Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications
The reconstruction of computed tomography (CT) images is an active area of research. Following the rise of deep learning methods, many data-driven models have been proposed in recent years. In this work, we present the results of a <i>data challenge</i> that we organized, bringing togeth...
| Main Authors: | , , , , , , , , , , |
|---|---|
| 格式: | 文件 |
| 语言: | English |
| 出版: |
MDPI AG
2021-03-01
|
| 丛编: | Journal of Imaging |
| 主题: | |
| 在线阅读: | https://www.mdpi.com/2313-433X/7/3/44 |
| _version_ | 1827604262113247232 |
|---|---|
| author | Johannes Leuschner Maximilian Schmidt Poulami Somanya Ganguly Vladyslav Andriiashen Sophia Bethany Coban Alexander Denker Dominik Bauer Amir Hadjifaradji Kees Joost Batenburg Peter Maass Maureen van Eijnatten |
| author_facet | Johannes Leuschner Maximilian Schmidt Poulami Somanya Ganguly Vladyslav Andriiashen Sophia Bethany Coban Alexander Denker Dominik Bauer Amir Hadjifaradji Kees Joost Batenburg Peter Maass Maureen van Eijnatten |
| author_sort | Johannes Leuschner |
| collection | DOAJ |
| description | The reconstruction of computed tomography (CT) images is an active area of research. Following the rise of deep learning methods, many data-driven models have been proposed in recent years. In this work, we present the results of a <i>data challenge</i> that we organized, bringing together algorithm experts from different institutes to jointly work on quantitative evaluation of several data-driven methods on two large, public datasets during a ten day sprint. We focus on two applications of CT, namely, low-dose CT and sparse-angle CT. This enables us to fairly compare different methods using standardized settings. As a general result, we observe that the deep learning-based methods are able to improve the reconstruction quality metrics in both CT applications while the top performing methods show only minor differences in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). We further discuss a number of other important criteria that should be taken into account when selecting a method, such as the availability of training data, the knowledge of the physical measurement model and the reconstruction speed. |
| first_indexed | 2024-03-09T05:56:31Z |
| format | Article |
| id | doaj.art-a9c9ce94377745e8adb2466faaf9be04 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-09T05:56:31Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-a9c9ce94377745e8adb2466faaf9be042023-12-03T12:13:35ZengMDPI AGJournal of Imaging2313-433X2021-03-01734410.3390/jimaging7030044Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT ApplicationsJohannes Leuschner0Maximilian Schmidt1Poulami Somanya Ganguly2Vladyslav Andriiashen3Sophia Bethany Coban4Alexander Denker5Dominik Bauer6Amir Hadjifaradji7Kees Joost Batenburg8Peter Maass9Maureen van Eijnatten10Center for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, GermanyCenter for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, GermanyCentrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The NetherlandsCentrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The NetherlandsCentrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The NetherlandsCenter for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, GermanyComputer Assisted Clinical Medicine, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, GermanySchool of Biomedical Engineering, University of British Columbia, 2222 Health Sciences Mall, Vancouver, BC V6T 1Z3, CanadaCentrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The NetherlandsCenter for Industrial Mathematics, University of Bremen, Bibliothekstr. 5, 28359 Bremen, GermanyCentrum Wiskunde & Informatica, Science Park 123, 1098 XG Amsterdam, The NetherlandsThe reconstruction of computed tomography (CT) images is an active area of research. Following the rise of deep learning methods, many data-driven models have been proposed in recent years. In this work, we present the results of a <i>data challenge</i> that we organized, bringing together algorithm experts from different institutes to jointly work on quantitative evaluation of several data-driven methods on two large, public datasets during a ten day sprint. We focus on two applications of CT, namely, low-dose CT and sparse-angle CT. This enables us to fairly compare different methods using standardized settings. As a general result, we observe that the deep learning-based methods are able to improve the reconstruction quality metrics in both CT applications while the top performing methods show only minor differences in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). We further discuss a number of other important criteria that should be taken into account when selecting a method, such as the availability of training data, the knowledge of the physical measurement model and the reconstruction speed.https://www.mdpi.com/2313-433X/7/3/44computed tomography (CT)image reconstructionlow-dosesparse-angledeep learningquantitative comparison |
| spellingShingle | Johannes Leuschner Maximilian Schmidt Poulami Somanya Ganguly Vladyslav Andriiashen Sophia Bethany Coban Alexander Denker Dominik Bauer Amir Hadjifaradji Kees Joost Batenburg Peter Maass Maureen van Eijnatten Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications Journal of Imaging computed tomography (CT) image reconstruction low-dose sparse-angle deep learning quantitative comparison |
| title | Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications |
| title_full | Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications |
| title_fullStr | Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications |
| title_full_unstemmed | Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications |
| title_short | Quantitative Comparison of Deep Learning-Based Image Reconstruction Methods for Low-Dose and Sparse-Angle CT Applications |
| title_sort | quantitative comparison of deep learning based image reconstruction methods for low dose and sparse angle ct applications |
| topic | computed tomography (CT) image reconstruction low-dose sparse-angle deep learning quantitative comparison |
| url | https://www.mdpi.com/2313-433X/7/3/44 |
| work_keys_str_mv | AT johannesleuschner quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT maximilianschmidt quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT poulamisomanyaganguly quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT vladyslavandriiashen quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT sophiabethanycoban quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT alexanderdenker quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT dominikbauer quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT amirhadjifaradji quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT keesjoostbatenburg quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT petermaass quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications AT maureenvaneijnatten quantitativecomparisonofdeeplearningbasedimagereconstructionmethodsforlowdoseandsparseanglectapplications |