Michitaka Fujiwara
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Michitaka Fujiwara has a total of 188 co-authors. Here are the top co-authors by number of shared publications:
- Yasuhiro Kodera
NHO Nagoya Medical Center, Nagoya, Japan
45 shared publications - Masahiko Koike
Nagoya University Graduate School of Medicine
37 shared publications - Suguru Yamada
Department of Gastroenterological Surgery, Nagoya Central Hospital, Nagoya, Japan
34 shared publications - Tsutomu Fujii
Department of Surgery and Science, Faculty of Medicine, Academic Assembly, University of Toyama, Toyama, Japan
33 shared publications - Mitsuro Kanda
Department of Gastroenterological Surgery Nagoya University Graduate School of Medicine Nagoya Japan
27 shared publications - Goro Nakayama
Department of Gastroenterological Surgery, Nagoya University Graduate School of Medicine, Nagoya, Japan
26 shared publications
Latest Publications
- Open Access
- 30 October 2026
- Published by JMIR Publications Inc. in JMIR XR and Spatial Computing
- Vol. 3, e103880
Real-Time Integration of Bronchoscope Video and 3D Airway Models on Apple Vision Pro: Phantom Feasibility Study
This single-operator phantom study demonstrates the technical feasibility of colocating a live bronchoscope video stream with patient-specific 3D airway models on Apple Vision Pro using a native Network Device Interface pipeline, without establishing comparative or clinical benefit.
- 30 October 2026
- Published by JMIR Publications Inc. in JMIR XR and Spatial Computing
- Vol. 3, e103880
Open AccessReal-Time Integration of Bronchoscope Video and 3D Airway Models on Apple Vision Pro: Phantom Feasibility Study
This single-operator phantom study demonstrates the technical feasibility of colocating a live bronchoscope video stream with patient-specific 3D airway models on Apple Vision Pro using a native Network Device Interface pipeline, without establishing comparative or clinical benefit.
- Open Access
- 1 April 2025
- Published by Oxford University Press (OUP) in Annals of the American Thoracic Society
- Vol. 22 (4) , 609-611
Clinical Applicability of Three-Dimensional Holographic Virtual Bronchoscopy with Mixed Reality
- 1 April 2025
- Published by Oxford University Press (OUP) in Annals of the American Thoracic Society
- Vol. 22 (4) , 609-611
Open AccessClinical Applicability of Three-Dimensional Holographic Virtual Bronchoscopy with Mixed Reality
- Open Access
- 12 September 2024
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 20 (1) , 77-87
Skeleton-guided 3D convolutional neural network for tubular structure segmentation
Purpose: Accurate segmentation of tubular structures is crucial for clinical diagnosis and treatment but is challenging due to their complex branching structures and volume imbalance. The purpose of this study is to propose a 3D deep learning network that incorporates skeleton information to enhance segmentation accuracy in these tubular structures. Methods: Our approach employs a 3D convolutional network to extract 3D tubular structures from medical images such as CT volumetric images. We introduce a skeleton-guided module that operates on extracted features to capture and preserve the skeleton information in the segmentation results. Additionally, to effectively train our deep model in leveraging skeleton information, we propose a sigmoid-adaptive Tversky loss function which is specifically designed for skeleton segmentation. Results: We conducted experiments on two distinct 3D medical image datasets. The first dataset consisted of 90 cases of chest CT volumetric images, while the second dataset comprised 35 cases of abdominal CT volumetric images. Comparative analysis with previous segmentation approaches demonstrated the superior performance of our method. For the airway segmentation task, our method achieved an average tree length rate of 93.0%, a branch detection rate of 91.5%, and a precision rate of 90.0%. In the case of abdominal artery segmentation, our method attained an average precision rate of 97.7%, a recall rate of 91.7%, and an F-measure of 94.6%. Conclusion: We present a skeleton-guided 3D convolutional network to segment tubular structures from 3D medical images. Our skeleton-guided 3D convolutional network could effectively segment small tubular structures, outperforming previous methods.
- 12 September 2024
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 20 (1) , 77-87
Open AccessSkeleton-guided 3D convolutional neural network for tubular structure segmentation
Purpose: Accurate segmentation of tubular structures is crucial for clinical diagnosis and treatment but is challenging due to their complex branching structures and volume imbalance. The purpose of this study is to propose a 3D deep learning network that incorporates skeleton information to enhance segmentation accuracy in these tubular structures. Methods: Our approach employs a 3D convolutional network to extract 3D tubular structures from medical images such as CT volumetric images. We introduce a skeleton-guided module that operates on extracted features to capture and preserve the skeleton information in the segmentation results. Additionally, to effectively train our deep model in leveraging skeleton information, we propose a sigmoid-adaptive Tversky loss function which is specifically designed for skeleton segmentation. Results: We conducted experiments on two distinct 3D medical image datasets. The first dataset consisted of 90 cases of chest CT volumetric images, while the second dataset comprised 35 cases of abdominal CT volumetric images. Comparative analysis with previous segmentation approaches demonstrated the superior performance of our method. For the airway segmentation task, our method achieved an average tree length rate of 93.0%, a branch detection rate of 91.5%, and a precision rate of 90.0%. In the case of abdominal artery segmentation, our method attained an average precision rate of 97.7%, a recall rate of 91.7%, and an F-measure of 94.6%. Conclusion: We present a skeleton-guided 3D convolutional network to segment tubular structures from 3D medical images. Our skeleton-guided 3D convolutional network could effectively segment small tubular structures, outperforming previous methods.
- Open Access
- 11 March 2024
- Published by Medical Communications Sp. z.o.o. in Journal of Ultrasonography
- Vol. 24 (96) , 20240012
Real-time ultrasound-guided thoracentesis simulation using an optical see-through head-mounted display: a proof-of-concept study
Aim This study aimed to examine the feasibility and potential benefits of an optical see-through head-mounted display (OST-HMD) during real-time ultrasound-guided thoracentesis simulations. Material and methods Six physicians performed a thoracentesis simulation using an OST-HMD and a wireless image transmission system. The time required, puncture needle visibility, pleural fluid collection success rate, and head movement during the procedure using a smart glass equipped with an inertial measurement unit were all recorded and compared with and without the HMD. Results Study participants successfully extracted effusions in all procedures. The use of OST-HMD did not significantly affect the time of the procedure, but notably decreased the horizontal and vertical head movements during the procedure. Conclusions The study demonstrated the feasibility of using an OST-HMD in a simulated real-time ultrasound-guided thoracentesis procedure and showed the potential of HMD in thoracentesis to improve ergonomics and accuracy. Further research is necessary to confirm these findings.
- 11 March 2024
- Published by Medical Communications Sp. z.o.o. in Journal of Ultrasonography
- Vol. 24 (96) , 20240012
Open AccessReal-time ultrasound-guided thoracentesis simulation using an optical see-through head-mounted display: a proof-of-concept study
Aim This study aimed to examine the feasibility and potential benefits of an optical see-through head-mounted display (OST-HMD) during real-time ultrasound-guided thoracentesis simulations. Material and methods Six physicians performed a thoracentesis simulation using an OST-HMD and a wireless image transmission system. The time required, puncture needle visibility, pleural fluid collection success rate, and head movement during the procedure using a smart glass equipped with an inertial measurement unit were all recorded and compared with and without the HMD. Results Study participants successfully extracted effusions in all procedures. The use of OST-HMD did not significantly affect the time of the procedure, but notably decreased the horizontal and vertical head movements during the procedure. Conclusions The study demonstrated the feasibility of using an OST-HMD in a simulated real-time ultrasound-guided thoracentesis procedure and showed the potential of HMD in thoracentesis to improve ergonomics and accuracy. Further research is necessary to confirm these findings.
- 22 October 2022
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 18 (3) , 1-12
A skeleton context-aware 3D fully convolutional network for abdominal artery segmentation
Purpose This paper aims to propose a deep learning-based method for abdominal artery segmentation. Blood vessel structure information is essential to diagnosis and treatment. Accurate blood vessel segmentation is critical to preoperative planning. Although deep learning-based methods perform well on large organs, segmenting small organs such as blood vessels is challenging due to complicated branching structures and positions. We propose a 3D deep learning network from a skeleton context-aware perspective to improve segmentation accuracy. In addition, we propose a novel 3D patch generation method which could strengthen the structural diversity of a training data set. Method The proposed method segments abdominal arteries from an abdominal computed tomography (CT) volume using a 3D fully convolutional network (FCN). We add two auxiliary tasks to the network to extract the skeleton context of abdominal arteries. In addition, our skeleton-based patch generation (SBPG) method further enables the FCN to segment small arteries. SBPG generates a 3D patch from a CT volume by leveraging artery skeleton information. These methods improve the segmentation accuracies of small arteries. Results We used 20 cases of abdominal CT volumes to evaluate the proposed method. The experimental results showed that our method outperformed previous segmentation accuracies. The averaged precision rate, recall rate, and F-measure were 95.5%, 91.0%, and 93.2%, respectively. Compared to a baseline method, our method improved 1.5% the averaged recall rate and 0.7% the averaged F-measure. Conclusions We present a skeleton context-aware 3D FCN to segment abdominal arteries from an abdominal CT volume. In addition, we propose a 3D patch generation method. Our fully automated method segmented most of the abdominal artery regions. The method produced competitive segmentation performance compared to previous methods.
- 22 October 2022
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 18 (3) , 1-12
A skeleton context-aware 3D fully convolutional network for abdominal artery segmentation
Purpose This paper aims to propose a deep learning-based method for abdominal artery segmentation. Blood vessel structure information is essential to diagnosis and treatment. Accurate blood vessel segmentation is critical to preoperative planning. Although deep learning-based methods perform well on large organs, segmenting small organs such as blood vessels is challenging due to complicated branching structures and positions. We propose a 3D deep learning network from a skeleton context-aware perspective to improve segmentation accuracy. In addition, we propose a novel 3D patch generation method which could strengthen the structural diversity of a training data set. Method The proposed method segments abdominal arteries from an abdominal computed tomography (CT) volume using a 3D fully convolutional network (FCN). We add two auxiliary tasks to the network to extract the skeleton context of abdominal arteries. In addition, our skeleton-based patch generation (SBPG) method further enables the FCN to segment small arteries. SBPG generates a 3D patch from a CT volume by leveraging artery skeleton information. These methods improve the segmentation accuracies of small arteries. Results We used 20 cases of abdominal CT volumes to evaluate the proposed method. The experimental results showed that our method outperformed previous segmentation accuracies. The averaged precision rate, recall rate, and F-measure were 95.5%, 91.0%, and 93.2%, respectively. Compared to a baseline method, our method improved 1.5% the averaged recall rate and 0.7% the averaged F-measure. Conclusions We present a skeleton context-aware 3D FCN to segment abdominal arteries from an abdominal CT volume. In addition, we propose a 3D patch generation method. Our fully automated method segmented most of the abdominal artery regions. The method produced competitive segmentation performance compared to previous methods.
- 23 August 2021
- Published by Wiley in The International Journal of Medical Robotics and Computer Assisted Surgery
- Vol. 17 (6) , e2325
SuP‐Ring: A pneumatic tactile display with substitutional representation of contact force components using normal indentation
Background: Shear force is important for tumour detection and can contribute to minimally invasive surgery (MIS). A popular method uses lateral skin stretch to produce shear force but has some limitations.Methods: We have developed a ring‐type pneumatic tactile display that employs normal indentation substituted for lateral skin stretch to represent normal and shear feedback, called SuP‐Ring. Psychophysical experiments were conducted to evaluate how users perceive the provided feedback and the effectiveness of SuP‐Ring in tumour localisation.Results: The experimental results show that the participants could perceive the provided normal and shear feedback well. Shear feedback enables users to enhance their performance in localising the tumour and normal feedback could contribute to ensuring the safety requirements in MIS.Conclusions: The proposed tactile display could be useful for intraoperative tumour localisation and has the potential to be used in a wide variety of applications.
- 23 August 2021
- Published by Wiley in The International Journal of Medical Robotics and Computer Assisted Surgery
- Vol. 17 (6) , e2325
SuP‐Ring: A pneumatic tactile display with substitutional representation of contact force components using normal indentation
Background: Shear force is important for tumour detection and can contribute to minimally invasive surgery (MIS). A popular method uses lateral skin stretch to produce shear force but has some limitations.Methods: We have developed a ring‐type pneumatic tactile display that employs normal indentation substituted for lateral skin stretch to represent normal and shear feedback, called SuP‐Ring. Psychophysical experiments were conducted to evaluate how users perceive the provided feedback and the effectiveness of SuP‐Ring in tumour localisation.Results: The experimental results show that the participants could perceive the provided normal and shear feedback well. Shear feedback enables users to enhance their performance in localising the tumour and normal feedback could contribute to ensuring the safety requirements in MIS.Conclusions: The proposed tactile display could be useful for intraoperative tumour localisation and has the potential to be used in a wide variety of applications.
- 25 November 2020
- Published by Springer Nature
- p. 17-26
Forceps-Type Palpation System for Laparoscopic Surgery
- 25 November 2020
- Published by Springer Nature
- p. 17-26
Forceps-Type Palpation System for Laparoscopic Surgery
- 1 September 2020
- Published by Springer Nature in Annals of Surgical Oncology
- Vol. 28 (4) , 2277-2286
Peritoneal Lavage Tumor DNA as a Novel Biomarker for Predicting Peritoneal Recurrence in Pancreatic Ductal Adenocarcinoma
The clinical role of peritoneal lavage cytology (CY) in pancreatic ductal adenocarcinoma (PDAC) remains controversial, partly due to its low sensitivity. T
- 1 September 2020
- Published by Springer Nature in Annals of Surgical Oncology
- Vol. 28 (4) , 2277-2286
Peritoneal Lavage Tumor DNA as a Novel Biomarker for Predicting Peritoneal Recurrence in Pancreatic Ductal Adenocarcinoma
The clinical role of peritoneal lavage cytology (CY) in pancreatic ductal adenocarcinoma (PDAC) remains controversial, partly due to its low sensitivity. T
- 1 February 2020
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 38 (4_suppl) , 447
Predictive value of the modified systemic inflammation score in patients undergoing curative resection of squamous cell carcinoma of the esophagus.
447 Background: Inflammation plays a critical role in the development and progression of cancers. Here we aimed to evaluate the clinical significance of the preoperative modified systemic inflammation score (mSIS) to predict long-term outcomes of patients with esophageal squamous cell carcinoma (ESCC). Methods: We included 443 patients who underwent curative resection of ESCC. The mSIS was formulated according to the serum albumin level (ALB) and lymphocyte-to-monocyte ratio (LMR) as follows: mSIS 0 (ALB ≥4.0 g/dL and LMR ≥3.4), mSIS 1 (ALB < 4.0 g/dL or LMR < 3.4), and mSIS 2 ( ALB < 4.0 g/dL and LMR < 3.4). Results: Patients were categorized into preoperative mSIS 0 (n = 165), mSIS 1 (n = 183), and mSIS 2 (n = 95) groups. Preoperative mSIS was significantly associated with age, preoperative body mass index, and pathological disease stage. The disease-specific survival times of patients in preoperative mSIS 0, 1, and 2 sequentially shortened (P = 0.009), and mSIS 2 was identified as an independent prognostic factor (hazard ratio 2.63, 95% confidence interval 1.33–5.27, P = 0.0053). In most patient subgroups, the mSIS was associated with greater risk of disease-specific death. A stepwise increase in the prevalence of hematogenous recurrences was directly proportion to the mSIS. When patients were subdivided by mSIS before neoadjuvant treatment, there were no significant differences in disease-specific survival. Conclusions: Our findings demonstrate that the preoperative mSIS may serve as a powerful prognosticator of ESCC that definitively stratifies clinical outcomes as well as a tool for selecting treatment strategies.
- 1 February 2020
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 38 (4_suppl) , 447
Predictive value of the modified systemic inflammation score in patients undergoing curative resection of squamous cell carcinoma of the esophagus.
447 Background: Inflammation plays a critical role in the development and progression of cancers. Here we aimed to evaluate the clinical significance of the preoperative modified systemic inflammation score (mSIS) to predict long-term outcomes of patients with esophageal squamous cell carcinoma (ESCC). Methods: We included 443 patients who underwent curative resection of ESCC. The mSIS was formulated according to the serum albumin level (ALB) and lymphocyte-to-monocyte ratio (LMR) as follows: mSIS 0 (ALB ≥4.0 g/dL and LMR ≥3.4), mSIS 1 (ALB < 4.0 g/dL or LMR < 3.4), and mSIS 2 ( ALB < 4.0 g/dL and LMR < 3.4). Results: Patients were categorized into preoperative mSIS 0 (n = 165), mSIS 1 (n = 183), and mSIS 2 (n = 95) groups. Preoperative mSIS was significantly associated with age, preoperative body mass index, and pathological disease stage. The disease-specific survival times of patients in preoperative mSIS 0, 1, and 2 sequentially shortened (P = 0.009), and mSIS 2 was identified as an independent prognostic factor (hazard ratio 2.63, 95% confidence interval 1.33–5.27, P = 0.0053). In most patient subgroups, the mSIS was associated with greater risk of disease-specific death. A stepwise increase in the prevalence of hematogenous recurrences was directly proportion to the mSIS. When patients were subdivided by mSIS before neoadjuvant treatment, there were no significant differences in disease-specific survival. Conclusions: Our findings demonstrate that the preoperative mSIS may serve as a powerful prognosticator of ESCC that definitively stratifies clinical outcomes as well as a tool for selecting treatment strategies.
- Open Access
- 1 January 2020
- Published by XMLink in Journal of Gastric Cancer
- Vol. 20 (1) , 41-49
Association between Lymphovascular Invasion and Recurrence in Patients with pT1N+ or pT2–3N0 Gastric Cancer: a Multi-institutional Dataset Analysis
Fujita K, et al. J Gastric Cancer. 2019 Sep;20:e3. https://doi.org/10.5230/jgc.2020.20.e3
- 1 January 2020
- Published by XMLink in Journal of Gastric Cancer
- Vol. 20 (1) , 41-49
Open AccessAssociation between Lymphovascular Invasion and Recurrence in Patients with pT1N+ or pT2–3N0 Gastric Cancer: a Multi-institutional Dataset Analysis
Fujita K, et al. J Gastric Cancer. 2019 Sep;20:e3. https://doi.org/10.5230/jgc.2020.20.e3