Faculty Profiles - MATSUNO Takayuki

Papers - MATSUNO Takayuki

Division display 1 - 20 of about 110 ／ All the affair displays >>

Proposal of new topology information Face-list for manipulation planning of deformable string tying Reviewed

Junxiang Wang, Tomoya Shirakawa, Tomotoshi Watanabe, Yuichiro Toda, Takayuki Matsuno

SICE Journal of Control, Measurement, and System Integration 16 ( 1 ) 257 - 272 2023.7

Rope Structure Recognition for Manipulation Using Topological Model and Knot Invariant

MATSUNO Takayuki, TAMAKI Daichi, ARAI Fumihito, FUKUDA Toshio

計測自動制御学会論文集 41 ( 4 ) 366 - 372 2005.4

Comparison of robotic versus manual needle insertion for CT-guided intervention: prospective randomized trial

Takao Hiraki, Yusuke Matsui, Jun Sakurai, Koji Tomita, Mayu Uka, Soichiro Kajita, Noriyuki Umakoshi, Toshihiro Iguchi, Michihiro Yoshida, Kota Sakamoto, Takayuki Matsuno, Tetsushi Kamegawa

Radiology Advances 2 ( 2 ) 2025.3

Publishing type：Research paper (scientific journal) Publisher：Oxford University Press (OUP)

Abstract

Background

Robotic needle insertion under CT guidance has been developed, but data on comparison with manual insertion are still lacking.

Purpose

To compare robotic versus manual needle insertion for CT fluoroscopy-guided intervention, primarily in terms of insertion accuracy.

Materials and Methods

This was a prospective study between May 2020 and March 2023 at a single site. The cohort comprised 22 patients undergoing CT (Aquilion One or Aquilion CX; Canon Medical Systems) fluoroscopy-guided biopsy, who were randomly allocated to either the robotic or manual group. The robot used (Zerobot; Medicalnet Okayama) is not yet commercially available. A biopsy introducer needle was inserted by 1 of 3 physicians using a remote-control robot in the robotic group, versus by 1 of 3 different physicians by hand in the manual group. The primary endpoint was needle insertion accuracy, which was defined as the 3-dimensional Euclidean distance between a predetermined target point and the needle tip after insertion. The non-inferiority of robotic insertion to manual one was then tested. Adverse events were evaluated. Statistical comparisons were made between the 2 groups.

Results

Technical success and pathological findings were confirmed in all patients of the 2 groups. The mean and SD of needle insertion were 4.8 mm ± 2.6 in the robotic group and 7.0 mm ± 3.1 in the manual group (P &lt; .001). The mean difference in accuracy between the 2 groups (robotic minus manual group) was −2.1 mm (95% CI, −4.7 to 0.4). Effective dose to physicians was zero in all cases in the robotic group, while median dose was 1.0 µSv in the manual group (P &lt; .001). Dose length product to patients was not significantly different between the 2 groups (P = .100). No major adverse events were observed.

Conclusion

Robotic needle insertion was non-inferior to manual insertion in terms of accuracy, while it effectively eliminated radiation exposure to physicians.

Trial registration number

jRCT2062200013

DOI： 10.1093/radadv/umaf010

researchmap

Other Link： https://academic.oup.com/radadv/article-pdf/2/2/umaf010/62871840/umaf010.pdf

Development of an Underwater Environment Analysis System Based on Neural Network Using Omnidirectional Camera

Kento Utsunomiya, Yuichiro Toda, Takayuki Matsuno

2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems (SCIS&amp;ISIS) 1 - 3 2024.11

Global Path Planning Based on Rough Terrain Perception Using Growing Neural Gas

Haruka Ozaki, Yuichiro Toda, Dalin Zhou, Takayuki Matsuno

2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems (SCIS&amp;ISIS) 1 - 3 2024.11

Case Study on a Navigation System using Growing Neural Gas

Koki Sakamoto, Yuichiro Toda, Makoto Tsujimoto, Kazuhiko Taniguchi, Takayuki Matsuno

2024 Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems (SCIS&amp;ISIS) 1 - 3 2024.11

Passability-Based Local Planner Using Growing Neural Gas for an Autonomous Mobile Robot

Koki Ozasa, Yuichiro Toda, Yoshimasa Nakamura, Toshiki Masuda, Hirohide Konishi, Takayuki Matsuno

IEEE Access 12 171824 - 171835 2024

Robotic systems in interventional oncology: a narrative review of the current status

Yusuke Matsui, Tetsushi Kamegawa, Koji Tomita, Mayu Uka, Noriyuki Umakoshi, Takahiro Kawabata, Kazuaki Munetomo, Toshihiro Iguchi, Takayuki Matsuno, Takao Hiraki

International Journal of Clinical Oncology 2023.4

Contact detection algorithm for needle puncturing robot Reviewed

T. Matsuno, N. Kido, T. Kamegawa, T. Hiraki, T. Fukuda

Communications in Information and Systems 22 ( 4 ) 477 - 497 2023.1

Growing Neural Gas based Traversability Clustering for an Autonomous Robot.

Koki Ozasa, Yuichiro Toda, Takayuki Matsuno

IJCNN 1 - 6 2023

Integration of Growing Neural Gas based 3D Space Perception with 2D Environmental Map

KUBOHIRA Daichi, OZASA Koki, NAKAMURA Yoshimasa, MASUDA Toshiki, KONISHI Hirohide, TODA Yuichiro, MATSUNO Takayuki

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2023 2A1-G02 2023

Language：Japanese Publisher：The Japan Society of Mechanical Engineers

Recently, various types of autonomous robots are expected with developments of Robot technologies and AI technologies. Especially, an unsupervised learning based perception methods of the robot is required in an unknown environment. In our previous works, we proposed 2D and 3D perception system based on Growing Neural Gas (GNG) that is one of the unsupervised learning methods. This paper proposes an integration method of GNG based 3D space perception with 2D environmental map for an autonomous mobile robot. For integrating the 3D space perception and 2D environmental map, this paper uses Robot Operating System. Next, this paper conducts an experiment to verify the effectiveness of our proposed method.

DOI： 10.1299/jsmermd.2023.2a1-g02

researchmap

Growing neural gas based navigation system in unknown terrain environment for an autonomous mobile robot Reviewed

Yuichiro Toda, Koki Ozasa, Takayuki Matsuno

Artificial Life and Robotics 2022.11

Automatic Puncture Needle Detection by Image Processing Using Deep Learning and CT Values Reviewed

Kotaro Mayumi, Takayuki Matsuno, Tetsushi Kamegawa, Ken’ichi, Morooka, Takao Hiraki, Yuichiro Toda

Proc of 33rd 2022 International Symposium on Micro-NanoMechatronics and Human Science 2022.11

Environmental Map Learning Method based on Growing Neural Gas for a Mobile Robot Reviewed

Qi Li, Yuichiro Toda, Keisuke Nagao, Takayuki Matsuno

2022 International Joint Conference on Neural Networks (IJCNN) 2022.7

Estimation of Needle Puncturing Form during Slight Needle Movement Based on Force Data for Robotic Automated Puncturing Function Reviewed

Takayuki Matsuno, Hikaru Murakami, Tetsushi Kamegawa, Nanako Sakai, Takao Hiraki, Yuichiro Toda

Journal of Medical Robotics Research 07 ( 02n03 ) 2022.6

Authorship：Lead author Language：English Publishing type：Research paper (scientific journal) Publisher：World Scientific Pub Co Pte Ltd

In this paper, we focused on the medical procedure to insert needles under computer tomography (CT) guidance as a target for the robotization of medical surgery, which is one of Interventional Radiology (IR). IR is a general term for treatments that use devices to visualize patients’ bodies. During surgery, our developed robot, known as Zerobot, specializes in inserting a needle into the patient under CT guidance. Its surgery is less invasive and more effective in treating small cancer tumors because the temperature of the inserted needle tip is controlled. Zerobot was originally designed to be remotely controlled by doctors, and first-in-human feasibility trials in 2018 confirmed its surgical capability. We are currently focusing on the automatic insertion function to reduce the workload of doctors. In an animal experiment, Zerobot was unable to insert the needle into the animal during IR surgery if the needle was bent. As a result, the goal of this research is to have the robot function automatically so that the needle does not bend during surgery. We propose a method for estimating the form of the needle using a force sensor. There are three different types of needle forms. Next, the proposed method distinguishes between these needle forms by measuring the difference in force sensor data when the needle root is moved slightly. In addition, we conducted tests to confirm the efficacy of the proposed method.

DOI： 10.1142/s2424905x22410045

researchmap

Growing Neural Gas with Different Topologies for 3D Space Perception

Yuichiro Toda, Akimasa Wada, Hikari Miyase, Koki Ozasa, Takayuki Matsuno, Mamoru Minami

Applied Sciences 12 ( 3 ) 1705 2022.2

Publisher：MDPI AG

<jats:p>Three-dimensional space perception is one of the most important capabilities for an autonomous mobile robot in order to operate a task in an unknown environment adaptively since the autonomous robot needs to detect the target object and estimate the 3D pose of the target object for performing given tasks efficiently. After the 3D point cloud is measured by an RGB-D camera, the autonomous robot needs to reconstruct a structure from the 3D point cloud with color information according to the given tasks since the point cloud is unstructured data. For reconstructing the unstructured point cloud, growing neural gas (GNG) based methods have been utilized in many research studies since GNG can learn the data distribution of the point cloud appropriately. However, the conventional GNG based methods have unsolved problems about the scalability and multi-viewpoint clustering. In this paper, therefore, we propose growing neural gas with different topologies (GNG-DT) as a new topological structure learning method for solving the problems. GNG-DT has multiple topologies of each property, while the conventional GNG method has a single topology of the input vector. In addition, the distance measurement in the winner node selection uses only the position information for preserving the environmental space of the point cloud. Next, we show several experimental results of the proposed method using simulation and RGB-D datasets measured by Kinect. In these experiments, we verified that our proposed method almost outperforms the other methods from the viewpoint of the quantization and clustering errors. Finally, we summarize our proposed method and discuss the future direction on this research.</jats:p>

DOI： 10.3390/app12031705

researchmap

Other Link： https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-20K19894/

Multilayer Batch Learning Growing Neural Gas for Learning Multiscale Topologies Reviewed

Yuichiro Toda, Takayuki Matsuno, Mamoru Minami

Journal of Advanced Computational Intelligence and Intelligent Informatics 25 ( 6 ) 1011 - 1023 2021.11

Publishing type：Research paper (scientific journal) Publisher：Fuji Technology Press Ltd.

Hierarchical topological structure learning methods are expected to be developed in the field of data mining for extracting multiscale topological structures from an unknown dataset. However, most methods require user-defined parameters, and it is difficult for users to determine these parameters and effectively utilize the method. In this paper, we propose a new parameter-less hierarchical topological structure learning method based on growing neural gas (GNG). First, we propose batch learning GNG (BL-GNG) to improve the learning convergence and reduce the user-designed parameters in GNG. BL-GNG uses an objective function based on fuzzy C-means to improve the learning convergence. Next, we propose multilayer BL-GNG (MBL-GNG), which is a parameter-less unsupervised learning algorithm based on hierarchical topological structure learning. In MBL-GNG, the input data of each layer uses parent nodes to learn more abstract topological structures from the dataset. Furthermore, MBL-GNG can automatically determine the number of nodes and layers according to the data distribution. Finally, we conducted several experiments to evaluate our proposed method by comparing it with other hierarchical approaches and discuss the effectiveness of our proposed method.

DOI： 10.20965/jaciii.2021.p1011

researchmap

Estimation of Needle Puncturing Form Based on Force Data during Slight Needle Movement Reviewed

Takayuki Matsuno, Hikaru Murakami, Tetsushi Kamegawa, Takaaki Miyamoto, Nanako Sakai, Mamoru Minami, Takao Hiraki

proc of 2021 International Symposium on Medical Robotics 1 - 7 2021.11

Collision detection calculation of robot to insert needles for interventional radiology Reviewed

Takayuki Matsuno, Kamegawa Tetsushi, Takao Hiraki

proc of 2021 IEEE International Conference on Advanced Robotics and Its Social Impacts (ARSO) 2021.7

Adaptive evolution strategy sample consensus for 3D reconstruction from two cameras Reviewed

Yuichiro Toda, Hsu Horng Yz, Takayuki Matsuno, Mamoru Minami, Dalin Zhou

ARTIFICIAL LIFE AND ROBOTICS 25 ( 3 ) 466 - 474 2020.8

Language：English Publishing type：Research paper (scientific journal) Publisher：SPRINGER

RANdom SAmple Consensus (RANSAC) has been applied to many 3D image processing problems such as homography matrix estimation problems and shape detection from 3D point clouds, and is one of the most popular robust estimator methods. However, RANSAC has a problem related to the trade-off between computational cost and stability of search because RANSAC is based on random sampling. In our previous work, we proposed Adaptive Evolution Strategy SAmple Consensus (A-ESSAC) as a new robust estimator, and we applied ESSAC to the homography matrix estimation for 3D SLAM using RGB-D camera. A-ESSAC is based on Evolution Strategy to maintain the genetic diversity. Furthermore, ESSAC has two heuristic searches. One is a search range control for reducing the computational cost of RANSAC. The other is adaptive/self-adaptive mutation for changing the search strategy of A-ESSAC according to the best fitness value. In this paper, we apply A-ESSAC to 3D reconstruction method using two cameras, and we show an experimental result, and discuss the effectiveness of the proposed method.

DOI： 10.1007/s10015-020-00603-9

Web of Science

researchmap

　 PREV - NEXT 　

< MATSUNO Takayuki >

Papers - MATSUNO Takayuki