1
|
Mandija S, Meliadò EF, Huttinga NRF, Luijten PR, van den Berg CAT. Opening a new window on MR-based Electrical Properties Tomography with deep learning. Sci Rep 2019; 9:8895. [PMID: 31222055 PMCID: PMC6586684 DOI: 10.1038/s41598-019-45382-x] [Citation(s) in RCA: 28] [Impact Index Per Article: 5.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2019] [Accepted: 06/04/2019] [Indexed: 11/09/2022] Open
Abstract
In the radiofrequency (RF) range, the electrical properties of tissues (EPs: conductivity and permittivity) are modulated by the ionic and water content, which change for pathological conditions. Information on tissues EPs can be used e.g. in oncology as a biomarker. The inability of MR-Electrical Properties Tomography techniques (MR-EPT) to accurately reconstruct tissue EPs by relating MR measurements of the transmit RF field to the EPs limits their clinical applicability. Instead of employing electromagnetic models posing strict requirements on the measured MRI quantities, we propose a data driven approach where the electrical properties reconstruction problem can be casted as a supervised deep learning task (DL-EPT). DL-EPT reconstructions for simulations and MR measurements at 3 Tesla on phantoms and human brains using a conditional generative adversarial network demonstrate high quality EPs reconstructions and greatly improved precision compared to conventional MR-EPT. The supervised learning approach leverages the strength of electromagnetic simulations, allowing circumvention of inaccessible MR electromagnetic quantities. Since DL-EPT is more noise-robust than MR-EPT, the requirements for MR acquisitions can be relaxed. This could be a major step forward to turn electrical properties tomography into a reliable biomarker where pathological conditions can be revealed and characterized by abnormalities in tissue electrical properties.
Collapse
Affiliation(s)
- Stefano Mandija
- Computational Imaging Group for MR diagnostic & therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands.
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands.
| | - Ettore F Meliadò
- Computational Imaging Group for MR diagnostic & therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands
- Department of Radiology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands
| | - Niek R F Huttinga
- Computational Imaging Group for MR diagnostic & therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands
| | - Peter R Luijten
- Department of Radiology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands
| | - Cornelis A T van den Berg
- Computational Imaging Group for MR diagnostic & therapy, Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands
- Department of Radiotherapy, Division of Imaging & Oncology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands
| |
Collapse
|
2
|
Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and Visualization. Sci Rep 2019; 9:6268. [PMID: 31000728 PMCID: PMC6472370 DOI: 10.1038/s41598-019-42557-4] [Citation(s) in RCA: 111] [Impact Index Per Article: 22.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2018] [Accepted: 03/22/2019] [Indexed: 01/23/2023] Open
Abstract
Automated diagnosis of tuberculosis (TB) from chest X-Rays (CXR) has been tackled with either hand-crafted algorithms or machine learning approaches such as support vector machines (SVMs) and convolutional neural networks (CNNs). Most deep neural network applied to the task of tuberculosis diagnosis have been adapted from natural image classification. These models have a large number of parameters as well as high hardware requirements, which makes them prone to overfitting and harder to deploy in mobile settings. We propose a simple convolutional neural network optimized for the problem which is faster and more efficient than previous models but preserves their accuracy. Moreover, the visualization capabilities of CNNs have not been fully investigated. We test saliency maps and grad-CAMs as tuberculosis visualization methods, and discuss them from a radiological perspective.
Collapse
|
3
|
Ravi D, Ghavami N, Alexander DC, Ianus A. Current Applications and Future Promises of Machine Learning in Diffusion MRI. COMPUTATIONAL DIFFUSION MRI 2019. [DOI: 10.1007/978-3-030-05831-9_9] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
|
4
|
Machine Learning in Neurooncology Imaging: From Study Request to Diagnosis and Treatment. AJR Am J Roentgenol 2018; 212:52-56. [PMID: 30403523 DOI: 10.2214/ajr.18.20328] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
OBJECTIVE Machine learning has potential to play a key role across a variety of medical imaging applications. This review seeks to elucidate the ways in which machine learning can aid and enhance diagnosis, treatment, and follow-up in neurooncology. CONCLUSION Given the rapid pace of development in machine learning over the past several years, a basic proficiency of the key tenets and use cases in the field is critical to assessing potential opportunities and challenges of this exciting new technology.
Collapse
|
5
|
Diffusion MRI Signal Augmentation: From Single Shell to Multi Shell with Deep Learning. COMPUTATIONAL DIFFUSION MRI 2017. [DOI: 10.1007/978-3-319-54130-3_5] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/02/2022]
|
6
|
Reisert M, Kellner E, Dhital B, Hennig J, Kiselev VG. Disentangling micro from mesostructure by diffusion MRI: A Bayesian approach. Neuroimage 2016; 147:964-975. [PMID: 27746388 DOI: 10.1016/j.neuroimage.2016.09.058] [Citation(s) in RCA: 124] [Impact Index Per Article: 15.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2016] [Revised: 08/11/2016] [Accepted: 09/23/2016] [Indexed: 10/20/2022] Open
Abstract
Diffusion-sensitized magnetic resonance imaging probes the cellular structure of the human brain, but the primary microstructural information gets lost in averaging over higher-level, mesoscopic tissue organization such as different orientations of neuronal fibers. While such averaging is inevitable due to the limited imaging resolution, we propose a method for disentangling the microscopic cell properties from the effects of mesoscopic structure. We further avoid the classical fitting paradigm and use supervised machine learning in terms of a Bayesian estimator to estimate the microstructural properties. The method finds detectable parameters of a given microstructural model and calculates them within seconds, which makes it suitable for a broad range of neuroscientific applications.
Collapse
Affiliation(s)
- Marco Reisert
- Medical Physics, Department of Radiology, University Medical Center Freiburg, Germany
| | - Elias Kellner
- Medical Physics, Department of Radiology, University Medical Center Freiburg, Germany
| | - Bibek Dhital
- Medical Physics, Department of Radiology, University Medical Center Freiburg, Germany
| | - Jürgen Hennig
- Medical Physics, Department of Radiology, University Medical Center Freiburg, Germany
| | - Valerij G Kiselev
- Medical Physics, Department of Radiology, University Medical Center Freiburg, Germany
| |
Collapse
|
7
|
Golkov V, Dosovitskiy A, Sperl JI, Menzel MI, Czisch M, Samann P, Brox T, Cremers D. q-Space Deep Learning: Twelve-Fold Shorter and Model-Free Diffusion MRI Scans. IEEE TRANSACTIONS ON MEDICAL IMAGING 2016; 35:1344-1351. [PMID: 27071165 DOI: 10.1109/tmi.2016.2551324] [Citation(s) in RCA: 145] [Impact Index Per Article: 18.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/07/2023]
Abstract
Numerous scientific fields rely on elaborate but partly suboptimal data processing pipelines. An example is diffusion magnetic resonance imaging (diffusion MRI), a non-invasive microstructure assessment method with a prominent application in neuroimaging. Advanced diffusion models providing accurate microstructural characterization so far have required long acquisition times and thus have been inapplicable for children and adults who are uncooperative, uncomfortable, or unwell. We show that the long scan time requirements are mainly due to disadvantages of classical data processing. We demonstrate how deep learning, a group of algorithms based on recent advances in the field of artificial neural networks, can be applied to reduce diffusion MRI data processing to a single optimized step. This modification allows obtaining scalar measures from advanced models at twelve-fold reduced scan time and detecting abnormalities without using diffusion models. We set a new state of the art by estimating diffusion kurtosis measures from only 12 data points and neurite orientation dispersion and density measures from only 8 data points. This allows unprecedentedly fast and robust protocols facilitating clinical routine and demonstrates how classical data processing can be streamlined by means of deep learning.
Collapse
|