1
|
Rahman H, Khan AR, Sadiq T, Farooqi AH, Khan IU, Lim WH. A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction. Tomography 2023; 9:2158-2189. [PMID: 38133073 PMCID: PMC10748093 DOI: 10.3390/tomography9060169] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2023] [Revised: 11/27/2023] [Accepted: 12/01/2023] [Indexed: 12/23/2023] Open
Abstract
Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.
Collapse
Affiliation(s)
- Hameedur Rahman
- Department of Computer Games Development, Faculty of Computing & AI, Air University, E9, Islamabad 44000, Pakistan;
| | - Abdur Rehman Khan
- Department of Creative Technologies, Faculty of Computing & AI, Air University, E9, Islamabad 44000, Pakistan;
| | - Touseef Sadiq
- Centre for Artificial Intelligence Research, Department of Information and Communication Technology, University of Agder, Jon Lilletuns vei 9, 4879 Grimstad, Norway
| | - Ashfaq Hussain Farooqi
- Department of Computer Science, Faculty of Computing AI, Air University, Islamabad 44000, Pakistan;
| | - Inam Ullah Khan
- Department of Electronic Engineering, School of Engineering & Applied Sciences (SEAS), Isra University, Islamabad Campus, Islamabad 44000, Pakistan;
| | - Wei Hong Lim
- Faculty of Engineering, Technology and Built Environment, UCSI University, Kuala Lumpur 56000, Malaysia;
| |
Collapse
|
2
|
Thies M, Wagner F, Huang Y, Gu M, Kling L, Pechmann S, Aust O, Grüneboom A, Schett G, Christiansen S, Maier A. Calibration by differentiation - Self-supervised calibration for X-ray microscopy using a differentiable cone-beam reconstruction operator. J Microsc 2022; 287:81-92. [PMID: 35638174 DOI: 10.1111/jmi.13125] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Revised: 04/20/2022] [Accepted: 05/22/2022] [Indexed: 11/28/2022]
Abstract
High-resolution X-ray microscopy (XRM) is gaining interest for biological investigations of extremely small-scale structures. XRM imaging of bones in living mice could provide new insights into the emergence and treatment of osteoporosis by observing osteocyte lacunae, which are holes in the bone of few micrometers in size. Imaging living animals at that resolution, however, is extremely challenging and requires very sophisticated data processing converting the raw XRM detector output into reconstructed images. This paper presents an open-source, differentiable reconstruction pipeline for XRM data which analytically computes the final image from the raw measurements. In contrast to most proprietary reconstruction software, it offers the user full control over each processing step and, additionally, makes the entire pipeline deep learning compatible by ensuring differentiability. This allows fitting trainable modules both before and after the actual reconstruction step in a purely data-driven way using the gradient-based optimizers of common deep learning frameworks. The value of such differentiability is demonstrated by calibrating the parameters of a simple cupping correction module operating on the raw projection images using only a self-supervisory quality metric based on the reconstructed volume and no further calibration measurements. The retrospective calibration directly improves image quality as it avoids cupping artifacts and decreases the difference in gray values between outer and inner bone by 68% to 94%. Furthermore, it makes the reconstruction process entirely independent of the XRM manufacturer and paves the way to explore modern deep learning reconstruction methods for arbitrary XRM and, potentially, other flat-panel CT systems. This exemplifies how differentiable reconstruction can be leveraged in the context of XRM and, hence, is an important step toward the goal of reducing the resolution limit of in-vivo bone imaging to the single micrometer domain. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Mareike Thies
- Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Fabian Wagner
- Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Yixing Huang
- Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Mingxuan Gu
- Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| | - Lasse Kling
- Institute for Nanotechnology and Correlative Microscopy e.V. INAM, Forchheim, Germany
| | - Sabrina Pechmann
- Fraunhofer Institute for Ceramic Technologies and Systems IKTS, Forchheim, Germany
| | - Oliver Aust
- Department of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander-Universität Erlangen-Nürnberg and Universitätsklinikum Erlangen, Erlangen, Germany
| | - Anika Grüneboom
- Leibniz Institute for Analytical Sciences ISAS, Dortmund, Germany
| | - Georg Schett
- Department of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander-Universität Erlangen-Nürnberg and Universitätsklinikum Erlangen, Erlangen, Germany.,Deutsches Zentrum für Immuntherapie, Friedrich-Alexander-Universität Erlangen-Nürnberg and Universitätsklinikum Erlangen, Erlangen, Germany
| | - Silke Christiansen
- Institute for Nanotechnology and Correlative Microscopy e.V. INAM, Forchheim, Germany.,Fraunhofer Institute for Ceramic Technologies and Systems IKTS, Forchheim, Germany.,Physics Department, Freie Universität Berlin, Berlin, Germany
| | - Andreas Maier
- Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany
| |
Collapse
|
3
|
Ganguly PS, Pelt DM, Gürsoy D, de Carlo F, Batenburg KJ. Improving reproducibility in synchrotron tomography using implementation-adapted filters. JOURNAL OF SYNCHROTRON RADIATION 2021; 28:1583-1597. [PMID: 34475305 PMCID: PMC8415339 DOI: 10.1107/s1600577521007153] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/17/2021] [Accepted: 07/12/2021] [Indexed: 06/13/2023]
Abstract
For reconstructing large tomographic datasets fast, filtered backprojection-type or Fourier-based algorithms are still the method of choice, as they have been for decades. These robust and computationally efficient algorithms have been integrated in a broad range of software packages. The continuous mathematical formulas used for image reconstruction in such algorithms are unambiguous. However, variations in discretization and interpolation result in quantitative differences between reconstructed images, and corresponding segmentations, obtained from different software. This hinders reproducibility of experimental results, making it difficult to ensure that results and conclusions from experiments can be reproduced at different facilities or using different software. In this paper, a way to reduce such differences by optimizing the filter used in analytical algorithms is proposed. These filters can be computed using a wrapper routine around a black-box implementation of a reconstruction algorithm, and lead to quantitatively similar reconstructions. Use cases for this approach are demonstrated by computing implementation-adapted filters for several open-source implementations and applying them to simulated phantoms and real-world data acquired at the synchrotron. Our contribution to a reproducible reconstruction step forms a building block towards a fully reproducible synchrotron tomography data processing pipeline.
Collapse
Affiliation(s)
- Poulami Somanya Ganguly
- Computational Imaging, Centrum Wiskunde and Informatica, Amsterdam, The Netherlands
- Mathematical Institute, Leiden University, Leiden, The Netherlands
| | - Daniël M. Pelt
- Computational Imaging, Centrum Wiskunde and Informatica, Amsterdam, The Netherlands
- Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands
| | - Doga Gürsoy
- X-ray Science Division, Argonne National Laboratory, Argonne,IL, USA
- Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL, USA
| | | | - K. Joost Batenburg
- Computational Imaging, Centrum Wiskunde and Informatica, Amsterdam, The Netherlands
- Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands
| |
Collapse
|