Prior-Guided Attribution (PGA), a novel method that takes advantage of prior spatial information during training by guiding part of its attribution towards these salient areas. Furthermore, we introduce a novel prior allocation strategy method to take into account several spatial priors at the same time while providing the model enough degrees of liberty to learn relevant features by itself. The proposed method only uses the additional information during training, without needing it during inference. After validating the different elements of the method as well as its genericity on a facial analysis problem, we demonstrate that the proposed PGA method constantly outperforms existing baselines on two ultrasound imaging OB/GYN tasks: breast cancer detection and scan plane detection with segmentation prior maps.


  • Open Access

    RULe: Relocalization-Uniformization-Landmark Estimation Network for Real-Time Face Alignment in Degraded Conditions

    by Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kevin Bailly

    Face alignment refers to the process of estimating the position of a number of salient landmarks on face images or videos, such as mouth and eye corners, nose tip, etc. With the availability of large annotated databases and the rise of deep learning-based methods, face alignment as a domain has matured to a point where it can be applied in more or less unconstrained conditions, e.g. non-frontal head poses, presence of heavy make-up or partial occlusions. However, when considering real-case alignment on videos with possibly low frame rates, we need to make sure that the algorithms are robust to jittering of the face bounding box localization, low-resolution of the face crops, possible bad environmental lighting, brightness, and presence of noise. To tackle these issues, we propose RULe, a three-staged Relocalization-Uniformization-Landmark Estimation network. In the first stage, an initial loosely localized bounding box gets refined to output a well centered face crop, thus reducing the variability of the images prior to passing them to the subsequent stage. Then, in the second stage, the face style is uniformized (using adversarial learning as well as perceptual losses) to correct low resolution or variations of brightness/contrast. Finally, the third stage outputs a precise landmark estimation given such enhanced face crop using a cascaded compact model trained using hint-based knowledge distillation. We show through a variety of experiments that RULe achieves real-time face alignment with state-of-the-art precision in heavily degraded conditions.

  • Open Access

    Adversarial Deep Multi-Task Learning Using Semantically Orthogonal Spaces and Application to Facial Attributes Prediction

    by Arnaud Dapogny, Gauthier Tallec, Jules Bonnard, Edouard Yvinec, Kevin Bailly

    Deep learning-based multi-task approaches usually rely on factorizing representation layers up to a certain point, where the network splits into several heads, each one addressing a specific task. Depending on the inter-task correlation, such naive model may or may not allow the tasks to benefit from each others. In this paper, we propose a novel Semantic Orthogonality Spaces (SOS) method for multi-task problems, where each task is predicted using the information from a common subspace that factorizes information among all tasks, as well as a task-specific subspace. We enforce orthogonality between these tasks by applying soft orthogonality constraints, as well as adversarially-learned semantic orthogonality objectives that ensures that predicting one task requires the specific information related to that task. We demonstrate the effectiveness of SOS on synthetic data, as well as for large-scale facial attributes prediction. In particular, we use SOS to craft a lightweight architecture that provides high-end accuracies on CelebA database.

  • Open Access

    Multi-Task Transformer with uncertainty modelling for Face Based Affective Computing

    by Gauthier Tallec, Jules Bonnard, Arnaud Dapogny, Kévin Bailly

    Face based affective computing consists in detecting emotions from face images. It is useful to unlock better automatic comprehension of human behaviours and could pave the way toward improved human-machines interactions. However it comes with the challenging task of designing a computational representation of emotions. So far, emotions have been represented either continuously in the 2D Valence/Arousal space or in a discrete manner with Ekman's 7 basic emotions. Alternatively, Ekman's Facial Action Unit (AU) system have also been used to caracterize emotions using a codebook of unitary muscular activations. ABAW3 and ABAW4 Multi-Task Challenges are the first work to provide a large scale database annotated with those three types of labels. In this paper we present a transformer based multi-task method for jointly learning to predict valence arousal, action units and basic emotions. From an architectural standpoint our method uses a taskwise token approach to efficiently model the similarities between the tasks. From a learning point of view we use an uncertainty weighted loss for modelling the difference of stochasticity between the three tasks annotations.

  • Open Access

    Privileged Attribution Constrained Deep Networks for Facial Expression Recognition

    by Jules Bonnard, Arnaud Dapogny, Ferdinand Dhombres, Kévin Bailly

    Facial Expression Recognition (FER) is crucial in many research domains because it enables machines to better understand human behaviours. FER methods face the problems of relatively small datasets and noisy data that don't allow classical networks to generalize well. To alleviate these issues, we guide the model to concentrate on specific facial areas like the eyes, the mouth or the eyebrows, which we argue are decisive to recognise facial expressions. We propose the Privileged Attribution Loss (PAL), a method that directs the attention of the model towards the most salient facial regions by encouraging its attribution maps to correspond to a heatmap formed by facial landmarks. Furthermore, we introduce several channel strategies that allow the model to have more degrees of freedom. The proposed method is independent of the backbone architecture and doesn't need additional semantic information at test time. Finally, experimental results show that the proposed PAL method outperforms current state-of-the-art methods on both RAF-DB and AffectNet.

  • Top Cited Papers
    Open Access

    Contributions of Artificial Intelligence Reported in Obstetrics and Gynecology Journals: Systematic Review

    by Ferdinand Dhombres, Jules Bonnard, Kévin Bailly, Paul Maurice, Aris T Papageorghiou, Jean-Marie Jouannic

    Background: The applications of artificial intelligence (AI) processes have grown significantly in all medical disciplines during the last decades. Two main types of AI have been applied in medicine: symbolic AI (eg, knowledge base and ontologies) and nonsymbolic AI (eg, machine learning and artificial neural networks). Consequently, AI has also been applied across most obstetrics and gynecology (OB/GYN) domains, including general obstetrics, gynecology surgery, fetal ultrasound, and assisted reproductive medicine, among others. Objective: The aim of this study was to provide a systematic review to establish the actual contributions of AI reported in OB/GYN discipline journals. Methods: The PubMed database was searched for citations indexed with “artificial intelligence” and at least one of the following medical subject heading (MeSH) terms between January 1, 2000, and April 30, 2020: “obstetrics”; “gynecology”; “reproductive techniques, assisted”; or “pregnancy.” All publications in OB/GYN core disciplines journals were considered. The selection of journals was based on disciplines defined in Web of Science. The publications were excluded if no AI process was used in the study. Review, editorial, and commentary articles were also excluded. The study analysis comprised (1) classification of publications into OB/GYN domains, (2) description of AI methods, (3) description of AI algorithms, (4) description of data sets, (5) description of AI contributions, and (6) description of the validation of the AI process. Results: The PubMed search retrieved 579 citations and 66 publications met the selection criteria. All OB/GYN subdomains were covered: obstetrics (41%, 27/66), gynecology (3%, 2/66), assisted reproductive medicine (33%, 22/66), early pregnancy (2%, 1/66), and fetal medicine (21%, 14/66). Both machine learning methods (39/66) and knowledge base methods (25/66) were represented. Machine learning used imaging, numerical, and clinical data sets. Knowledge base methods used mostly omics data sets. The actual contributions of AI were method/algorithm development (53%, 35/66), hypothesis generation (42%, 28/66), or software development (3%, 2/66). Validation was performed on one data set (86%, 57/66) and no external validation was reported. We observed a general rising trend in publications related to AI in OB/GYN over the last two decades. Most of these publications (82%, 54/66) remain out of the scope of the usual OB/GYN journals. Conclusions: In OB/GYN discipline journals, mostly preliminary work (eg, proof-of-concept algorithm or method) in AI applied to this discipline is reported and clinical validation remains an unmet prerequisite. Improvement driven by new AI research guidelines is expected. However, these guidelines are covering only a part of AI approaches (nonsymbolic) reported in this review; hence, updates need to be considered.


  • Open Access

    Contributions of Artificial Intelligence Reported in Obstetrics and Gynecology Journals: Systematic Review (Preprint)

    by Ferdinand Dhombres, Jules Bonnard, Kévin Bailly, Paul Maurice, Aris T Papageorghiou, Jean-Marie Jouannic

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: The applications of artificial intelligence (AI) processes have grown significantly in all medical disciplines during the last decades. Two main types of AI have been applied in medicine: symbolic AI (eg, knowledge base and ontologies) and nonsymbolic AI (eg, machine learning and artificial neural networks). Consequently, AI has also been applied across most obstetrics and gynecology (OB/GYN) domains, including general obstetrics, gynecology surgery, fetal ultrasound, and assisted reproductive medicine, among others. Objective: The aim of this study was to provide a systematic review to establish the actual contributions of AI reported in OB/GYN discipline journals. Methods: The PubMed database was searched for citations indexed with “artificial intelligence” and at least one of the following medical subject heading (MeSH) terms between January 1, 2000, and April 30, 2020: “obstetrics”; “gynecology”; “reproductive techniques, assisted”; or “pregnancy.” All publications in OB/GYN core disciplines journals were considered. The selection of journals was based on disciplines defined in Web of Science. The publications were excluded if no AI process was used in the study. Review, editorial, and commentary articles were also excluded. The study analysis comprised (1) classification of publications into OB/GYN domains, (2) description of AI methods, (3) description of AI algorithms, (4) description of data sets, (5) description of AI contributions, and (6) description of the validation of the AI process. Results: The PubMed search retrieved 579 citations and 66 publications met the selection criteria. All OB/GYN subdomains were covered: obstetrics (41%, 27/66), gynecology (3%, 2/66), assisted reproductive medicine (33%, 22/66), early pregnancy (2%, 1/66), and fetal medicine (21%, 14/66). Both machine learning methods (39/66) and knowledge base methods (25/66) were represented. Machine learning used imaging, numerical, and clinical data sets. Knowledge base methods used mostly omics data sets. The actual contributions of AI were method/algorithm development (53%, 35/66), hypothesis generation (42%, 28/66), or software development (3%, 2/66). Validation was performed on one data set (86%, 57/66) and no external validation was reported. We observed a general rising trend in publications related to AI in OB/GYN over the last two decades. Most of these publications (82%, 54/66) remain out of the scope of the usual OB/GYN journals. Conclusions: In OB/GYN discipline journals, mostly preliminary work (eg, proof-of-concept algorithm or method) in AI applied to this discipline is reported and clinical validation remains an unmet prerequisite. Improvement driven by new AI research guidelines is expected. However, these guidelines are covering only a part of AI approaches (nonsymbolic) reported in this review; hence, updates need to be considered.