A5057717199- 3D Shape Modeling and Analysis
- Advanced Numerical Analysis Techniques
- Computer Graphics and Visualization Techniques
- Advanced Vision and Imaging
- Cardiac Valve Diseases and Treatments
- Medical Image Segmentation Techniques
- Orthodontics and Dentofacial Orthopedics
- Phonocardiography and Auscultation Techniques
- Morphological variations and asymmetry
- Bioinformatics and Genomic Networks
- Computational Geometry and Mesh Generation
- Education, sociology, and vocational training
- Temporomandibular Joint Disorders
- Soft Robotics and Applications
- Educational Tools and Methods
- Cardiovascular Function and Risk Factors
- Forensic Anthropology and Bioarchaeology Studies
- Hepatocellular Carcinoma Treatment and Prognosis
- Infective Endocarditis Diagnosis and Management
- Smart Systems and Machine Learning
- COVID-19 diagnosis using AI
- Robotics and Sensor-Based Localization
- Single-cell and spatial transcriptomics
- 3D Surveying and Cultural Heritage
- Gene expression and cancer classification
Massachusetts General Hospital
2022-2024
Harvard University Press
2024
Harvard University
2023-2024
University of Iowa
2018-2020
Korea Institute of Science and Technology
2017
Université de Bordeaux
2015
Laboratoire Bordelais de Recherche en Informatique
2013-2015
Abstract This study presents Anthropological Facial Approximation in Three Dimensions ( AFA 3D), a new computerized method for estimating face shape based on computed tomography CT ) scans of 500 French individuals. soft tissue depths are estimated age, sex, corpulence, and craniometrics, projected using reference planes to obtain the global facial appearance. Position eyes, nose, mouth, ears inferred from cranial landmarks through geometric morphometrics. The 100 cutaneous then used warp...
In this paper, we propose a novel formulation to extend CNNs two-dimensional (2D) manifolds using orthogonal basis functions, called Zernike polynomials. many areas, geometric features play key role in understanding scientific phenomena. Thus, an ability codify into mathematical quantity can be critical. Recently, convolutional neural networks (CNNs) have demonstrated the promising capability of extracting and codifying from visual information. However, progress has been concentrated...
Abstract Objective . This paper presents a novel approach for addressing the intricate task of diagnosing aortic valve regurgitation (AR), valvular disease characterized by blood leakage due to incompetence closure. Conventional diagnostic techniques require detailed evaluations multi-modal clinical data, frequently resulting in labor-intensive and time-consuming procedures that are vulnerable varying subjective assessment severity. Approach In our research, we introduce multi-view video...
Abstract Geometrical and topological inconsistencies, such as self-intersections non-manifold elements, are common in triangular meshes, causing various problems across all stages of geometry processing. In this paper, we propose a method to resolve these inconsistencies using graph-based approach. We first convert geometrical into construct topology graph. then define local pairing operations on the graph, which is guaranteed not introduce new inconsistencies. The final output our an...
Les articulations temporo-mandibulaires fonctionnent en synergie avec l’occlusion dentaire, dans le cadre du système manducateur. La prise compte condyle mandibulaire par l’orthodontiste et chirurgien orthognathique est fondamentale car un problème de positionnement condylien pourrait entraîner trouble occlusal risque récidive d’apparition, décompensation ou d’aggravation d’une dysfonction temporo-mandibulaire. Nous avons voulu répondre à trois questions : Quelle la position post-opératoire...
In this paper, we propose a novel formulation to extend CNNs two-dimensional (2D) manifolds using orthogonal basis functions, called Zernike polynomials. many areas, geometric features play key role in understanding scientific phenomena. Thus, an ability codify into mathematical quantity can be critical. Recently, convolutional neural networks (CNNs) have demonstrated the promising capability of extracting and codifying from visual information. However, progress has been concentrated...
The paper introduces a novel autonomous robot ultrasound (US) system targeting liver follow-up scans for outpatients in local communities. Given computed tomography (CT) image with specific target regions of interest, the proposed carries out scan three steps: (i) initial contact to surface, (ii) coordinate mapping between CT and robot, (iii) US scan. Utilizing 3D US-CT registration deep learning-based segmentation networks, we can achieve precise imaging hepatic veins, facilitating accurate...
Summary For over a century, scientists have been attempting to map the human cerebral cortex, however, they not taken into account complex molecular structure of which is only beginning be understood. Here, we parcellate cortex using machine learning (ML) approach define its transcriptomic architecture, revealing multi-resolution organization across individuals. The transcriptomically-derived spatial patterns gene expression separate three major regions, frontal, temporal and...
Boolean operations between two colliding shells:a robust, exact, and simple method
Autonomous robotic ultrasound System (RUSS) has been extensively studied. However, fully automated image acquisition is still challenging, partly due to the lack of study in combining two phases path planning: guiding probe scan target and covering surface or volume. This paper presents a system Automated Path Planning for RUSS (APP-RUSS). Our focus on first phase automation, which emphasizes directing probe's toward over extended distances. Specifically, our APP-RUSS consists RealSense D405...