Naruomi Akino - Academia.edu (original) (raw)
Papers by Naruomi Akino
Radiology, Oct 1, 2019
Purpose To evaluate the effect of a deep learning-based reconstruction (DLR) method on the conspi... more Purpose To evaluate the effect of a deep learning-based reconstruction (DLR) method on the conspicuity of hypovascular hepatic metastases on abdominal CT images. Materials and Methods This retrospective study with institutional review board approval included 58 patients with hypovascular hepatic metastases. A radiologist recorded the standard deviation of attenuation in the paraspinal muscle as the image noise and the contrast-to-noise ratio (CNR). CNR was calculated as region of interest ([ROI]L - ROIT)/N, where ROIL is the mean liver parenchyma attenuation, ROIT, the mean tumor attenuation, and N, the noise. Two other radiologists graded the conspicuity of the liver lesion on a five-point scale where 1 is unidentifiable and 5 is detected without diagnostic compromise. Only the smallest liver lesion in each patient, classified as smaller or larger than 10 mm, was evaluated. The difference between hybrid iterative reconstruction (IR) and DLR images was determined by using a two-sided Wilcoxon signed-rank test. Results The image noise was significantly lower, and the CNR was significantly higher on DLR images than hybrid IR images (median image noise: 19.2 vs 12.8 HU, P < .001; median CNR: tumors < 10 mm: 1.9 vs 2.5; tumors > 10 mm: 1.7 vs 2.2, both P < .001). The scores for liver lesions were significantly higher for DLR images than hybrid IR images (P < .01 for both in tumors smaller or larger than 10 mm). Conclusion DLR improved the quality of abdominal CT images for the evaluation of hypovascular hepatic metastases.© RSNA, 2019Supplemental material is available for this article.
Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstructi... more Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstruction" by: "T. Higaki1, Y. Nakamura1, F. Tatsugami1, M. Iida1, Z. Yu2, J. Zhou2, N. Akino3, S. Tsushima 4, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara-shi, Tochigi-ken/JP, 4Tochigi 324-8550/JP"
Japanese Journal of Radiological Technology, 2005
European Radiology, May 27, 2019
Medical Physics, Aug 5, 2020
To validate a normal resolution (NR) simulation (NRsim) algorithm that uses high resolution (HR) ... more To validate a normal resolution (NR) simulation (NRsim) algorithm that uses high resolution (HR) or super high resolution (SHR) acquisitions on a commercial high resolution CT scanner by comparing image quality between NRsim generated images and actual NR images. NRsim is intended to allow direct comparison between normal resolution CT and HR/SHR reconstructions in clinical investigations, without repeating exams. Methods: The Aquilion Precision CT (Canon Medical Systems Corporation) high resolution CT scanner has three resolution modes resulting from detector binning in the channel (x-y) and row (z) directions. For NR, each detector element is 0.5 mm 0.5 mm along the channel and row directions, 0.25 mm x 0.5 mm for HR, and 0.25 × mm x 0.25 mm for SHR. The NRsim algorithm simulates NR acquisitions from HR or SHR acquisitions (termed NR HR and NR SHR , respectively) by downsampling the pre-log raw data in the channel direction for HR/SHR acquisitions, and row direction for SHR. The downsampled data is then reconstructed using the same process as NR. The axial MTF, slice sensitivity profile (SSP) and CT number accuracy were measured using the Catphan 600 phantom, and the 3D NPS was measured in water-equivalent phantoms for standard protocols across a range of size specific dose estimates (SSDE): head (6.2-29.8 mGy), lung (2.2-18.2 mGy), and body (5.6-19.4 mGy). The MTF and NPS measurements were combined to estimate low contrast detectability (LCD) using a nonprewhitening model observer with an eye filter for a 5 mm disk with 10 HU contrast. All metrics were compared for NR, NR HR and NR SHR images reconstructed using FBP and an iterative reconstruction algorithm (AIDR3D). We chose a 15% error threshold as a reasonable definition of success for NRsim when compared against actual NR based on published studies showing that a just-noticeable difference in image noise level for human observers is typically < 15%. Accepted Article This article is protected by copyright. All rights reserved Results: The axial MTF and SSPs for NRsim were in good agreement with NR demonstrated by a maximum difference of 5.1% for the MTF at 10% and 50% across materials (air, Teflon, LDPE, and polystyrene) and a maximum SSP difference of 2.2%. Noise magnitude differences were within 15% across the SSDE levels with the exception of below 4.5 mGy for the lung protocol with FBP. The relative RMSE of normalized NPS comparisons were all < 15%. Differences in CT numbers for NRsim reconstructions were within 2 HU of NR. LCD for NRsim was within 15% of NR with the exception of NR SHR for the lung protocol SSDE levels below 3.7 mGy with FBP. Conclusions: NRsim, an algorithm for simulating NR acquisitions using HR and SHR raw data, was introduced and shown to generate images with spatial resolution, noise, HU accuracy and LCD largely equivalent to scans acquired using an actual NR acquisition. At SSDE levels below ~5 mGy for the lung protocol, differences in noise magnitude and LCD for NR SHR were > 15% which defines a region where NRsim degrades due to contributions from electronic noise.
European Radiology, Jul 16, 2022
European Journal of Radiology, Sep 1, 2023
Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Recons... more Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Reconstruction (DLR): A phantom study" by: "T. Higaki1, E. Nishimaru1, Y. Nakamura1, F. Tatsugami1, Z. Yu2, J. Zhou2, A. Prabhu Verleker3, N. Akino3, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara/JP"
IEEE transactions on radiation and plasma medical sciences, 2021
It is common for CT images to be reconstructed differently for different clinical examination pur... more It is common for CT images to be reconstructed differently for different clinical examination purposes. It is difficult for conventional filtered backprojection (FBP) methods and standard model-based iterative reconstruction (MBIR) methods to produce a single context-sensitive image without multiple reconstructions. In this article, we address this challenge by leveraging the power of deep learning. We propose to train a deep convolution neural network to reconstruct a universal image from one FBP image. We present a new data argumentation method that generates the specific training target image, specifically the feature-aware target. The resulting method, called feature-aware deep-learning reconstruction (DLR), requires only one FBP image as input and is much faster than MBIR. In experiments, we investigate one application of low-dose CT feature-aware DLR which aims to achieve noise and resolution consistency across different body parts. We evaluate the performance of the proposed method using both simulated and real clinical low-dose CT scans. The results show that our feature-aware DLR outperforms both FBP and standard MBIR by producing improved CT image quality potentially suitable for a broad range of clinical diagnoses.
Japanese Journal of Radiology
Purpose Deep learning reconstruction (DLR) has been introduced by major vendors, tested for CT ex... more Purpose Deep learning reconstruction (DLR) has been introduced by major vendors, tested for CT examinations of a variety of organs, and compared with other reconstruction methods. The purpose of this study was to compare the capabilities of DLR for image quality improvement and lung texture evaluation with those of hybrid-type iterative reconstruction (IR) for standard-, reduced- and ultra-low-dose CTs (SDCT, RDCT and ULDCT) obtained with high-definition CT (HDCT) and reconstructed at 0.25-mm, 0.5-mm and 1-mm section thicknesses with 512 × 512 or 1024 × 1024 matrixes for patients with various pulmonary diseases. Materials and methods Forty age-, gender- and body mass index-matched patients with various pulmonary diseases underwent SDCT (CT dose index volume : mean ± standard deviation, 9.0 ± 1.8 mGy), RDCT (CTDIvol: 1.7 ± 0.2 mGy) and ULDCT (CTDIvol: 0.8 ± 0.1 mGy) at a HDCT. All CT data set were then reconstructed with 512 × 512 or 1024 × 1024 matrixes by means of hybrid-type IR an...
European Radiology, Apr 11, 2019
European Journal of Radiology
Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Recons... more Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Reconstruction (DLR): A phantom study" by: "T. Higaki1, E. Nishimaru1, Y. Nakamura1, F. Tatsugami1, Z. Yu2, J. Zhou2, A. Prabhu Verleker3, N. Akino3, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara/JP"
Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstructi... more Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstruction" by: "T. Higaki1, Y. Nakamura1, F. Tatsugami1, M. Iida1, Z. Yu2, J. Zhou2, N. Akino3, S. Tsushima 4, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara-shi, Tochigi-ken/JP, 4Tochigi 324-8550/JP"
15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine
IEEE Transactions on Radiation and Plasma Medical Sciences, 2021
It is common for CT images to be reconstructed differently for different clinical examination pur... more It is common for CT images to be reconstructed differently for different clinical examination purposes. It is difficult for conventional filtered backprojection (FBP) methods and standard model-based iterative reconstruction (MBIR) methods to produce a single context-sensitive image without multiple reconstructions. In this article, we address this challenge by leveraging the power of deep learning. We propose to train a deep convolution neural network to reconstruct a universal image from one FBP image. We present a new data argumentation method that generates the specific training target image, specifically the feature-aware target. The resulting method, called feature-aware deep-learning reconstruction (DLR), requires only one FBP image as input and is much faster than MBIR. In experiments, we investigate one application of low-dose CT feature-aware DLR which aims to achieve noise and resolution consistency across different body parts. We evaluate the performance of the proposed method using both simulated and real clinical low-dose CT scans. The results show that our feature-aware DLR outperforms both FBP and standard MBIR by producing improved CT image quality potentially suitable for a broad range of clinical diagnoses.
Radiology, Oct 1, 2019
Purpose To evaluate the effect of a deep learning-based reconstruction (DLR) method on the conspi... more Purpose To evaluate the effect of a deep learning-based reconstruction (DLR) method on the conspicuity of hypovascular hepatic metastases on abdominal CT images. Materials and Methods This retrospective study with institutional review board approval included 58 patients with hypovascular hepatic metastases. A radiologist recorded the standard deviation of attenuation in the paraspinal muscle as the image noise and the contrast-to-noise ratio (CNR). CNR was calculated as region of interest ([ROI]L - ROIT)/N, where ROIL is the mean liver parenchyma attenuation, ROIT, the mean tumor attenuation, and N, the noise. Two other radiologists graded the conspicuity of the liver lesion on a five-point scale where 1 is unidentifiable and 5 is detected without diagnostic compromise. Only the smallest liver lesion in each patient, classified as smaller or larger than 10 mm, was evaluated. The difference between hybrid iterative reconstruction (IR) and DLR images was determined by using a two-sided Wilcoxon signed-rank test. Results The image noise was significantly lower, and the CNR was significantly higher on DLR images than hybrid IR images (median image noise: 19.2 vs 12.8 HU, P < .001; median CNR: tumors < 10 mm: 1.9 vs 2.5; tumors > 10 mm: 1.7 vs 2.2, both P < .001). The scores for liver lesions were significantly higher for DLR images than hybrid IR images (P < .01 for both in tumors smaller or larger than 10 mm). Conclusion DLR improved the quality of abdominal CT images for the evaluation of hypovascular hepatic metastases.© RSNA, 2019Supplemental material is available for this article.
Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstructi... more Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstruction" by: "T. Higaki1, Y. Nakamura1, F. Tatsugami1, M. Iida1, Z. Yu2, J. Zhou2, N. Akino3, S. Tsushima 4, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara-shi, Tochigi-ken/JP, 4Tochigi 324-8550/JP"
Japanese Journal of Radiological Technology, 2005
European Radiology, May 27, 2019
Medical Physics, Aug 5, 2020
To validate a normal resolution (NR) simulation (NRsim) algorithm that uses high resolution (HR) ... more To validate a normal resolution (NR) simulation (NRsim) algorithm that uses high resolution (HR) or super high resolution (SHR) acquisitions on a commercial high resolution CT scanner by comparing image quality between NRsim generated images and actual NR images. NRsim is intended to allow direct comparison between normal resolution CT and HR/SHR reconstructions in clinical investigations, without repeating exams. Methods: The Aquilion Precision CT (Canon Medical Systems Corporation) high resolution CT scanner has three resolution modes resulting from detector binning in the channel (x-y) and row (z) directions. For NR, each detector element is 0.5 mm 0.5 mm along the channel and row directions, 0.25 mm x 0.5 mm for HR, and 0.25 × mm x 0.25 mm for SHR. The NRsim algorithm simulates NR acquisitions from HR or SHR acquisitions (termed NR HR and NR SHR , respectively) by downsampling the pre-log raw data in the channel direction for HR/SHR acquisitions, and row direction for SHR. The downsampled data is then reconstructed using the same process as NR. The axial MTF, slice sensitivity profile (SSP) and CT number accuracy were measured using the Catphan 600 phantom, and the 3D NPS was measured in water-equivalent phantoms for standard protocols across a range of size specific dose estimates (SSDE): head (6.2-29.8 mGy), lung (2.2-18.2 mGy), and body (5.6-19.4 mGy). The MTF and NPS measurements were combined to estimate low contrast detectability (LCD) using a nonprewhitening model observer with an eye filter for a 5 mm disk with 10 HU contrast. All metrics were compared for NR, NR HR and NR SHR images reconstructed using FBP and an iterative reconstruction algorithm (AIDR3D). We chose a 15% error threshold as a reasonable definition of success for NRsim when compared against actual NR based on published studies showing that a just-noticeable difference in image noise level for human observers is typically < 15%. Accepted Article This article is protected by copyright. All rights reserved Results: The axial MTF and SSPs for NRsim were in good agreement with NR demonstrated by a maximum difference of 5.1% for the MTF at 10% and 50% across materials (air, Teflon, LDPE, and polystyrene) and a maximum SSP difference of 2.2%. Noise magnitude differences were within 15% across the SSDE levels with the exception of below 4.5 mGy for the lung protocol with FBP. The relative RMSE of normalized NPS comparisons were all < 15%. Differences in CT numbers for NRsim reconstructions were within 2 HU of NR. LCD for NRsim was within 15% of NR with the exception of NR SHR for the lung protocol SSDE levels below 3.7 mGy with FBP. Conclusions: NRsim, an algorithm for simulating NR acquisitions using HR and SHR raw data, was introduced and shown to generate images with spatial resolution, noise, HU accuracy and LCD largely equivalent to scans acquired using an actual NR acquisition. At SSDE levels below ~5 mGy for the lung protocol, differences in noise magnitude and LCD for NR SHR were > 15% which defines a region where NRsim degrades due to contributions from electronic noise.
European Radiology, Jul 16, 2022
European Journal of Radiology, Sep 1, 2023
Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Recons... more Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Reconstruction (DLR): A phantom study" by: "T. Higaki1, E. Nishimaru1, Y. Nakamura1, F. Tatsugami1, Z. Yu2, J. Zhou2, A. Prabhu Verleker3, N. Akino3, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara/JP"
IEEE transactions on radiation and plasma medical sciences, 2021
It is common for CT images to be reconstructed differently for different clinical examination pur... more It is common for CT images to be reconstructed differently for different clinical examination purposes. It is difficult for conventional filtered backprojection (FBP) methods and standard model-based iterative reconstruction (MBIR) methods to produce a single context-sensitive image without multiple reconstructions. In this article, we address this challenge by leveraging the power of deep learning. We propose to train a deep convolution neural network to reconstruct a universal image from one FBP image. We present a new data argumentation method that generates the specific training target image, specifically the feature-aware target. The resulting method, called feature-aware deep-learning reconstruction (DLR), requires only one FBP image as input and is much faster than MBIR. In experiments, we investigate one application of low-dose CT feature-aware DLR which aims to achieve noise and resolution consistency across different body parts. We evaluate the performance of the proposed method using both simulated and real clinical low-dose CT scans. The results show that our feature-aware DLR outperforms both FBP and standard MBIR by producing improved CT image quality potentially suitable for a broad range of clinical diagnoses.
Japanese Journal of Radiology
Purpose Deep learning reconstruction (DLR) has been introduced by major vendors, tested for CT ex... more Purpose Deep learning reconstruction (DLR) has been introduced by major vendors, tested for CT examinations of a variety of organs, and compared with other reconstruction methods. The purpose of this study was to compare the capabilities of DLR for image quality improvement and lung texture evaluation with those of hybrid-type iterative reconstruction (IR) for standard-, reduced- and ultra-low-dose CTs (SDCT, RDCT and ULDCT) obtained with high-definition CT (HDCT) and reconstructed at 0.25-mm, 0.5-mm and 1-mm section thicknesses with 512 × 512 or 1024 × 1024 matrixes for patients with various pulmonary diseases. Materials and methods Forty age-, gender- and body mass index-matched patients with various pulmonary diseases underwent SDCT (CT dose index volume : mean ± standard deviation, 9.0 ± 1.8 mGy), RDCT (CTDIvol: 1.7 ± 0.2 mGy) and ULDCT (CTDIvol: 0.8 ± 0.1 mGy) at a HDCT. All CT data set were then reconstructed with 512 × 512 or 1024 × 1024 matrixes by means of hybrid-type IR an...
European Radiology, Apr 11, 2019
European Journal of Radiology
Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Recons... more Poster: "ECR 2018 / C-1656 / Radiation dose reduction in CT using Deep Learning based Reconstruction (DLR): A phantom study" by: "T. Higaki1, E. Nishimaru1, Y. Nakamura1, F. Tatsugami1, Z. Yu2, J. Zhou2, A. Prabhu Verleker3, N. Akino3, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara/JP"
Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstructi... more Poster: "ECR 2018 / C-1653 / Possibility of deep learning technique in CT image reconstruction" by: "T. Higaki1, Y. Nakamura1, F. Tatsugami1, M. Iida1, Z. Yu2, J. Zhou2, N. Akino3, S. Tsushima 4, K. Awai1; 1Hiroshima/JP, 2Vernon Hills, IL/US, 3Otawara-shi, Tochigi-ken/JP, 4Tochigi 324-8550/JP"
15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine
IEEE Transactions on Radiation and Plasma Medical Sciences, 2021
It is common for CT images to be reconstructed differently for different clinical examination pur... more It is common for CT images to be reconstructed differently for different clinical examination purposes. It is difficult for conventional filtered backprojection (FBP) methods and standard model-based iterative reconstruction (MBIR) methods to produce a single context-sensitive image without multiple reconstructions. In this article, we address this challenge by leveraging the power of deep learning. We propose to train a deep convolution neural network to reconstruct a universal image from one FBP image. We present a new data argumentation method that generates the specific training target image, specifically the feature-aware target. The resulting method, called feature-aware deep-learning reconstruction (DLR), requires only one FBP image as input and is much faster than MBIR. In experiments, we investigate one application of low-dose CT feature-aware DLR which aims to achieve noise and resolution consistency across different body parts. We evaluate the performance of the proposed method using both simulated and real clinical low-dose CT scans. The results show that our feature-aware DLR outperforms both FBP and standard MBIR by producing improved CT image quality potentially suitable for a broad range of clinical diagnoses.