LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 103

Search options

  1. Article: Evaluation of a Generative Adversarial Network to Improve Image Quality and Reduce Radiation-Dose during Digital Breast Tomosynthesis.

    Gomi, Tsutomu / Kijima, Yukie / Kobayashi, Takayuki / Koibuchi, Yukio

    Diagnostics (Basel, Switzerland)

    2022  Volume 12, Issue 2

    Abstract: In this study, we evaluated the improvement of image quality in digital breast tomosynthesis under low-radiation dose conditions of pre-reconstruction processing using conditional generative adversarial networks [cGAN (pix2pix)]. Pix2pix pre- ... ...

    Abstract In this study, we evaluated the improvement of image quality in digital breast tomosynthesis under low-radiation dose conditions of pre-reconstruction processing using conditional generative adversarial networks [cGAN (pix2pix)]. Pix2pix pre-reconstruction processing with filtered back projection (FBP) was compared with and without multiscale bilateral filtering (MSBF) during pre-reconstruction processing. Noise reduction and preserve contrast rates were compared using full width at half-maximum (FWHM), contrast-to-noise ratio (CNR), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) in the in-focus plane using a BR3D phantom at various radiation doses [reference-dose (automatic exposure control reference dose: AECrd), 50% and 75% reduction of AECrd] and phantom thicknesses (40 mm, 50 mm, and 60 mm). The overall performance of pix2pix pre-reconstruction processing was effective in terms of FWHM, PSNR, and SSIM. At ~50% radiation-dose reduction, FWHM yielded good results independently of the microcalcification size used in the BR3D phantom, and good noise reduction and preserved contrast. PSNR results showed that pix2pix pre-reconstruction processing represented the minimum in the error with reference FBP images at an approximately 50% reduction in radiation-dose. SSIM analysis indicated that pix2pix pre-reconstruction processing yielded superior similarity when compared with and without MSBF pre-reconstruction processing at ~50% radiation-dose reduction, with features most similar to the reference FBP images. Thus, pix2pix pre-reconstruction processing is promising for reducing noise with preserve contrast and radiation-dose reduction in clinical practice.
    Language English
    Publishing date 2022-02-14
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2662336-5
    ISSN 2075-4418
    ISSN 2075-4418
    DOI 10.3390/diagnostics12020495
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  2. Article ; Online: Evaluation of a Generative Adversarial Network to Improve Image Quality and Reduce Radiation-Dose during Digital Breast Tomosynthesis

    Tsutomu Gomi / Yukie Kijima / Takayuki Kobayashi / Yukio Koibuchi

    Diagnostics, Vol 12, Iss 495, p

    2022  Volume 495

    Abstract: In this study, we evaluated the improvement of image quality in digital breast tomosynthesis under low-radiation dose conditions of pre-reconstruction processing using conditional generative adversarial networks [cGAN (pix2pix)]. Pix2pix pre- ... ...

    Abstract In this study, we evaluated the improvement of image quality in digital breast tomosynthesis under low-radiation dose conditions of pre-reconstruction processing using conditional generative adversarial networks [cGAN (pix2pix)]. Pix2pix pre-reconstruction processing with filtered back projection (FBP) was compared with and without multiscale bilateral filtering (MSBF) during pre-reconstruction processing. Noise reduction and preserve contrast rates were compared using full width at half-maximum (FWHM), contrast-to-noise ratio (CNR), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) in the in-focus plane using a BR3D phantom at various radiation doses [reference-dose (automatic exposure control reference dose: AECrd), 50% and 75% reduction of AECrd] and phantom thicknesses (40 mm, 50 mm, and 60 mm). The overall performance of pix2pix pre-reconstruction processing was effective in terms of FWHM, PSNR, and SSIM. At ~50% radiation-dose reduction, FWHM yielded good results independently of the microcalcification size used in the BR3D phantom, and good noise reduction and preserved contrast. PSNR results showed that pix2pix pre-reconstruction processing represented the minimum in the error with reference FBP images at an approximately 50% reduction in radiation-dose. SSIM analysis indicated that pix2pix pre-reconstruction processing yielded superior similarity when compared with and without MSBF pre-reconstruction processing at ~50% radiation-dose reduction, with features most similar to the reference FBP images. Thus, pix2pix pre-reconstruction processing is promising for reducing noise with preserve contrast and radiation-dose reduction in clinical practice.
    Keywords digital breast tomosynthesis ; generative adversarial networks ; radiation-dose reduction ; improve image quality ; Medicine (General) ; R5-920
    Subject code 616 ; 600
    Language English
    Publishing date 2022-02-01T00:00:00Z
    Publisher MDPI AG
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  3. Article: [Breast cancer, from diagnosis to treatment. At the conclusion of the series].

    Gomi, Tsutomu

    Nihon Hoshasen Gijutsu Gakkai zasshi

    2013  Volume 69, Issue 4, Page(s) 450

    MeSH term(s) Breast Neoplasms/diagnosis ; Breast Neoplasms/therapy ; Female ; Humans
    Language Japanese
    Publishing date 2013-04-20
    Publishing country Japan
    Document type Journal Article
    ZDB-ID 2269092-X
    ISSN 1881-4883 ; 0369-4305
    ISSN (online) 1881-4883
    ISSN 0369-4305
    DOI 10.6009/jjrt.2013_jsrt_69.4.450
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  4. Article: [Basis and image characteristics of tomosynthesis].

    Gomi, Tsutomu

    Nihon Hoshasen Gijutsu Gakkai zasshi

    2013  Volume 69, Issue 5, Page(s) 547–550

    MeSH term(s) Arthroplasty, Replacement ; Humans ; Orthopedic Procedures ; Tomography, X-Ray/methods
    Language Japanese
    Publishing date 2013-05
    Publishing country Japan
    Document type Journal Article
    ZDB-ID 2269092-X
    ISSN 1881-4883 ; 0369-4305
    ISSN (online) 1881-4883
    ISSN 0369-4305
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  5. Article ; Online: [From diagnosis of the breast to treatment. Introduction].

    Gomi, Tsutomu

    Nihon Hoshasen Gijutsu Gakkai zasshi

    2012  Volume 68, Issue 1, Page(s) 136

    MeSH term(s) Breast Diseases/diagnosis ; Breast Diseases/radiotherapy ; Diagnostic Imaging ; Female ; Humans
    Language Japanese
    Publishing date 2012-01-22
    Publishing country Japan
    Document type Introductory Journal Article
    ZDB-ID 2269092-X
    ISSN 1881-4883 ; 0369-4305
    ISSN (online) 1881-4883
    ISSN 0369-4305
    DOI 10.6009/jjrt.2012_jsrt_68.1.136
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  6. Article ; Online: A Comparison of Reconstruction Algorithms Regarding Exposure Dose Reductions during Digital Breast Tomosynthesis

    Tsutomu Gomi

    Journal of Biomedical Science and Engineering, Vol 07, Iss 08, Pp 516-

    2014  Volume 525

    Abstract: This study compared reconstruction algorithms [filtered back projection (FBP) and simultaneous iterative reconstruction technique (SIRT)] with respect to radiation doses and image quality and suggested the possibility of decreasing the exposure dose in ... ...

    Abstract This study compared reconstruction algorithms [filtered back projection (FBP) and simultaneous iterative reconstruction technique (SIRT)] with respect to radiation doses and image quality and suggested the possibility of decreasing the exposure dose in digital breast tomosynthesis (DBT). These two existing algorithms were implemented using a DBT system and experimentally evaluated using contrast-detail (CD) phantom measurements, such as contrast-to-noise ratio (CNR), root mean square error (RMSE), intensity profile, and artifact spread function (ASF), and the results obtained with FBP and SIRT were compared. The potential dose reduction, contrast improvement, quantum noise reduction, and artifact reduction in DBT were evaluated using different exposures and the two reconstruction techniques. The effectiveness of each technique for enhancing the visibility of a CD phantom was quantified with respect to CNR and RMSE, and artifact reduction was quantified with respect to the intensity profile and ASF. SIRT produced reconstructed images with CNR values indicative of high-contrast detection. Image error was smaller in the in-focus plane SIRT images, and artifacts were decreased in these images according to the determined intensity profiles and ASF. These results suggest that when using SIRT, the exposure dose could possibly be decreased to half.
    Keywords Digital Breast Tomosynthesis ; 3-Dimensional Reconstruction ; Radiation Dose ; Medicine (General) ; R5-920 ; Medicine ; R
    Subject code 616
    Language English
    Publishing date 2014-06-01T00:00:00Z
    Publisher Scientific Research Publishing
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  7. Article ; Online: [Image quality of cone-beam CT].

    Gomi, Tsutomu

    Nihon Hoshasen Gijutsu Gakkai zasshi

    2011  Volume 67, Issue 11, Page(s) 1468–1472

    MeSH term(s) Image Processing, Computer-Assisted/methods ; Phantoms, Imaging ; Quality Improvement ; Radiation Dosage ; Radiation Protection/methods ; Radiographic Image Enhancement/methods ; Tomography, X-Ray Computed/methods
    Language Japanese
    Publishing date 2011-11-17
    Publishing country Japan
    Document type Journal Article ; Research Support, Non-U.S. Gov't ; Review
    ZDB-ID 2269092-X
    ISSN 1881-4883 ; 0369-4305
    ISSN (online) 1881-4883
    ISSN 0369-4305
    DOI 10.6009/jjrt.67.1468
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  8. Article: Usefulness of a Metal Artifact Reduction Algorithm in Digital Tomosynthesis Using a Combination of Hybrid Generative Adversarial Networks.

    Gomi, Tsutomu / Sakai, Rina / Hara, Hidetake / Watanabe, Yusuke / Mizukami, Shinya

    Diagnostics (Basel, Switzerland)

    2021  Volume 11, Issue 9

    Abstract: In this study, a novel combination of hybrid generative adversarial networks (GANs) comprising cycle-consistent GAN, pix2pix, and (mask pyramid network) MPN (CGpM-metal artifact reduction [MAR]), was developed using projection data to reduce metal ... ...

    Abstract In this study, a novel combination of hybrid generative adversarial networks (GANs) comprising cycle-consistent GAN, pix2pix, and (mask pyramid network) MPN (CGpM-metal artifact reduction [MAR]), was developed using projection data to reduce metal artifacts and the radiation dose during digital tomosynthesis. The CGpM-MAR algorithm was compared with the conventional filtered back projection (FBP) without MAR, FBP with MAR, and convolutional neural network MAR. The MAR rates were compared using the artifact index (AI) and Gumbel distribution of the largest variation analysis using a prosthesis phantom at various radiation doses. The novel CGpM-MAR yielded an adequately effective overall performance in terms of AI. The resulting images yielded good results independently of the type of metal used in the prosthesis phantom (
    Language English
    Publishing date 2021-09-06
    Publishing country Switzerland
    Document type Journal Article
    ZDB-ID 2662336-5
    ISSN 2075-4418
    ISSN 2075-4418
    DOI 10.3390/diagnostics11091629
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

  9. Article ; Online: Comparison of metal artifact in digital tomosynthesis and computed tomography for evaluation of phantoms

    Tsutomu Gomi

    Journal of Biomedical Science and Engineering, Vol 06, Iss 07, Pp 722-

    2013  Volume 731

    Abstract: We compared metal artifact in X-ray digital tomosynthesis (DT) and modern computed tomography (CT) reconstruction to improve the image quality. We compared the images of a prosthetic phantom (titanium) and a contrast-detail phantom obtained by DT using ... ...

    Abstract We compared metal artifact in X-ray digital tomosynthesis (DT) and modern computed tomography (CT) reconstruction to improve the image quality. We compared the images of a prosthetic phantom (titanium) and a contrast-detail phantom obtained by DT using conventional filtered backprojection (FBP), metal artifact reduction (MAR) processing, and simultaneous iterative reconstruction technique (SIRT) methods and those obtained by CT using conventional FBP and adaptive statistical iterative reconstruction methods. The effectiveness of each method for enhancing the visibility of a prosthetic phantom was quantified in terms of the intensity profile and root mean square error, and the removal of ghosting artifacts was quantified in terms of the artifact spread function (ASF). In addition, low contrast resolution was evaluated in terms of the contrast-to- noise ratio. Image error was smaller in the MAR DT images in the near in-focus-plane, and the intensity profiles revealed the beam hardening effect. Streak artifacts were reduced in the SIRT DT and adaptive statistical iterati ve reconstruction CT images. The ASF performances of the algorithms were ranked in descending order: 1) MAR DT; 2) CT (adaptive statistical iterative reco nstruction, and conventional FBP); 3) SIRT DT; and 4) conventional FBP DT. The low contrast resolution was higher in the CT images than in the DT images. In conclusion, a review of the results revealed t hat the metal artifact reduction was highest fo r tomosynthesis with MAR processing, and the low contrast resolution performance was highest for CT.
    Keywords Tomosynthesis ; Computed Tomography ; Prosthesis ; Medicine (General) ; R5-920 ; Medicine ; R ; DOAJ:Medicine (General) ; DOAJ:Health Sciences
    Subject code 796
    Language English
    Publishing date 2013-07-01T00:00:00Z
    Publisher Scientific Research Publishing
    Document type Article ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    More links

    Kategorien

  10. Article ; Online: Use of a Total Variation Minimization Iterative Reconstruction Algorithm to Evaluate Reduced Projections during Digital Breast Tomosynthesis.

    Gomi, Tsutomu / Koibuchi, Yukio

    BioMed research international

    2018  Volume 2018, Page(s) 5239082

    Abstract: Purpose: We evaluated the efficacies of the adaptive steepest descent projection onto convex sets (ASD-POCS), simultaneous algebraic reconstruction technique (SART), filtered back projection (FBP), and maximum likelihood expectation maximization (MLEM) ... ...

    Abstract Purpose: We evaluated the efficacies of the adaptive steepest descent projection onto convex sets (ASD-POCS), simultaneous algebraic reconstruction technique (SART), filtered back projection (FBP), and maximum likelihood expectation maximization (MLEM) total variation minimization iterative algorithms for reducing exposure doses during digital breast tomosynthesis for reduced projections.
    Methods: Reconstructions were evaluated using normal (15 projections) and half (i.e., thinned-out normal) projections (seven projections). The algorithms were assessed by determining the full width at half-maximum (FWHM), and the BR3D Phantom was used to evaluate the contrast-to-noise ratio (CNR) for the in-focus plane. A mean similarity measure of structural similarity (MSSIM) was also used to identify the preservation of contrast in clinical cases.
    Results: Spatial resolution tended to deteriorate in ASD-POCS algorithm reconstructions involving a reduced number of projections. However, the microcalcification size did not affect the rate of FWHM change. The ASD-POCS algorithm yielded a high CNR independently of the simulated mass lesion size and projection number. The ASD-POCS algorithm yielded a high MSSIM in reconstructions from reduced numbers of projections.
    Conclusions: The ASD-POCS algorithm can preserve contrast despite a reduced number of projections and could therefore be used to reduce radiation doses.
    MeSH term(s) Algorithms ; Breast Neoplasms/diagnostic imaging ; Female ; Humans ; Image Processing, Computer-Assisted ; Mammography ; Phantoms, Imaging ; Radionuclide Imaging ; Tomography, X-Ray Computed
    Language English
    Publishing date 2018-06-19
    Publishing country United States
    Document type Journal Article
    ZDB-ID 2698540-8
    ISSN 2314-6141 ; 2314-6133
    ISSN (online) 2314-6141
    ISSN 2314-6133
    DOI 10.1155/2018/5239082
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

To top