Review
Computer Science, Theory & Methods
Lucas H. Sallaberry, Romero Tori, Fatima L. S. Nunes
Summary: This study presents a systematic review of automatic performance assessment in three-dimensional interactive medical and dental simulators with haptic feedback. The review includes 63 articles and focuses on the analysis of procedures, metrics, experiment types, and assessment techniques. The findings suggest that most studies have used statistical techniques to analyze metrics for performance assessment, while machine learning algorithms have not been explored extensively. Metrics related to time were commonly observed, while aspects related to force, error, and precision were less investigated. The study discusses difficulties reported in the articles and presents research opportunities.
ACM COMPUTING SURVEYS
(2023)
Article
Computer Science, Software Engineering
Ata Otaran, Ildar Farkhatdinov
Summary: This article presents an impedance type ankle haptic interface for providing users with an immersive navigation experience in virtual reality (VR). The interface uses an electric motor and feedback control to simulate real walking through ankle gestures and haptically render different types of terrains. Experimental studies demonstrate that the interface enables easy generation of virtual walking and is capable of rendering various terrains.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2022)
Article
Engineering, Mechanical
Silvia Logozzo, Maria Cristina Valigi, Monica Malvezzi
Summary: This research contributes to understanding human fingertip mechanical properties for optimizing new skin haptic interfaces, comparing simulated and experimental data, and developing a stiffness and damping model for new haptic interfaces design.
TRIBOLOGY INTERNATIONAL
(2022)
Article
Automation & Control Systems
Xinwei Yan, Peter X. Liu
Summary: Neurosurgeons face challenges such as poor geometric accuracy, unpredictable factors, and visual obstacles. A neurosurgery simulator allows for preoperative simulation and planning, reducing the risk of surgery. A haptic device with six degrees of freedom is designed based on the general requirements of neurosurgery, and its kinematics is analyzed. The feasibility of the design is confirmed through simulation and data analysis.
INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION
(2023)
Article
Chemistry, Analytical
Jin Woo Kim, Jeremy Jarzembak, Kwangtaek Kim
Summary: We developed a new haptic-mixed reality intravenous (HMR-IV) needle insertion simulation system that integrates a bimanual haptic interface and a mixed reality system. The system allows nursing students and healthcare professionals to practice IV needle insertion into a virtual arm under various changing insertion conditions. By integrating different haptic devices and a mixed reality system, accurate hand-eye coordination is achieved. The system also provides force-profile-based haptic rendering to mimic the real tactile feeling of IV needle insertion, and a global hand-tracking method for accurate tracking of a haptic glove.
Article
Computer Science, Software Engineering
Rinat Abdrashitov, Seungbae Bang, David Levin, Karan Singh, Alec Jacobson
Summary: The study introduces a new method for modeling musculoskeletal anatomy, utilizing volumetric segmentation and muscle curves control for automatic handling of intersections and calculation of muscle fiber fields. Additionally, an interactive skeleton authoring tool is introduced for creating skeletal anatomy starting from a skin mesh.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Interdisciplinary Applications
Gregory Ewing, Ricardo Mantilla, Witold Krajewski, Ibrahim Demir
Summary: Computational hydrological models and simulations are essential in contemporary hydroscience research and education. With improvements in browser-side compute performance, client-side resources can be leveraged for hydrological simulations, playing a central role in a web-ready ecosystem of hydrological tools.
JOURNAL OF HYDROINFORMATICS
(2022)
Article
Green & Sustainable Science & Technology
Maikel Issermann, Fi-John Chang, Pu-Yun Kow
Summary: The study introduces a Functional Mockup Interface (FMI)-based Urban Building Energy Modelling (UBEM) tool that couples with external models, enabling real-time estimation of building energy demand based on environmental conditions, enhancing its applicability. The tool was tested on a real-world example in Wuppertal, Germany, demonstrating effective building simulation and energy demand assessment using urban microclimate data.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Computer Science, Information Systems
Abhishek Kumar, Bhavana Srinivasan, Abdul Khader Jilani Saudagar, Abdullah AlTameem, Mohammed Alkhathami, Badr Alsamani, Muhammad Badruddin Khan, Zakir Hussain Ahmed, Ankit Kumar, Kamred Udham Singh
Summary: Virtual reality technology has great potential in the field of education, especially in medical education. Research suggests that using VR simulators for teaching can enhance students' learning motivation and outcomes, bridging the gap between traditional learning and practical experience. VR technology is also being researched and developed in India's education sector.
Article
Automation & Control Systems
Fei Wang, Zhiqin Qian, Yingzi Lin, Wenjun Zhang
Summary: This article presents a study on the rapid construction of a cost-effective virtual haptic device by proposing a new design concept called the haptic environment. By combining a haptic robot with the environment, the system's customizability and adaptability are enhanced.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2021)
Article
Computer Science, Artificial Intelligence
Jibin Gao, Jia-Hui Pan, Shao-Jie Zhang, Wei-Shi Zheng
Summary: This study proposes a framework for action assessment that considers asymmetric interactions among agents. It introduces an automatic assigner and an asymmetric interaction network search module for modeling non-symmetric interactions in interactive actions. The experimental results on various datasets demonstrate the effectiveness and robustness of the proposed framework.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2023)
Article
Robotics
Margaret Koehler, Thor Morales Bieze, Alexandre Kruszewski, Allison M. Okamura, Christian Duriez
Summary: In this article, a new approach for haptic rendering and comanipulation in continuum robotics using a robotic interface with deformable beams and bending sensors is proposed and demonstrated. A nonlinear finite element mechanical model is utilized for real-time computation of the robot's motion, which enables accurate estimation of the user's force on the end effector. Additionally, a higher frequency control loop is implemented to achieve sensing and control at high rates, allowing for haptic rendering of stiffer virtual walls and successful comanipulation tasks.
IEEE TRANSACTIONS ON ROBOTICS
(2023)
Article
Multidisciplinary Sciences
Hwan Kim, Kyung Hoon Hyun
Summary: This study proposes a novel graspable haptic device called HAPmini, which enhances the user's touch interaction. The device is designed with low mechanical complexity and a simple structure, while still providing force and tactile feedback to users. Experimental results confirm that HAPmini enhances the usability of touch interaction and provides additional texture information that was previously unavailable on the touchscreen.
Article
Chemistry, Analytical
Van-Cuong Nguyen, Victor Oliva-Torres, Sophie Bernadet, Guilhem Rival, Claude Richard, Jean-Fabien Capsal, Pierre-Jean Cottinet, Minh-Quyen Le
Summary: This study focuses on developing a piezoelectric device that can generate feedback vibrations for the user. The goal is to explore the possibility of replacing physical buttons on in-car systems with a haptic system. An FEM model was used to optimize the haptic performance of the wafer structure, and various parameters were shown to impact the device's ability to actuate. The study also found that a multilayered design can enhance the haptic performance while preventing electrical breakdown.
Article
Surgery
Anishan Vamadevan, Lars Konge, Morten Stadeager, Flemming Bjerrum
Summary: The study investigated the effect of adding haptic simulators to a proficiency-based laparoscopy training program. The results showed that haptic simulators reduced the time to reach proficiency compared to non-haptic simulators. However, the acquired skills were not transferable to the conventional non-haptic setting.
SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES
(2023)
Article
Biology
Agustina La Greca Saint-Esteven, Marta Bogowicz, Ender Konukoglu, Oliver Riesterer, Panagiotis Balermpas, Matthias Guckenberger, Stephanie Tanadini-Lang, Janita E. van Timmeren
Summary: Deep learning was successfully applied to predict HPV status in CT images of advanced OPC, achieving high diagnostic accuracy. This indicates the potential of deep learning as a support tool in cancer precision medicine.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Multidisciplinary Sciences
Kyriakos Flouris, Oscar Jimenez-del-Toro, Christoph Aberle, Michael Bach, Roger Schaer, Markus M. Obmann, Bram Stieltjes, Henning Muller, Adrien Depeursinge, Ender Konukoglu
Summary: Medical imaging quantitative features are becoming increasingly useful in clinical studies, particularly through the extraction of radiomics features. However, the stability of these features remains a significant challenge, which can be addressed using a simulator to assess their stability and discriminative power.
SCIENTIFIC REPORTS
(2022)
Article
Chemistry, Multidisciplinary
Carlos Albors, Eric Lluch, Juan Francisco Gomez, Nicolas Cedilnik, Konstantinos A. Mountris, Tommaso Mansi, Svyatoslav Khamzin, Arsenii Dokuchaev, Olga Solovyova, Esther Pueyo, Maxime Sermesant, Rafael Sebastian, Hernan G. Morales, Oscar Camara
Summary: Computational models of cardiac electrophysiology can reduce non-response to CRT by optimizing electrode placement, meshless models are valid alternatives, and data assimilation strategy is crucial.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Mathilde Merle, Florent Collot, Julien Castelneau, Pauline Migerditichan, Mehdi Juhoor, Buntheng Ly, Valery Ozenne, Bruno Quesson, Nejib Zemzemi, Yves Coudiere, Pierre Jais, Hubert Cochet, Maxime Sermesant
Summary: The advancement of cardiac imaging methods and predictive modeling poses challenges to current technologies in cardiology. To address this, researchers have developed a novel multimodality software platform called MUSIC for cardiovascular diagnosis and therapy guidance.
APPLIED SCIENCES-BASEL
(2022)
Editorial Material
Cardiac & Cardiovascular Systems
Aurelien Bustin, Matthias Stuber, Maxime Sermesant, Hubert Cochet
EUROPEAN HEART JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Paul Tourniaire, Marius Ilie, Paul Hofman, Nicholas Ayache, Herve Delingette
Summary: Using mixed supervision, we improve the classification and localization performances of a weakly-supervised model based on attention-based deep Multiple Instance Learning. With a limited amount of patch-level labeled slides, we achieve performance close to fully-supervised models.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Computer Science, Artificial Intelligence
Tianfei Zhou, Liulei Li, Gustav Bredell, Jianwu Li, Jan Unkelbach, Ender Konukoglu
Summary: Despite recent progress in automatic medical image segmentation, fully automatic results often require further refinement. In this paper, we propose a novel interactive segmentation method, called VMN, which propagates segmentation information bidirectionally to all slices of a 3D medical image volume based on user hints and guidance, and improves the accuracy through multi-round refinement. Extensive experiments on public medical image segmentation datasets demonstrate the superiority of our method compared to state-of-the-art segmentation models.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Medicine, General & Internal
Jan Margeta, Raabid Hussain, Paula Lopez Diez, Anika Morgenstern, Thomas Demarcy, Zihao Wang, Dan Gnansia, Octavio Martinez Manzanera, Clair Vandersteen, Herve Delingette, Andreas Buechner, Thomas Lenarz, Francois Patou, Nicolas Guevara
Summary: This study presents Nautilus, a web-based platform for automated cochlear analysis. It combines deep learning and Bayesian inference methods to delineate cochlear structures from clinical CT images and extract electrode locations from post-operative images. By fusing pre- and post-operative images, Nautilus can provide personalized metrics for research in cochlear implantation therapy.
JOURNAL OF CLINICAL MEDICINE
(2022)
Article
Medicine, General & Internal
Raabid Hussain, Attila Frater, Roger Calixto, Chadlia Karoui, Jan Margeta, Zihao Wang, Michel Hoen, Herve Delingette, Francois Patou, Charles Raffaelli, Clair Vandersteen, Nicolas Guevara
Summary: Understanding cochlear anatomy is essential for developing less invasive cochlear implantation techniques. This study analyzed over 1000 clinical temporal bone CT images to determine population statistics and correlations between cochlear dimensions and morphology. The findings indicate that cochlear morphology follows a normal distribution and that certain dimensions are more correlated with duct lengths, wrapping factor, and volume. The results also highlight the variability in scala tympani size and suggest differences in size and shape between ears of the same individual. Overall, this research provides important insights for implant development and reducing trauma during insertion.
JOURNAL OF CLINICAL MEDICINE
(2023)
Review
Radiology, Nuclear Medicine & Medical Imaging
Carine Wu, Sarah Montagne, Dimitri Hamzaoui, Nicholas Ayache, Herve Delingette, Raphaele Renard-Penna
Summary: This review analyzed and compared the applicability and efficiency of published methods for automatic segmentation of prostate zone anatomy, providing insights into the methodological flaws, biases, and low applicability in clinical practice.
INSIGHTS INTO IMAGING
(2022)
Article
Computer Science, Artificial Intelligence
Krishna Chaitanya, Ertunc Erdil, Neerav Karani, Ender Konukoglu
Summary: Supervised deep learning methods require large labeled datasets for accurate medical image segmentation. This paper proposes a local contrastive loss-based approach that utilizes pseudo-labels of unlabeled images and limited annotated images to learn pixel-level features for segmentation. Experimental results on three public medical datasets demonstrate the substantial improvement achieved by the proposed method.
MEDICAL IMAGE ANALYSIS
(2023)
Proceedings Paper
Cardiac & Cardiovascular Systems
Zihao Wang, Yingyu Yang, Maxime Sermesant, Herve Delingette
Summary: Image registration is a crucial and challenging task in medical image computing. Traditional approaches are time-consuming, while CNN and attention-based models such as Transformer have shown good performance. This study introduces patch-based MLP/Transformer models for image registration and demonstrates their effectiveness in unsupervised echocardiography registration, outperforming popular CNN models in terms of registration performance.
STATISTICAL ATLASES AND COMPUTATIONAL MODELS OF THE HEART: REGULAR AND CMRXMOTION CHALLENGE PAPERS, STACOM 2022
(2022)
Proceedings Paper
Cardiac & Cardiovascular Systems
Marta Saiz-Vivo, Jord Mill, Josquin Harrison, Guillermo Jimenez-Perez, Benoit Legghe, Xavier Iriart, Hubert Cochet, Gemma Piella, Maxime Sermesant, Oscar Camara
Summary: This study investigated the morphological and hemodynamic characteristics of the left atria and left atrial appendage using unsupervised machine learning techniques. The results found that patients with higher risk of thrombus formation had higher values of LAA height, tortuosity, and ostium perimeter, as well as a lower angle between the LAA and the left superior pulmonary vein.
STATISTICAL ATLASES AND COMPUTATIONAL MODELS OF THE HEART: REGULAR AND CMRXMOTION CHALLENGE PAPERS, STACOM 2022
(2022)
Article
Computer Science, Artificial Intelligence
Hind Dadoun, Anne-Laure Rousseau, Eric de Kerviler, Jean-Michel Correas, Anne-Marie Tissier, Fanny Joujou, Sylvain Bodard, Kemel Khezzane, Constance De Margerie-Mellon, Herve Delingette, Nicholas Ayache
Summary: The purpose of this study was to train and evaluate a deep learning-based network for detecting, localizing, and characterizing liver lesions in abdominal ultrasound images. The results showed that the network performed better than caregivers in detecting and localizing the lesions, and achieved similar performance in lesion characterization compared to experts.
RADIOLOGY-ARTIFICIAL INTELLIGENCE
(2022)
Article
Cardiac & Cardiovascular Systems
Pamela Moceri, Nicolas Duchateau, Delphine Baudouy, Fabien Squara, Sok Sithikun Bun, Emile Ferrari, Maxime Sermesant
Summary: This study aimed to assess changes in RV function in PH patients between baseline and a 6-month follow-up using 3D echocardiography. The results showed that improvements in RV global AS were associated with stable or improving clinical condition and survival, highlighting the prognostic importance of these changes. Multivariate COX analysis identified changes in WHO class, BNP, and RV global AS as independent predictors of outcomes.
EUROPEAN HEART JOURNAL-CARDIOVASCULAR IMAGING
(2022)
Article
Computer Science, Software Engineering
Rafael Maio, Tiago Araujo, Bernardo Marques, Andre Santos, Pedro Ramalho, Duarte Almeida, Paulo Dias, Beatriz Sousa Santos
Summary: Augmented Reality (AR) is a crucial technology in Industry 4.0 and smart manufacturing, particularly in the field of data monitoring. In this study, we developed a Pervasive AR tool for data monitoring, along with a web application for comparison purposes. User studies were conducted to gather feedback and evaluate the effectiveness of the systems, confirming the potential of Pervasive AR for data monitoring.
COMPUTERS & GRAPHICS-UK
(2024)
Article
Computer Science, Software Engineering
Berk Cebeci, Mehmet Bahadir Askin, Tolga K. Capin, Ufuk Celikcan
Summary: Despite advances in virtual reality technologies, extended VR sessions with head-mounted displays (HMDs) still face challenges in terms of comfort. In this study, a methodology using gaze-directed and visual saliency-guided paradigms for automatic stereo camera control in real-time interactive VR was proposed. The results showed that the gaze-directed approach outperformed the saliency-guided approach, both improving the overall depth feeling without hindering visual comfort in the tested virtual environments (VEs).
COMPUTERS & GRAPHICS-UK
(2024)
Article
Computer Science, Software Engineering
Ali Egemen Tasoren, Ufuk Celikcan
Summary: By developing the NOVAction engine, we have created the NOVAction23 dataset, which consists of highly diversified and photorealistic synthetic human action sequences. This dataset is significant in improving the performance of human action recognition.
COMPUTERS & GRAPHICS-UK
(2024)