Takahiro Tanaka
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
Takahiro Tanaka has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
Isao Kondoh
National Institute of Advanced Industrial Science and Technology
4 shared publicationsMikio Iwasa
National Institute of Advanced Industrial Science and Technology
3 shared publicationsNobuyuki Tamari
Osaka National Research Institute, AIST
3 shared publications- Akiyoshi Chayahara
National Institute of Advanced Industrial Science and Technology
1 shared publication Atsuko Arisawa
Department of Diagnostic and Interventional Radiology, Osaka University Graduate School of Medicine, Osaka, Japan
1 shared publication- Atsushi Nishida
Unit for Mental Health Promotion, Research Center for Social Science and Medicine, Tokyo Metropolitan Institute of Medical Science, Tokyo, Japan
1 shared publication
Latest Publications
- 6 October 2020
- Published by Springer Nature in Neuroradiology
- Vol. 63 (5) , 713-720
Improvement of the diagnostic accuracy for intracranial haemorrhage using deep learning–based computer-assisted detection
Purpose To elucidate the effect of deep learning–based computer-assisted detection (CAD) on the performance of different-level physicians in detecting intracranial haemorrhage using CT. Methods A total of 40 head CT datasets (normal, 16; haemorrhagic, 24) were evaluated by 15 physicians (5 board-certificated radiologists, 5 radiology residents, and 5 medical interns). The physicians attended 2 reading sessions without and with CAD. All physicians annotated the haemorrhagic regions with a degree of confidence, and the reading time was recorded in each case. Our CAD system was developed using 433 patients’ head CT images (normal, 203; haemorrhagic, 230), and haemorrhage rates were displayed as corresponding probability heat maps using U-Net and a machine learning–based false-positive removal method. Sensitivity, specificity, accuracy, and figure of merit (FOM) were calculated based on the annotations and confidence levels. Results In patient-based evaluation, the mean accuracy of all physicians significantly increased from 83.7 to 89.7% (p < 0.001) after using CAD. Additionally, accuracies of board-certificated radiologists, radiology residents, and interns were 92.5, 82.5, and 76.0% without CAD and 97.5, 90.5, and 81.0% with CAD, respectively. The mean FOM of all physicians increased from 0.78 to 0.82 (p = 0.004) after using CAD. The reading time was significantly lower when CAD (43 s) was used than when it was not (68 s, p < 0.001) for all physicians. Conclusion The CAD system developed using deep learning significantly improved the diagnostic performance and reduced the reading time among all physicians in detecting intracranial haemorrhage.
- 6 October 2020
- Published by Springer Nature in Neuroradiology
- Vol. 63 (5) , 713-720
Improvement of the diagnostic accuracy for intracranial haemorrhage using deep learning–based computer-assisted detection
Purpose To elucidate the effect of deep learning–based computer-assisted detection (CAD) on the performance of different-level physicians in detecting intracranial haemorrhage using CT. Methods A total of 40 head CT datasets (normal, 16; haemorrhagic, 24) were evaluated by 15 physicians (5 board-certificated radiologists, 5 radiology residents, and 5 medical interns). The physicians attended 2 reading sessions without and with CAD. All physicians annotated the haemorrhagic regions with a degree of confidence, and the reading time was recorded in each case. Our CAD system was developed using 433 patients’ head CT images (normal, 203; haemorrhagic, 230), and haemorrhage rates were displayed as corresponding probability heat maps using U-Net and a machine learning–based false-positive removal method. Sensitivity, specificity, accuracy, and figure of merit (FOM) were calculated based on the annotations and confidence levels. Results In patient-based evaluation, the mean accuracy of all physicians significantly increased from 83.7 to 89.7% (p < 0.001) after using CAD. Additionally, accuracies of board-certificated radiologists, radiology residents, and interns were 92.5, 82.5, and 76.0% without CAD and 97.5, 90.5, and 81.0% with CAD, respectively. The mean FOM of all physicians increased from 0.78 to 0.82 (p = 0.004) after using CAD. The reading time was significantly lower when CAD (43 s) was used than when it was not (68 s, p < 0.001) for all physicians. Conclusion The CAD system developed using deep learning significantly improved the diagnostic performance and reduced the reading time among all physicians in detecting intracranial haemorrhage.
- 1 August 2018
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 55, 56-66
Iterative applications of image completion with CNN-based failure detection
- 1 August 2018
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 55, 56-66
Iterative applications of image completion with CNN-based failure detection
- Open Access
- 1 January 2011
- Published by Japanese Society for Dental Materials and Devices in Dental Materials Journal
- Vol. 30 (2) , 170-175
Silica film coating method for veneering resin composite
The preceramic polymer perhydropolysilazane (PHPS) is an attractive candidate as a coating material to prevent discoloration of veneering resin composites. At the present time, however, a practical method to apply this material is not available. The purpose of this study was to establish a low-temperature method for applying a silica film coating to a veneering resin composite. Two types of PHPS, NP and NL, were coated onto a veneering resin composite. The specimens were exposed to hydrogen peroxide vapor at 97°C, and the state of the conversion process was evaluated using FT-IR. With exposure to the hydrogen peroxide vapor, a 0.5-μm-thick silica film similar to that produced by baking was formed on the surface of the NP samples in 10 min, while a 0.2-μm-thick film was formed on the NL in 15 min. The silica coating method described in this study may mitigate the discoloration of veneering resin composite.
- 1 January 2011
- Published by Japanese Society for Dental Materials and Devices in Dental Materials Journal
- Vol. 30 (2) , 170-175
Open AccessSilica film coating method for veneering resin composite
The preceramic polymer perhydropolysilazane (PHPS) is an attractive candidate as a coating material to prevent discoloration of veneering resin composites. At the present time, however, a practical method to apply this material is not available. The purpose of this study was to establish a low-temperature method for applying a silica film coating to a veneering resin composite. Two types of PHPS, NP and NL, were coated onto a veneering resin composite. The specimens were exposed to hydrogen peroxide vapor at 97°C, and the state of the conversion process was evaluated using FT-IR. With exposure to the hydrogen peroxide vapor, a 0.5-μm-thick silica film similar to that produced by baking was formed on the surface of the NP samples in 10 min, while a 0.2-μm-thick film was formed on the NL in 15 min. The silica coating method described in this study may mitigate the discoloration of veneering resin composite.
- 1 February 2003
- Published by Elsevier in Scripta Materialia
- Vol. 48 (4) , 437-441
Preparation and mechanical properties of Al2O3–15wt.%ZrO2 composites
- 1 February 2003
- Published by Elsevier in Scripta Materialia
- Vol. 48 (4) , 437-441
Preparation and mechanical properties of Al2O3–15wt.%ZrO2 composites
- 1 January 2003
- Published by Elsevier in Ceramics International
- Vol. 29 (2) , 209-212
Centrifugal casting of Al2O3–15 wt.%ZrO2 ceramic composites
- 1 January 2003
- Published by Elsevier in Ceramics International
- Vol. 29 (2) , 209-212
Centrifugal casting of Al2O3–15 wt.%ZrO2 ceramic composites
- Open Access
- 1 January 2000
- Published by Japan Society of Mechanical Engineers in TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series A
- Vol. 66 (645) , 1008-1014
Green's Functions for Axisymmetric Body Force Problems of an Elastic Thick Infinite Plate and Their Application. Compression of a Thick Plate with a Spherical Cavity.
- 1 January 2000
- Published by Japan Society of Mechanical Engineers in TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series A
- Vol. 66 (645) , 1008-1014
Open AccessGreen's Functions for Axisymmetric Body Force Problems of an Elastic Thick Infinite Plate and Their Application. Compression of a Thick Plate with a Spherical Cavity.
- 1 January 1997
- Published by Elsevier in Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms
- Vol. 121 (1-4) , 335-339
Ultramicrohardness measurement of ion implanted alumina
- 1 January 1997
- Published by Elsevier in Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms
- Vol. 121 (1-4) , 335-339
Ultramicrohardness measurement of ion implanted alumina
- 1 January 1996
- Published by Ceramic Society of Japan in Journal of the Ceramic Society of Japan
- Vol. 104 (1209) , 454-457
Fabrication and Mechanical Properties of 3-Dimensional Tyranno Fiber Reinforced SiC Composites by Repeated Infiltration of Polycarbosilane
- 1 January 1996
- Published by Ceramic Society of Japan in Journal of the Ceramic Society of Japan
- Vol. 104 (1209) , 454-457
Fabrication and Mechanical Properties of 3-Dimensional Tyranno Fiber Reinforced SiC Composites by Repeated Infiltration of Polycarbosilane
- 1 January 1995
- Published by Ceramic Society of Japan in Journal of the Ceramic Society of Japan
- Vol. 103 (1193) , 1-5
Fabrication and Evaluation of 3-Dimensional Tyranno Fiber Reinforced SiC Composites by Repeated Infiltration of Polycarbosilane
- 1 January 1995
- Published by Ceramic Society of Japan in Journal of the Ceramic Society of Japan
- Vol. 103 (1193) , 1-5
Fabrication and Evaluation of 3-Dimensional Tyranno Fiber Reinforced SiC Composites by Repeated Infiltration of Polycarbosilane