Takumi Ino

Mr. Takumi Ino

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 December 2023 in Sensors
Verified
Journal Article
Open access
PDF file
TITakumi Ino
Takumi Ino
MSMina Samukawa
Mina Samukawa
TITomoya Ishida
Tomoya Ishida
NWNaofumi Wada
Naofumi Wada
YKYuta Koshino
Yuta Koshino
HTHarukazu Tohyama
Harukazu Tohyama
Accuracy validation of gait analysis using pose estimation with artificial intelligence (AI) remains inadequate, particularly in objective assessments of absolute error and similarity of waveform patterns. This study aimed to clarify objective measures for absolute error and waveform pattern similarity in gait analysis using pose estimation AI (OpenPose). Additionally, we investigated the feasibility of simultaneous measuring both lower limbs using a single camera from one side. We compared motion analysis data from pose estimation AI using video footage that was synchronized with a three-dimensional motion analysis device. The comparisons involved mean absolute error (MAE) and the coefficient of multiple correlation (CMC) to compare the waveform pattern similarity. The MAE ranged from 2.3 to 3.1° on the camera side and from 3.1 to 4.1° on the opposite side, with slightly higher accuracy on the camera side. Moreover, the CMC ranged from 0.936 to 0.994 on the camera side and from 0.890 to 0.988 on the opposite side, indicating a “very good to excellent” waveform similarity. Gait analysis using a single camera revealed that the precision on both sides was sufficiently robust for clinical evaluation, while measurement accuracy was slightly superior on the camera side.

9 September 2024 in Journal of Sports Science and Medicine
Verified
Journal Article
Open access
PDF file
TITakumi Ino
Takumi Ino
MSMina Samukawa
Mina Samukawa
TITomoya Ishida
Tomoya Ishida
NWNaofumi Wada
Naofumi Wada
YKYuta Koshino
Yuta Koshino
HTHarukazu Tohyama
Harukazu Tohyama
OpenPose-based motion analysis (OpenPose-MA), utilizing deep learning methods, has emerged as a compelling technique for estimating human motion. It addresses the drawbacks associated with conventional three-dimensional motion analysis (3D-MA) and human visual detection-based motion analysis (Human-MA), including costly equipment, time-consuming analysis, and restricted experimental settings. This study aims to assess the precision of OpenPose-MA in comparison to Human-MA, using 3D-MA as the reference standard. The study involved a cohort of 21 young and healthy adults. OpenPose-MA employed the OpenPose algorithm, a deep learning-based open-source two-dimensional (2D) pose estimation method. Human-MA was conducted by a skilled physiotherapist. The knee valgus angle during a drop vertical jump task was computed by OpenPose-MA and Human-MA using the same frontal-plane video image, with 3D-MA serving as the reference standard. Various metrics were utilized to assess the reproducibility, accuracy and similarity of the knee valgus angle between the different methods, including the intraclass correlation coefficient (ICC) (1, 3), mean absolute error (MAE), coefficient of multiple correlation (CMC) for waveform pattern similarity, and Pearson’s correlation coefficients (OpenPose-MA vs. 3D-MA, Human-MA vs. 3D-MA). Unpaired t-tests were conducted to compare MAEs and CMCs between OpenPose-MA and Human-MA. The ICCs (1,3) for OpenPose-MA, Human-MA, and 3D-MA demonstrated excellent reproducibility in the DVJ trial. No significant difference between OpenPose-MA and Human-MA was observed in terms of the MAEs (OpenPose: 2.4° [95%CI: 1.9-3.0°], Human: 3.2° [95%CI: 2.1-4.4°]) or CMCs (OpenPose: 0.83 [range: 0.99-0.53], Human: 0.87 [range: 0.24-0.98]) of knee valgus angles. The Pearson’s correlation coefficients of OpenPose-MA and Human-MA relative to that of 3D-MA were 0.97 and 0.98, respectively. This study demonstrated that OpenPose-MA achieved satisfactory reproducibility, accuracy and exhibited waveform similarity comparable to 3D-MA, similar to Human-MA. Both OpenPose-MA and Human-MA showed a strong correlation with 3D-MA in terms of knee valgus angle excursion.

1 January 2015 in Journal of Physical Therapy Science
Verified
Journal Article
Open access
PDF file
TITakumi Ino
Takumi Ino
YOYasumitsu Ohkoshi
Yasumitsu Ohkoshi
TMTatsunori Maeda
Tatsunori Maeda
KKKensaku Kawakami
Kensaku Kawakami
SSShoji Suzuki
Shoji Suzuki
HTHarukazu Tohyama
Harukazu Tohyama
Japan's largest platform for academic e-journals: J-STAGE is a full text database for reviewed academic papers published by Japanese societies

1 February 2023 in Journal of Applied Biomechanics
Verified
Journal Article
Closed access
TITomoya Ishida
Tomoya Ishida
MSMina Samukawa
Mina Samukawa
YKYuta Koshino
Yuta Koshino
TITakumi Ino
Takumi Ino
SKSatoshi Kasahara
Satoshi Kasahara
HTHarukazu Tohyama
Harukazu Tohyama
Asymmetry in knee extensor moment during double-leg squatting was observed after anterior cruciate ligament reconstruction, even after the completion of the rehabilitation program for return to sports. The purpose of this study was to clarify the association between asymmetry in the knee extensor moment and pelvic rotation angle during double-leg squatting after anterior cruciate ligament reconstruction. Twenty-four participants performed double-leg squatting. Kinetics and kinematics during squatting were analyzed using a 3-dimensional motion analysis system with 2 force plates. The limb symmetry index of knee extensor moment was predicted by the pelvic rotation angle (R2 = .376, P = .001). In addition, the pelvic rotation and the limb symmetry index of the vertical ground reaction force independently explained the limb symmetry index of the knee extensor moment (R2 = .635, P < .001, β of pelvic rotation = −0.489, β of vertical ground reaction force = 0.524). Pelvic rotation toward the involved limb was associated with a smaller knee extensor moment in the involved limb than in the uninvolved limb. The assessment of pelvic rotation would be useful for partially predicting asymmetry in the knee extensor moment during double-leg squatting. Minimizing pelvic rotation may improve the asymmetry in the knee extensor moment during double-leg squatting after anterior cruciate ligament reconstruction.

1 August 2023 in Journal of Applied Biomechanics
Verified
Journal Article
Closed access
PDF file
MCMasato Chijimatsu
Masato Chijimatsu
TITomoya Ishida
Tomoya Ishida
MYMasanori Yamanaka
Masanori Yamanaka
STShohei Taniguchi
Shohei Taniguchi
RURyo Ueno
Ryo Ueno
HTHarukazu Tohyama
Harukazu Tohyama
Single-leg landings with or without subsequent jumping are frequently used to evaluate landing biomechanics. The purpose of this study was to investigate the effects of subsequent jumping on the external knee abduction moment and trunk and hip biomechanics during single-leg landing. Thirty young adult female participants performed a single-leg drop vertical jumping (SDVJ; landing with subsequent jumping) and single-leg drop landing (SDL; landing without subsequent jumping). Trunk, hip, and knee biomechanics were evaluated using a 3-dimensional motion analysis system. The peak knee abduction moment was significantly larger during SDVJ than during SDL (SDVJ 0.08 [0.10] N·m·kg−1·m−1, SDL 0.05 [0.10] N·m·kg−1·m−1, P = .002). The trunk lateral tilt and rotation angles toward the support-leg side and external hip abduction moment were significantly larger during SDVJ than during SDL (P < .05). The difference in the peak hip abduction moment between SDVJ and SDL predicted the difference in the peak knee abduction moment (P = .003, R 2 = .252). Landing tasks with subsequent jumping would have advantages for evaluating trunk and hip control as well as knee abduction moment. In particular, evaluating hip abduction moment may be important because of its association with the knee abduction moment.

7 March 2025 in Journal of Bodywork and Movement Therapies
Verified
Journal Article
Closed access
TITomonobu Ishigaki
Tomonobu Ishigaki
TITomoya Ishida
Tomoya Ishida
TITakumi Ino
Takumi Ino
TOTakumi Okunuki
Takumi Okunuki
HYHiroko Yokoyama
Hiroko Yokoyama
Mutsuaki EdamaMutsuaki Edama
Mutsuaki Edama