Dr. Toru Hironaka Profile

Dr. Toru Hironaka

at Massachusetts General Hospital

SPIE Involvement:

Author

Publications (25)

Proceedings Article | 2 April 2024 Presentation + Paper

3D generative AI for electronic cleansing in CT colonography

Rie Tachibana, Janne Näppi, Toru Hironaka, Masaki Okamoto, Hiroyuki Yoshida

Proceedings Volume 12931, 129310J (2024) https://doi.org/10.1117/12.3009202

KEYWORDS: 3D image processing, Virtual colonoscopy

Read Abstract +

Proceedings Article | 2 April 2024 Poster + Paper

Automated segmentation of polyps by 3D deep learning in photon-counting CT colonography

Janne Näppi, Toru Hironaka, Dufan Wu, Rajiv Gupta, Rie Tachibana, Katsuyuki Taguchi, Masaki Okamoto, Hiroyuki Yoshida

Proceedings Volume 12931, 129311C (2024) https://doi.org/10.1117/12.3007290

KEYWORDS: Artificial intelligence, Image denoising, Polyps, Image segmentation, Virtual colonoscopy, 3D image processing, Colorectal cancer, Denoising, Transformers, Cancer

Read Abstract +

Proceedings Article | 10 April 2023 Poster + Paper

Automated detection of colorectal polyps in photon-counting CT colonography

Janne Näppi, Toru Hironaka, Dufan Wu, Stephen Yoshida, Rajiv Gupta, Rie Tachibana, Katsuyuki Taguchi, Hiroyuki Yoshida

Proceedings Volume 12469, 124690T (2023) https://doi.org/10.1117/12.2654292

KEYWORDS: Computed tomography, Photon counting, Polyps, Virtual colonoscopy, Computer aided detection, Error control coding, Quantum noise, Photons, Ionizing radiation, Colorectal cancer, Colon, X-rays

Read Abstract +

Proceedings Article | 10 April 2023 Poster + Paper

Electronic cleansing in photon-counting CT colonography by use of self-supervised 3D-GAN

Rie Tachibana, Janne Näppi, Toru Hironaka, Stephen Yoshida, Dufan Wu, Rajiv Gupta, Hiroyuki Yoshida

Proceedings Volume 12469, 124690U (2023) https://doi.org/10.1117/12.2654341

KEYWORDS: Education and training, Computed tomography, Virtual colonoscopy, Gallium nitride, Colon, Image quality, 3D modeling, Contrast agents, Polyps, Scanners, Photon counting

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Presentation + Paper

Electronic cleansing by unpaired contrastive learning in non-cathartic laxative-free CT colonography

Janne Näppi, Rie Tachibana, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 12037, 120370S (2022) https://doi.org/10.1117/12.2611213

KEYWORDS: Virtual colonoscopy, 3D modeling, Computed tomography, Colorectal cancer, Colon, Cancer, Visualization, Gallium nitride, Statistical modeling, Forward error correction

Read Abstract +

Proceedings Article | 4 April 2022 Poster + Presentation + Paper

Unsupervised 3D prediction model for pulmonary disease progression in chest CT

Janne Näppi, Tomoki Uemura, Chinatsu Watari, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 12037, 120370O (2022) https://doi.org/10.1117/12.2612375

KEYWORDS: Computed tomography, 3D modeling, Chest, Data modeling, Compound parabolic concentrators, 3D image processing, Lung, Visualization, Statistical analysis, Network architectures

Read Abstract +

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Comparative performance of self-supervised 3D-ResNet-GAN for electronic cleansing in single- and dual-energy CT colonography

Rie Tachibana, Janne Näppi, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 11601, 1160116 (2021) https://doi.org/10.1117/12.2582013

KEYWORDS: Virtual colonoscopy, 3D modeling, Yield improvement, Visualization, Performance modeling, Convolution

Read Abstract +

Proceedings Article | 17 March 2020 Paper

GAN-based survival prediction model from CT images of patients with idiopathic pulmonary fibrosis

Tomoki Uemura, Chinatsu Watari, Janne Näppi, Toru Hironaka, Hyoungseop Kim, Hiroyuki Yoshida

Proceedings Volume 11318, 113181F (2020) https://doi.org/10.1117/12.2551369

KEYWORDS: Computed tomography, Chest, Pulmonary fibrosis, Performance modeling, Network architectures, Physiology, Lung, Biological research, Image analysis, 3D modeling

Read Abstract +

We developed a novel survival prediction model for images, called pix2surv, based on a conditional generative adversarial network (cGAN), and evaluated its performance based on chest CT images of patients with idiopathic pulmonary fibrosis (IPF). The architecture of the pix2surv model has a time-generator network that consists of an encoding convolutional network, a fully connected prediction network, and a discriminator network. The fully connected prediction network is trained to generate survival-time images from the chest CT images of each patient. The discriminator network is a patchbased convolutional network that is trained to differentiate the “fake pair” of a chest CT image and a generated survivaltime image from the “true pair” of an input CT image and the observed survival-time image of a patient. For evaluation, we retrospectively collected 75 IPF patients with high-resolution chest CT and pulmonary function tests. The survival predictions of the pix2surv model on these patients were compared with those of an established clinical prognostic biomarker known as the gender, age, and physiology (GAP) index by use of a two-sided t-test with bootstrapping. Concordance index (C-index) and relative absolute error (RAE) were used as measures of the prediction performance. Preliminary results showed that the survival prediction by the pix2surv model yielded more than 15% higher C-index value and more than 10% lower RAE values than those of the GAP index. The improvement in survival prediction by the pix2surv model was statistically significant (P < 0.0001). Also, the separation between the survival curves for the low- and high-risk groups was larger with pix2surv than that of the GAP index. These results show that the pix2surv model outperforms the GAP index in the prediction of the survival time and risk stratification of patients with IPF, indicating that the pix2surv model can be an effective predictor of the overall survival of patients with IPF.

Proceedings Article | 16 March 2020 Paper

U-radiomics for predicting survival of patients with idiopathic pulmonary fibrosis

Tomoki Uemura, Chinatsu Watari, Janne Näppi, Toru Hironaka, Hyoungseop Kim, Hiroyuki Yoshida

Proceedings Volume 11314, 113140T (2020) https://doi.org/10.1117/12.2551273

KEYWORDS: Computed tomography, Lung, Pulmonary fibrosis, Chest, Performance modeling

Read Abstract +

Proceedings Article | 16 March 2020 Paper

Comparative performance of 3D-DenseNet, 3D-ResNet, and 3D-VGG models in polyp detection for CT colonography

Tomoki Uemura, Janne Näppi, Toru Hironaka, Hyoungseop Kim, Hiroyuki Yoshida

Proceedings Volume 11314, 1131435 (2020) https://doi.org/10.1117/12.2549103

KEYWORDS: 3D modeling, Computer aided diagnosis and therapy, 3D image processing, Medical imaging, Performance modeling, Computed tomography, Virtual colonoscopy, Visualization, Data modeling, Solid modeling

Read Abstract +

Proceedings Article | 12 March 2020 Paper

Self-supervised generative adversarial network for electronic cleansing in dual-energy CT colonography

Rie Tachibana, Janne Näppi, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 11318, 113181E (2020) https://doi.org/10.1117/12.2549234

KEYWORDS: Colon, Virtual colonoscopy, 3D modeling, Computed tomography, Image quality, Colorectal cancer, Visualization, Data modeling, Endoscopy, Cancer

Read Abstract +

Proceedings Article | 27 March 2019 Paper

Deep radiomic precision CT imaging for prognostic biomarkers for interstitial lung diseases

Tomoki Uemura, Mikio Matsuhiro, Chinatsu Watari, Janne Näppi, Radin Nasirudin, Toru Hironaka, Yoshiki Kawata, Noboru Niki, Hiroyuki Yoshida

Proceedings Volume 10954, 109541E (2019) https://doi.org/10.1117/12.2512058

KEYWORDS: Lung, Computed tomography, Image analysis, Performance modeling, Convolutional neural networks, Pulmonary function tests, Statistical analysis, Physiology, Gallium nitride, Feature extraction

Read Abstract +

Proceedings Article | 18 March 2019 Presentation + Paper

Ensemble 3D residual network (E3D-ResNet) for reduction of false-positive polyp detections in CT colonography

Tomoki Uemura, Janne Näppi, Huimin Lu, Hyoungseop Kim, Rie Tachibana, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 10950, 1095013 (2019) https://doi.org/10.1117/12.2512173

KEYWORDS: Performance modeling, Virtual colonoscopy, Data modeling, Statistical modeling, Gallium nitride, Computed tomography, Image processing, Convolution, 3D modeling, Computer aided diagnosis and therapy

Read Abstract +

Proceedings Article | 15 March 2019 Paper

Electronic cleansing in CT colonography using a generative adversarial network

Rie Tachibana, Janne Näppi, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 10954, 1095419 (2019) https://doi.org/10.1117/12.2512466

KEYWORDS: 3D modeling, Virtual colonoscopy, Colon, Data modeling, Computed tomography, Network architectures, Colorectal cancer, Tissues, Natural surfaces

Read Abstract +

Proceedings Article | 6 March 2018 Paper

Radiomic texture-curvature (RTC) features for precision medicine of patients with rheumatoid arthritis-associated interstitial lung disease

Chinatsu Watari, Mikio Matsuhiro, Janne Näppi, Radin Nasirudin, Toru Hironaka, Yoshiki Kawata, Noboru Niki, Hiroyuki Yoshida

Proceedings Volume 10579, 105791N (2018) https://doi.org/10.1117/12.2294043

KEYWORDS: Lung, Computed tomography, Feature extraction, Chest, Pulmonary function tests

Read Abstract +

Proceedings Article | 28 February 2018 Paper

Deep radiomic prediction with clinical predictors of the survival in patients with rheumatoid arthritis-associated interstitial lung diseases

Radin Nasirudina, Janne Näppi, Chinatsu Watari, Mikio Matsuhiro, Toru Hironaka, Shoji Kido, Hiroyuki Yoshida

Proceedings Volume 10575, 105753R (2018) https://doi.org/10.1117/12.2293374

KEYWORDS: Lung, Computed tomography, Feature extraction, Performance modeling, Pulmonary function tests, Convolutional neural networks

Read Abstract +

We developed and evaluated the effect of our deep-learning-derived radiomic features, called deep radiomic features (DRFs), together with their combination with clinical predictors, on the prediction of the overall survival of patients with rheumatoid arthritis-associated interstitial lung disease (RA-ILD). We retrospectively identified 70 RA-ILD patients with thin-section lung CT and pulmonary function tests. An experienced observer delineated regions of interest (ROIs) from the lung regions on the CT images, and labeled them into one of four ILD patterns (ground-class opacity, reticulation, consolidation, and honeycombing) or a normal pattern. Small image patches centered at individual pixels on these ROIs were extracted and labeled with the class of the ROI to which the patch belonged. A deep convolutional neural network (DCNN), which consists of a series of convolutional layers for feature extraction and a series of fully connected layers, was trained and validated with 5-fold cross-validation for classifying the image patches into one of the above five patterns. A DRF vector for each patch was identified as the output of the last convolutional layer of the DCNN. Statistical moments of each element of the DRF vectors were computed to derive a DRF vector that characterizes the patient. The DRF vector was subjected to a Cox proportional hazards model with elastic-net penalty for predicting the survival of the patient. Evaluation was performed by use of bootstrapping with 2,000 replications, where concordance index (C-index) was used as a comparative performance metric. Preliminary results on clinical predictors, DRFs, and their combinations thereof showed (a) Gender and Age: C-index 64.8% [95% confidence interval (CI): 51.7, 77.9]; (b) gender, age, and physiology (GAP index): C-index: 78.5% [CI: 70.50 86.51], P < 0.0001 in comparison with (a); (c) DRFs: C-index 85.5% [CI: 73.4, 99.6], P < 0.0001 in comparison with (b); and (d) DRF and GAP: C-index 91.0% [CI: 84.6, 97.2], P < 0.0001 in comparison with (c). Kaplan-Meier survival curves of patients stratified to low- and high-risk groups based on the DRFs showed a statistically significant (P < 0.0001) difference. The DRFs outperform the clinical predictors in predicting patient survival, and a combination of the DRFs and GAP index outperforms either one of these predictors. Our results indicate that the DRFs and their combination with clinical predictors provide an accurate prognostic biomarker for patients with RA-ILD.

Proceedings Article | 27 February 2018 Presentation + Paper

Detection of colorectal masses in CT colonography: application of deep residual networks for differentiating masses from normal colon anatomy

Janne Näppi, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 10575, 1057518 (2018) https://doi.org/10.1117/12.2293848

KEYWORDS: Colon, Network architectures, Computer aided diagnosis and therapy, Virtual colonoscopy, Colorectal cancer, Computer-aided diagnosis, Neural networks, Cancer, Computing systems, Data modeling

Read Abstract +

Proceedings Article | 10 March 2017 Paper

Enhancement of weakly tagged fecal materials in dual-energy CT colonography using spectral-driven iterative reconstruction technique

Radin Nasirudin, Janne Näppi, Toru Hironaka, Rie Tachibana, Hiroyuki Yoshida

Proceedings Volume 10132, 101323N (2017) https://doi.org/10.1117/12.2255673

KEYWORDS: Computed tomography, Image enhancement, Computer aided diagnosis and therapy, Virtual colonoscopy, Iodine, Computer aided design, CT reconstruction, Tissues, Visualization, Reconstruction algorithms

Read Abstract +

Dual-energy computed tomography is used increasingly in CT colonography (CTC). The combination of computer-aided detection (CAD) and dual-energy CTC has a high clinical value because it can automatically detect clinically significant colonic lesions in CTC images with higher accuracy than does single-energy CTC. While CAD has demonstrated its ability to detect small polyps, its performance is highly dependent on the quality of the input images. The presence of artifacts such as beam hardening and image noise in ultra-low-dose CTC may severely degrade detection performance for small polyps. A further limitation to the effectiveness of CAD are the weakly tagged fecal materials in the colon that may cause false-positive detections. In this work, we developed a dual-energy method for enhancing the appearance of weakly tagged fecal materials in CTC images. The proposed method consists of two stages: 1) the detection of weakly tagged fecal materials by use of sinogram-based image decomposition and 2) the enhancement of the detected tagged fecal materials in the images using an iterative reconstruction method. In the first stage, the ultra-low-dose dual-energy projection data obtained from a CT scanner are decomposed into two basis materials – soft tissue and fecal-tagged material (iodine). Virtual monochromatic projection data are calculated from the material decomposition at a pre-determined energy. The iodine-decomposed sinogram and the virtual monochromatic projection data are then used as input to an iterative reconstruction method. In the second stage, virtual monochromatic images are reconstructed iteratively while the intensity of weakly tagged iodine in the images is enhanced. The performance of the proposed method was assessed qualitatively and quantitatively. Preliminary results show that our method effectively enhances the visual appearance of weakly tagged fecal materials in the reconstructed CT images while reducing noise and improving the overall quality of the reconstructed images.

Proceedings Article | 3 March 2017 Presentation + Paper

Deep ensemble learning of virtual endoluminal views for polyp detection in CT colonography

Kensuke Umehara, Janne Näppi, Toru Hironaka, Daniele Regge, Takayuki Ishida, Hiroyuki Yoshida

Proceedings Volume 10134, 101340G (2017) https://doi.org/10.1117/12.2255606

KEYWORDS: Virtual colonoscopy, Neural networks, Colon, Computer-aided diagnosis, Machine learning, Cancer, Convolutional neural networks, Colorectal cancer, Algorithm development, 3D image processing, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 3 March 2017 Presentation + Paper

Deep multi-spectral ensemble learning for electronic cleansing in dual-energy CT colonography

Rie Tachibana, Janne Näppi, Toru Hironaka, Se Hyung Kim, Hiroyuki Yoshida

Proceedings Volume 10134, 101340E (2017) https://doi.org/10.1117/12.2254726

KEYWORDS: Medical imaging, Image compression, Multispectral imaging, Image classification, RGB color model, Endoscopy, Virtual colonoscopy, Neural networks, Tissues, Image segmentation, Colon, Computed tomography

Read Abstract +

Proceedings Article | 3 March 2017 Presentation + Paper

Deep learning of contrast-coated serrated polyps for computer-aided detection in CT colonography

Janne Näppi, Perry Pickhardt, David Kim, Toru Hironaka, Hiroyuki Yoshida

Proceedings Volume 10134, 101340H (2017) https://doi.org/10.1117/12.2255634

KEYWORDS: Computer aided diagnosis and therapy, Computer-aided diagnosis, Virtual colonoscopy, Colon, Coating, Neural networks, Colorectal cancer, Feature extraction, Machine learning, Error control coding, Barium, Cancer, Convolutional neural networks

Read Abstract +

Proceedings Article | 3 March 2017 Paper

Electronic cleansing for CT colonography using spectral-driven iterative reconstruction

Radin Nasirudin, Janne Näppi, Toru Hironaka, Rie Tachibana, Hiroyuki Yoshida

Proceedings Volume 10134, 1013436 (2017) https://doi.org/10.1117/12.2255678

KEYWORDS: Image quality, Computer aided diagnosis and therapy, Colon, CT reconstruction, Virtual colonoscopy, Computed tomography, Computer-aided diagnosis, Reconstruction algorithms, X-ray computed tomography

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Deep learning for electronic cleansing in dual-energy CT colonography

Rie Tachibana, Janne Näppi, Toru Hironakaa, Se Hyung Kim, Hiroyuki Yoshida

Proceedings Volume 9785, 97851M (2016) https://doi.org/10.1117/12.2216446

KEYWORDS: Convolutional neural networks, Forward error correction, Tissues, Virtual colonoscopy, Medical imaging, Colon, Image compression, Iodine, Colorectal cancer, Natural surfaces

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Deep transfer learning of virtual endoluminal views for the detection of polyps in CT colonography

Janne Näppi, Toru Hironaka, Daniele Regge, Hiroyuki Yoshida

Proceedings Volume 9785, 97852B (2016) https://doi.org/10.1117/12.2217260

KEYWORDS: Convolutional neural networks, Computer aided diagnosis and therapy, Virtual colonoscopy, Colon, Data modeling, Colorectal cancer, Feature extraction, Computing systems, Cancer

Read Abstract +

Proceedings Article | 24 March 2016 Paper

Performance evaluation of multi-material electronic cleansing for ultra-low-dose dual-energy CT colonography

Rie Tachibana, Naja Kohlhase, Janne Näppi, Toru Hironaka, Junko Ota, Takayuki Ishida, Daniele Regge, Hiroyuki Yoshida

Proceedings Volume 9785, 978526 (2016) https://doi.org/10.1117/12.2217140

KEYWORDS: Cancer, Colorectal cancer, Computed tomography, Iodine, Machine learning, Medical research

Read Abstract +

Showing 5 of 25 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years