Mariana Costa Bernardes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mariana Costa Bernardes has a total of 59 co-authors. Here are the top co-authors by number of shared publications:
- Geovany Araujo Borges
Department of Electrical Engineering, University of Brasilia, Brasília, Brazil
6 shared publications - Pedro Moreira
Department of Radiology, Brigham and Women’s Hospital and Harvard Medical School, 75 Francis St., Boston, MA, USA
6 shared publications - Junichi Tokuda
Department of Radiology, Harvard Medical School, Boston, MA, USA
5 shared publications - Bruno Vilhena Adorno
University of Manchester
4 shared publications - Clare Tempany
Brigham and Women's Hospital, Boston, MA
4 shared publications - Kemal Tuncali
Department of Radiology, Brigham and Women’s Hospital and Harvard Medical School, 75 Francis St., Boston, MA, USA
4 shared publications
Latest Publications
- 30 March 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Robot assisted steering of flexible needles for percutaneous procedures
Guidage robotisé des aiguilles fexibles pour des procédures percutanées: Les travaux de cette thèse proposent une nouvelle approche pour le guidage assisté par robots d'aiguilles flexibles pour des procédures percutanées. La méthode est basée sur l'utilisation d'une rotation de l'aiguille avec un rapport cyclique variable pour réaliser une insertion avec des arcs de rayons de courbure différents. Elle combine un retour visuel avec une stratégie de planification adaptative pour compenser les incertitudes du système et les perturbations. Par rapport aux approches présentées précédemment dans la littérature, la stratégie de planification en boucle fermée est adaptée à des scènes dynamiques qui présentent des changements de position des obstacles et de la cible. Cette approche a été implémentée sur un système robotique et les résultats obtenus in vitro confirment tout l'intérêt de cette technique.
- 30 March 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Robot assisted steering of flexible needles for percutaneous procedures
Guidage robotisé des aiguilles fexibles pour des procédures percutanées: Les travaux de cette thèse proposent une nouvelle approche pour le guidage assisté par robots d'aiguilles flexibles pour des procédures percutanées. La méthode est basée sur l'utilisation d'une rotation de l'aiguille avec un rapport cyclique variable pour réaliser une insertion avec des arcs de rayons de courbure différents. Elle combine un retour visuel avec une stratégie de planification adaptative pour compenser les incertitudes du système et les perturbations. Par rapport aux approches présentées précédemment dans la littérature, la stratégie de planification en boucle fermée est adaptée à des scènes dynamiques qui présentent des changements de position des obstacles et de la cible. Cette approche a été implémentée sur un système robotique et les résultats obtenus in vitro confirment tout l'intérêt de cette technique.
- 23 March 2026
- Published by World Scientific Pub Co Pte Ltd in Journal of Medical Robotics Research
- Vol. 11 (01n02)
Clinical Validation of a Novel Robotic Device for MR-guided Prostate Biopsy: Initial Patient Experience
Magnetic resonance imaging (MRI)-guided transperineal targeted prostate biopsy has the potential to provide a precise cancer diagnosis. However, it is challenged by targeting errors and needle deflection. The main issue is that the traditional needle guides have limited degrees of freedom (DoF) and therefore restrict insertion path options. Thus, the targeting error can be larger than 5[ ]mm. This study evaluates the performance of a custom-built 4-DoF needle guiding device designed to enable alternative insertion paths. The 4-DoF Smart Template was designed to improve image quality and stability, including redesigned fiducials and titanium positioning frames. Four MRI-guided biopsy cases were conducted. Targets were identified on T2-weighted images, and insertion paths were planned and adjusted to avoid critical structures. The targeting error was measured as the in-plane distance between the target and the actual needle position. The average targeting error of the best insertion attempt was 3.7[ ]mm ± 2.6[ ]mm (mean ± standard deviation). When discarding the case where the device had to be removed due to patient anatomy, the average targeting error was reduced to 2.7[ ]mm ± 1.1[ ]mm. No adverse events were reported. The new 4-DoF Smart Template device has demonstrated improved accuracy as compared to the traditional needle guide device, successfully reaching the target location with just one insertion in four out of six targets.
- 23 March 2026
- Published by World Scientific Pub Co Pte Ltd in Journal of Medical Robotics Research
- Vol. 11 (01n02)
Clinical Validation of a Novel Robotic Device for MR-guided Prostate Biopsy: Initial Patient Experience
Magnetic resonance imaging (MRI)-guided transperineal targeted prostate biopsy has the potential to provide a precise cancer diagnosis. However, it is challenged by targeting errors and needle deflection. The main issue is that the traditional needle guides have limited degrees of freedom (DoF) and therefore restrict insertion path options. Thus, the targeting error can be larger than 5[ ]mm. This study evaluates the performance of a custom-built 4-DoF needle guiding device designed to enable alternative insertion paths. The 4-DoF Smart Template was designed to improve image quality and stability, including redesigned fiducials and titanium positioning frames. Four MRI-guided biopsy cases were conducted. Targets were identified on T2-weighted images, and insertion paths were planned and adjusted to avoid critical structures. The targeting error was measured as the in-plane distance between the target and the actual needle position. The average targeting error of the best insertion attempt was 3.7[ ]mm ± 2.6[ ]mm (mean ± standard deviation). When discarding the case where the device had to be removed due to patient anatomy, the average targeting error was reduced to 2.7[ ]mm ± 1.1[ ]mm. No adverse events were reported. The new 4-DoF Smart Template device has demonstrated improved accuracy as compared to the traditional needle guide device, successfully reaching the target location with just one insertion in four out of six targets.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (10) , 8975-8982
In Vivo Feasibility Study: Evaluating Autonomous Data-Driven Robotic Needle Trajectory Correction in MRI-Guided Transperineal Procedures
This letter addresses the targeting challenges in MRI-guided transperineal needle placement for prostate cancer (PCa) diagnosis and treatment, a procedure where accuracy is crucial for effective outcomes. We introduce a parameter-agnostic trajectory correction approach incorporating a data-driven closed-loop strategy by radial displacement and an FBG-based shape sensing to enable autonomous needle steering. In an animal study designed to emulate clinical complexity and assess MRI compatibility through a PCa mock biopsy procedure, our approach demonstrated a significant improvement in targeting accuracy (p < 0.05), with mean target error of only 2.2 $\pm$ 1.9 mm on first insertion attempts, without needle reinsertions. To the best of our knowledge, this work represents the first in vivo evaluation of robotic needle steering with FBG-sensor feedback, marking a significant step towards its clinical translation.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (10) , 8975-8982
In Vivo Feasibility Study: Evaluating Autonomous Data-Driven Robotic Needle Trajectory Correction in MRI-Guided Transperineal Procedures
This letter addresses the targeting challenges in MRI-guided transperineal needle placement for prostate cancer (PCa) diagnosis and treatment, a procedure where accuracy is crucial for effective outcomes. We introduce a parameter-agnostic trajectory correction approach incorporating a data-driven closed-loop strategy by radial displacement and an FBG-based shape sensing to enable autonomous needle steering. In an animal study designed to emulate clinical complexity and assess MRI compatibility through a PCa mock biopsy procedure, our approach demonstrated a significant improvement in targeting accuracy (p < 0.05), with mean target error of only 2.2 $\pm$ 1.9 mm on first insertion attempts, without needle reinsertions. To the best of our knowledge, this work represents the first in vivo evaluation of robotic needle steering with FBG-sensor feedback, marking a significant step towards its clinical translation.
- 12 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (11) , 18359-18371
Hybrid Deep Learning and Model-Based Needle Shape Prediction
Needle insertion using flexible bevel-tip needles is a common minimally invasive surgical technique for prostate cancer interventions. Flexible, asymmetric bevel-tip needles enable physicians for complex needle steering techniques to avoid sensitive anatomical structures during needle insertion. For accurate placement of the needle, predicting the trajectory of these needles intraoperatively would greatly reduce the need for frequently needle reinsertions, thus improving patient comfort and positive outcomes. However, predicting the trajectory of the needle during insertion is a complex task that has yet to be solved due to random needle–tissue interactions. In this article, we present and validate, for the first time, a hybrid deep learning and model-based approach to handle the intraoperative needle shape prediction problem through leveraging a validated Lie-group theoretic model for needle shape representation. Furthermore, we present a novel self-supervised learning (SSL) and method in conjunction with the Lie-group shape model for training these networks in the absence of data, enabling further refinement of these networks with transfer learning (TL). Needle shape prediction was performed in single-layer and double-layer homogeneous phantom tissue for C- and S-shaped needle insertions. Our method demonstrates an average root-mean-square prediction error of 1.03 mm over a dataset containing approximately 3000 prediction samples with the maximum prediction steps of 110 mm.
- 12 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (11) , 18359-18371
Hybrid Deep Learning and Model-Based Needle Shape Prediction
Needle insertion using flexible bevel-tip needles is a common minimally invasive surgical technique for prostate cancer interventions. Flexible, asymmetric bevel-tip needles enable physicians for complex needle steering techniques to avoid sensitive anatomical structures during needle insertion. For accurate placement of the needle, predicting the trajectory of these needles intraoperatively would greatly reduce the need for frequently needle reinsertions, thus improving patient comfort and positive outcomes. However, predicting the trajectory of the needle during insertion is a complex task that has yet to be solved due to random needle–tissue interactions. In this article, we present and validate, for the first time, a hybrid deep learning and model-based approach to handle the intraoperative needle shape prediction problem through leveraging a validated Lie-group theoretic model for needle shape representation. Furthermore, we present a novel self-supervised learning (SSL) and method in conjunction with the Lie-group shape model for training these networks in the absence of data, enabling further refinement of these networks with transfer learning (TL). Needle shape prediction was performed in single-layer and double-layer homogeneous phantom tissue for C- and S-shaped needle insertions. Our method demonstrates an average root-mean-square prediction error of 1.03 mm over a dataset containing approximately 3000 prediction samples with the maximum prediction steps of 110 mm.
- 15 May 2023
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 68 (10) , 105016
Data-driven adaptive needle insertion assist for transperineal prostate interventions
Objective. Clinical outcomes of transperineal prostate interventions, such as biopsy, thermal ablations, and brachytherapy, depend on accurate needle placement for effectiveness. However, the accurate placement of a long needle, typically 150–200 mm in length, is challenging due to needle deviation induced by needle-tissue interaction. While several approaches for needle trajectory correction have been studied, many of them do not translate well to practical applications due to the use of specialized needles not yet approved for clinical use, or to relying on needle-tissue models that need to be tailored to individual patients. Approach. In this paper, we present a robot-assisted collaborative needle insertion method that only requires an actuated passive needle guide and a conventional needle. The method is designed to assist a physician inserting a needle manually through a needle guide. If the needle is deviated from the intended path, actuators shifts the needle radially in order to steer the needle trajectory and compensate for needle deviation adaptively. The needle guide is controlled by a new data-driven algorithm which does not require a priori information about needle or tissue properties. The method was evaluated in experiments with both in vitro and ex vivo phantoms. Main results. The experiments in ex vivo tissue reported a mean final placement error of 0.36 mm with a reduction of 96.25% of placement error when compared to insertions without the use of assistive correction. Significance. Presented results show that the proposed closed-loop formulation can be successfully used to correct needle deflection during collaborative manual insertion with potential to be easily translated into clinical application.
- 15 May 2023
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 68 (10) , 105016
Data-driven adaptive needle insertion assist for transperineal prostate interventions
Objective. Clinical outcomes of transperineal prostate interventions, such as biopsy, thermal ablations, and brachytherapy, depend on accurate needle placement for effectiveness. However, the accurate placement of a long needle, typically 150–200 mm in length, is challenging due to needle deviation induced by needle-tissue interaction. While several approaches for needle trajectory correction have been studied, many of them do not translate well to practical applications due to the use of specialized needles not yet approved for clinical use, or to relying on needle-tissue models that need to be tailored to individual patients. Approach. In this paper, we present a robot-assisted collaborative needle insertion method that only requires an actuated passive needle guide and a conventional needle. The method is designed to assist a physician inserting a needle manually through a needle guide. If the needle is deviated from the intended path, actuators shifts the needle radially in order to steer the needle trajectory and compensate for needle deviation adaptively. The needle guide is controlled by a new data-driven algorithm which does not require a priori information about needle or tissue properties. The method was evaluated in experiments with both in vitro and ex vivo phantoms. Main results. The experiments in ex vivo tissue reported a mean final placement error of 0.36 mm with a reduction of 96.25% of placement error when compared to insertions without the use of assistive correction. Significance. Presented results show that the proposed closed-loop formulation can be successfully used to correct needle deflection during collaborative manual insertion with potential to be easily translated into clinical application.
- Open Access
- 30 June 2022
- Published by Springer Nature in European Radiology
- Vol. 33 (1) , 461-471
Promoting the use of the PI-QUAL score for prostate MRI quality: results from the ESOR Nicholas Gourtsoyiannis teaching fellowship
Objectives: The Prostate Imaging Quality (PI-QUAL) score is a new metric to evaluate the diagnostic quality of multiparametric magnetic resonance imaging (MRI) of the prostate. This study assesses the impact of an intervention, namely a prostate MRI quality training lecture, on the participant’s ability to apply PI-QUAL. Methods: Sixteen participants (radiologists, urologists, physicists, and computer scientists) of varying experience in reviewing diagnostic prostate MRI all assessed the image quality of ten examinations from different vendors and machines. Then, they attended a dedicated lecture followed by a hands-on workshop on MRI quality assessment using the PI-QUAL score. Five scans assessed by the participants were evaluated in the workshop using the PI-QUAL score for teaching purposes. After the course, the same participants evaluated the image quality of a new set of ten scans applying the PI-QUAL score. Results were assessed using receiver operating characteristic analysis. The reference standard was the PI-QUAL score assessed by one of the developers of PI-QUAL. Results: There was a significant improvement in average area under the curve for the evaluation of image quality from baseline (0.59 [95 % confidence intervals: 0.50–0.66]) to post-teaching (0.96 [0.92–0.98]), an improvement of 0.37 [0.21–0.41] (p < 0.001). Conclusions: A teaching course (dedicated lecture + hands-on workshop) on PI-QUAL significantly improved the application of this scoring system to assess the quality of prostate MRI examinations. Key Points: • A significant improvement in the application of PI-QUAL for the assessment of prostate MR image quality was observed after an educational intervention. • Appropriate training on image quality can be delivered to those involved in the acquisition and interpretation of prostate MRI. • Further investigation will be needed to understand the impact on improving the acquisition of high-quality diagnostic prostate MR examinations.
- 30 June 2022
- Published by Springer Nature in European Radiology
- Vol. 33 (1) , 461-471
Open AccessPromoting the use of the PI-QUAL score for prostate MRI quality: results from the ESOR Nicholas Gourtsoyiannis teaching fellowship
Objectives: The Prostate Imaging Quality (PI-QUAL) score is a new metric to evaluate the diagnostic quality of multiparametric magnetic resonance imaging (MRI) of the prostate. This study assesses the impact of an intervention, namely a prostate MRI quality training lecture, on the participant’s ability to apply PI-QUAL. Methods: Sixteen participants (radiologists, urologists, physicists, and computer scientists) of varying experience in reviewing diagnostic prostate MRI all assessed the image quality of ten examinations from different vendors and machines. Then, they attended a dedicated lecture followed by a hands-on workshop on MRI quality assessment using the PI-QUAL score. Five scans assessed by the participants were evaluated in the workshop using the PI-QUAL score for teaching purposes. After the course, the same participants evaluated the image quality of a new set of ten scans applying the PI-QUAL score. Results were assessed using receiver operating characteristic analysis. The reference standard was the PI-QUAL score assessed by one of the developers of PI-QUAL. Results: There was a significant improvement in average area under the curve for the evaluation of image quality from baseline (0.59 [95 % confidence intervals: 0.50–0.66]) to post-teaching (0.96 [0.92–0.98]), an improvement of 0.37 [0.21–0.41] (p < 0.001). Conclusions: A teaching course (dedicated lecture + hands-on workshop) on PI-QUAL significantly improved the application of this scoring system to assess the quality of prostate MRI examinations. Key Points: • A significant improvement in the application of PI-QUAL for the assessment of prostate MR image quality was observed after an educational intervention. • Appropriate training on image quality can be delivered to those involved in the acquisition and interpretation of prostate MRI. • Further investigation will be needed to understand the impact on improving the acquisition of high-quality diagnostic prostate MR examinations.
- 4 June 2019
- Published by Springer Nature in IFMBE Proceedings
- p. 737-742
Virtual Reality Simulator for Laparoscopic Procedures Performed with a Robotic Endoscope Holder
- 4 June 2019
- Published by Springer Nature in IFMBE Proceedings
- p. 737-742
Virtual Reality Simulator for Laparoscopic Procedures Performed with a Robotic Endoscope Holder
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 598-603
Project Edubot: Teaching Robotics to High School Students
Technology is evolving rapidly and increasing the need for professionals. Therefore, is necessary to prepare student at the early levels with the skills need to fill this gap. In this paper we describe the Edubot project. The project aims to teach programming and robotics principles at public high schools in Brasilia to attract students to STEM subjects and engineering, as well as to develop their problem solving skills. The course has a project based approach and has been implemented at a few high schools in a partnership among professors, undergrad and high school students. We present the expansion of the project over the years, mainly the number of schools and high school students reached, and improvements in the teaching methodology.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 598-603
Project Edubot: Teaching Robotics to High School Students
Technology is evolving rapidly and increasing the need for professionals. Therefore, is necessary to prepare student at the early levels with the skills need to fill this gap. In this paper we describe the Edubot project. The project aims to teach programming and robotics principles at public high schools in Brasilia to attract students to STEM subjects and engineering, as well as to develop their problem solving skills. The course has a project based approach and has been implemented at a few high schools in a partnership among professors, undergrad and high school students. We present the expansion of the project over the years, mainly the number of schools and high school students reached, and improvements in the teaching methodology.
- 20 February 2018
- Published by SAGE Publications in International Journal of Electrical Engineering & Education
- Vol. 55 (2) , 130-141
A real-time web-based networked control system education platform
Networked control systems have recently experienced a surge in fundamental theoretical results ignited by numerous advantages of introducing shared multipurpose communication networks in control systems. Regarding developments on the practical side, however, a networked control system is still wanting when it comes to experimental platforms suitable for research and educational purposes, which contributes to most of networked control system theory being validated by means of numerical examples and simulations. This paper addresses this issue by presenting a low-cost real-time networked control system platform, based on custom hardware and software solutions that can be readily explored with the sole use of a web browser connected to the Internet. The technical decisions made during development represent a fundamentally novel take on networked control system experimental platforms that can potentially be reproduced by several universities. The platform provides the user with multiple controller and input reference options, network configurations, delay statistics, and even a downloadable file containing advanced experiment data. A survey conducted with students located over 1200 km away from the platform who used it during laboratory assignments highlight the system’s usability and interactivity, and supports the platform is suitable for educational purposes.
- 20 February 2018
- Published by SAGE Publications in International Journal of Electrical Engineering & Education
- Vol. 55 (2) , 130-141
A real-time web-based networked control system education platform
Networked control systems have recently experienced a surge in fundamental theoretical results ignited by numerous advantages of introducing shared multipurpose communication networks in control systems. Regarding developments on the practical side, however, a networked control system is still wanting when it comes to experimental platforms suitable for research and educational purposes, which contributes to most of networked control system theory being validated by means of numerical examples and simulations. This paper addresses this issue by presenting a low-cost real-time networked control system platform, based on custom hardware and software solutions that can be readily explored with the sole use of a web browser connected to the Internet. The technical decisions made during development represent a fundamentally novel take on networked control system experimental platforms that can potentially be reproduced by several universities. The platform provides the user with multiple controller and input reference options, network configurations, delay statistics, and even a downloadable file containing advanced experiment data. A survey conducted with students located over 1200 km away from the platform who used it during laboratory assignments highlight the system’s usability and interactivity, and supports the platform is suitable for educational purposes.