1
|
Maus J, Nikulin P, Hofheinz F, Petr J, Braune A, Kotzerke J, van den Hoff J. Deep learning based bilateral filtering for edge-preserving denoising of respiratory-gated PET. EJNMMI Phys 2024; 11:58. [PMID: 38977533 PMCID: PMC11231129 DOI: 10.1186/s40658-024-00661-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2024] [Accepted: 06/17/2024] [Indexed: 07/10/2024] Open
Abstract
BACKGROUND Residual image noise is substantial in positron emission tomography (PET) and one of the factors limiting lesion detection, quantification, and overall image quality. Thus, improving noise reduction remains of considerable interest. This is especially true for respiratory-gated PET investigations. The only broadly used approach for noise reduction in PET imaging has been the application of low-pass filters, usually Gaussians, which however leads to loss of spatial resolution and increased partial volume effects affecting detectability of small lesions and quantitative data evaluation. The bilateral filter (BF) - a locally adaptive image filter - allows to reduce image noise while preserving well defined object edges but manual optimization of the filter parameters for a given PET scan can be tedious and time-consuming, hampering its clinical use. In this work we have investigated to what extent a suitable deep learning based approach can resolve this issue by training a suitable network with the target of reproducing the results of manually adjusted case-specific bilateral filtering. METHODS Altogether, 69 respiratory-gated clinical PET/CT scans with three different tracers ([ 18 F ] FDG,[ 18 F ] L-DOPA,[ 68 Ga ] DOTATATE) were used for the present investigation. Prior to data processing, the gated data sets were split, resulting in a total of 552 single-gate image volumes. For each of these image volumes, four 3D ROIs were delineated: one ROI for image noise assessment and three ROIs for focal uptake (e.g. tumor lesions) measurements at different target/background contrast levels. An automated procedure was used to perform a brute force search of the two-dimensional BF parameter space for each data set to identify the "optimal" filter parameters to generate user-approved ground truth input data consisting of pairs of original and optimally BF filtered images. For reproducing the optimal BF filtering, we employed a modified 3D U-Net CNN incorporating residual learning principle. The network training and evaluation was performed using a 5-fold cross-validation scheme. The influence of filtering on lesion SUV quantification and image noise level was assessed by calculating absolute and fractional differences between the CNN, manual BF, or original (STD) data sets in the previously defined ROIs. RESULTS The automated procedure used for filter parameter determination chose adequate filter parameters for the majority of the data sets with only 19 patient data sets requiring manual tuning. Evaluation of the focal uptake ROIs revealed that CNN as well as BF based filtering essentially maintain the focal SUV max values of the unfiltered images with a low mean ± SD difference of δ SUV max CNN , STD = (-3.9 ± 5.2)% and δ SUV max BF , STD = (-4.4 ± 5.3)%. Regarding relative performance of CNN versus BF, both methods lead to very similar SUV max values in the vast majority of cases with an overall average difference of δ SUV max CNN , BF = (0.5 ± 4.8)%. Evaluation of the noise properties showed that CNN filtering mostly satisfactorily reproduces the noise level and characteristics of BF with δ Noise CNN , BF = (5.6 ± 10.5)%. No significant tracer dependent differences between CNN and BF were observed. CONCLUSIONS Our results show that a neural network based denoising can reproduce the results of a case by case optimized BF in a fully automated way. Apart from rare cases it led to images of practically identical quality regarding noise level, edge preservation, and signal recovery. We believe such a network might proof especially useful in the context of improved motion correction of respiratory-gated PET studies but could also help to establish BF-equivalent edge-preserving CNN filtering in clinical PET since it obviates time consuming manual BF parameter tuning.
Collapse
Affiliation(s)
- Jens Maus
- Department of Positron Emission Tomography, Institute of Radiopharmaceutical Cancer Research, Helmholtz-Zentrum Dresden-Rossendorf, Bautzner Landstraße 400, 01314, Dresden, Germany.
| | - Pavel Nikulin
- Department of Positron Emission Tomography, Institute of Radiopharmaceutical Cancer Research, Helmholtz-Zentrum Dresden-Rossendorf, Bautzner Landstraße 400, 01314, Dresden, Germany
| | - Frank Hofheinz
- Department of Positron Emission Tomography, Institute of Radiopharmaceutical Cancer Research, Helmholtz-Zentrum Dresden-Rossendorf, Bautzner Landstraße 400, 01314, Dresden, Germany
| | - Jan Petr
- Department of Positron Emission Tomography, Institute of Radiopharmaceutical Cancer Research, Helmholtz-Zentrum Dresden-Rossendorf, Bautzner Landstraße 400, 01314, Dresden, Germany
| | - Anja Braune
- Klinik und Poliklinik für Nuklearmedizin, Universtitätsklinikum Carl Gustav Carus, Fetscherstraße 74, 01307, Dresden, Germany
| | - Jörg Kotzerke
- Klinik und Poliklinik für Nuklearmedizin, Universtitätsklinikum Carl Gustav Carus, Fetscherstraße 74, 01307, Dresden, Germany
| | - Jörg van den Hoff
- Department of Positron Emission Tomography, Institute of Radiopharmaceutical Cancer Research, Helmholtz-Zentrum Dresden-Rossendorf, Bautzner Landstraße 400, 01314, Dresden, Germany
- Klinik und Poliklinik für Nuklearmedizin, Universtitätsklinikum Carl Gustav Carus, Fetscherstraße 74, 01307, Dresden, Germany
| |
Collapse
|
2
|
Fard AS, Reutens DC, Ramsay SC, Goodman SJ, Ghosh S, Vegh V. Image synthesis of interictal SPECT from MRI and PET using machine learning. Front Neurol 2024; 15:1383773. [PMID: 38988603 PMCID: PMC11234346 DOI: 10.3389/fneur.2024.1383773] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Accepted: 06/12/2024] [Indexed: 07/12/2024] Open
Abstract
Background Cross-modality image estimation can be performed using generative adversarial networks (GANs). To date, SPECT image estimation from another medical imaging modality using this technique has not been considered. We evaluate the estimation of SPECT from MRI and PET, and additionally assess the necessity for cross-modality image registration for GAN training. Methods We estimated interictal SPECT from PET and MRI as a single-channel input, and as a multi-channel input to the GAN. We collected data from 48 individuals with epilepsy and converted them to 3D isotropic images for consistence across the modalities. Training and testing data were prepared in native and template spaces. The Pix2pix framework within the GAN network was adopted. We evaluated the addition of the structural similarity index metric to the loss function in the GAN implementation. Root-mean-square error, structural similarity index, and peak signal-to-noise ratio were used to assess how well SPECT images were able to be synthesised. Results High quality SPECT images could be synthesised in each case. On average, the use of native space images resulted in a 5.4% percentage improvement in SSIM than the use of images registered to template space. The addition of structural similarity index metric to the GAN loss function did not result in improved synthetic SPECT images. Using PET in either the single channel or dual channel implementation led to the best results, however MRI could produce SPECT images close in quality. Conclusion Synthesis of SPECT from MRI or PET can potentially reduce the number of scans needed for epilepsy patient evaluation and reduce patient exposure to radiation.
Collapse
Affiliation(s)
- Azin Shokraei Fard
- Centre for Advanced Imaging, University of Queensland, Brisbane, QLD, Australia
| | - David C. Reutens
- Centre for Advanced Imaging, University of Queensland, Brisbane, QLD, Australia
- Royal Brisbane and Women’s Hospital, Brisbane, QLD, Australia
- ARC Training Centre for Innovation in Biomedical Imaging Technology, Brisbane, QLD, Australia
| | | | | | - Soumen Ghosh
- Centre for Advanced Imaging, University of Queensland, Brisbane, QLD, Australia
- ARC Training Centre for Innovation in Biomedical Imaging Technology, Brisbane, QLD, Australia
| | - Viktor Vegh
- Centre for Advanced Imaging, University of Queensland, Brisbane, QLD, Australia
- ARC Training Centre for Innovation in Biomedical Imaging Technology, Brisbane, QLD, Australia
| |
Collapse
|
3
|
Yang S, Kim KD, Ariji E, Kise Y. Generative adversarial networks in dental imaging: a systematic review. Oral Radiol 2024; 40:93-108. [PMID: 38001347 DOI: 10.1007/s11282-023-00719-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2023] [Accepted: 10/27/2023] [Indexed: 11/26/2023]
Abstract
OBJECTIVES This systematic review on generative adversarial network (GAN) architectures for dental image analysis provides a comprehensive overview to readers regarding current GAN trends in dental imagery and potential future applications. METHODS Electronic databases (PubMed/MEDLINE, Scopus, Embase, and Cochrane Library) were searched to identify studies involving GANs for dental image analysis. Eighteen full-text articles describing the applications of GANs in dental imagery were reviewed. Risk of bias and applicability concerns were assessed using the QUADAS-2 tool. RESULTS GANs were used for various imaging modalities, including two-dimensional and three-dimensional images. In dental imaging, GANs were utilized for tasks such as artifact reduction, denoising, and super-resolution, domain transfer, image generation for augmentation, outcome prediction, and identification. The generated images were incorporated into tasks such as landmark detection, object detection and classification. Because of heterogeneity among the studies, a meta-analysis could not be conducted. Most studies (72%) had a low risk of bias in all four domains. However, only three (17%) studies had a low risk of applicability concerns. CONCLUSIONS This extensive analysis of GANs in dental imaging highlighted their broad application potential within the dental field. Future studies should address limitations related to the stability, repeatability, and overall interpretability of GAN architectures. By overcoming these challenges, the applicability of GANs in dentistry can be enhanced, ultimately benefiting the dental field in its use of GANs and artificial intelligence.
Collapse
Affiliation(s)
- Sujin Yang
- Department of Advanced General Dentistry, College of Dentistry, Yonsei University, Seoul, Korea
| | - Kee-Deog Kim
- Department of Advanced General Dentistry, College of Dentistry, Yonsei University, Seoul, Korea
| | - Eiichiro Ariji
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Aichi Gakuin University, 2-11 Suemori-dori, Chikusa-ku, Nagoya, 464-8651, Japan
| | - Yoshitaka Kise
- Department of Oral and Maxillofacial Radiology, School of Dentistry, Aichi Gakuin University, 2-11 Suemori-dori, Chikusa-ku, Nagoya, 464-8651, Japan.
| |
Collapse
|
4
|
Hashimoto F, Onishi Y, Ote K, Tashima H, Reader AJ, Yamaya T. Deep learning-based PET image denoising and reconstruction: a review. Radiol Phys Technol 2024; 17:24-46. [PMID: 38319563 PMCID: PMC10902118 DOI: 10.1007/s12194-024-00780-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 01/03/2024] [Accepted: 01/04/2024] [Indexed: 02/07/2024]
Abstract
This review focuses on positron emission tomography (PET) imaging algorithms and traces the evolution of PET image reconstruction methods. First, we provide an overview of conventional PET image reconstruction methods from filtered backprojection through to recent iterative PET image reconstruction algorithms, and then review deep learning methods for PET data up to the latest innovations within three main categories. The first category involves post-processing methods for PET image denoising. The second category comprises direct image reconstruction methods that learn mappings from sinograms to the reconstructed images in an end-to-end manner. The third category comprises iterative reconstruction methods that combine conventional iterative image reconstruction with neural-network enhancement. We discuss future perspectives on PET imaging and deep learning technology.
Collapse
Affiliation(s)
- Fumio Hashimoto
- Central Research Laboratory, Hamamatsu Photonics K. K, 5000 Hirakuchi, Hamana-Ku, Hamamatsu, 434-8601, Japan.
- Graduate School of Science and Engineering, Chiba University, 1-33, Yayoicho, Inage-Ku, Chiba, 263-8522, Japan.
- National Institutes for Quantum Science and Technology, 4-9-1, Anagawa, Inage-Ku, Chiba, 263-8555, Japan.
| | - Yuya Onishi
- Central Research Laboratory, Hamamatsu Photonics K. K, 5000 Hirakuchi, Hamana-Ku, Hamamatsu, 434-8601, Japan
| | - Kibo Ote
- Central Research Laboratory, Hamamatsu Photonics K. K, 5000 Hirakuchi, Hamana-Ku, Hamamatsu, 434-8601, Japan
| | - Hideaki Tashima
- National Institutes for Quantum Science and Technology, 4-9-1, Anagawa, Inage-Ku, Chiba, 263-8555, Japan
| | - Andrew J Reader
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, SE1 7EH, UK
| | - Taiga Yamaya
- Graduate School of Science and Engineering, Chiba University, 1-33, Yayoicho, Inage-Ku, Chiba, 263-8522, Japan
- National Institutes for Quantum Science and Technology, 4-9-1, Anagawa, Inage-Ku, Chiba, 263-8555, Japan
| |
Collapse
|
5
|
Bousse A, Kandarpa VSS, Shi K, Gong K, Lee JS, Liu C, Visvikis D. A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches. ARXIV 2024:arXiv:2401.00232v2. [PMID: 38313194 PMCID: PMC10836084] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 02/06/2024]
Abstract
Low-dose emission tomography (ET) plays a crucial role in medical imaging, enabling the acquisition of functional information for various biological processes while minimizing the patient dose. However, the inherent randomness in the photon counting process is a source of noise which is amplified in low-dose ET. This review article provides an overview of existing post-processing techniques, with an emphasis on deep neural network (NN) approaches. Furthermore, we explore future directions in the field of NN-based low-dose ET. This comprehensive examination sheds light on the potential of deep learning in enhancing the quality and resolution of low-dose ET images, ultimately advancing the field of medical imaging.
Collapse
Affiliation(s)
| | | | - Kuangyu Shi
- Lab for Artificial Intelligence & Translational Theranostics, Dept. Nuclear Medicine, Inselspital, University of Bern, 3010 Bern, Switzerland
| | - Kuang Gong
- The Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital/Harvard Medical School, Boston, MA 02114, USA
| | - Jae Sung Lee
- Department of Nuclear Medicine, Seoul National University College of Medicine, Seoul 03080, Korea
| | - Chi Liu
- Department of Radiology and Biomedical Imaging, Yale University, New Haven, CT, USA
| | | |
Collapse
|
6
|
Gong K, Johnson K, El Fakhri G, Li Q, Pan T. PET image denoising based on denoising diffusion probabilistic model. Eur J Nucl Med Mol Imaging 2024; 51:358-368. [PMID: 37787849 PMCID: PMC10958486 DOI: 10.1007/s00259-023-06417-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Accepted: 08/22/2023] [Indexed: 10/04/2023]
Abstract
PURPOSE Due to various physical degradation factors and limited counts received, PET image quality needs further improvements. The denoising diffusion probabilistic model (DDPM) was a distribution learning-based model, which tried to transform a normal distribution into a specific data distribution based on iterative refinements. In this work, we proposed and evaluated different DDPM-based methods for PET image denoising. METHODS Under the DDPM framework, one way to perform PET image denoising was to provide the PET image and/or the prior image as the input. Another way was to supply the prior image as the network input with the PET image included in the refinement steps, which could fit for scenarios of different noise levels. 150 brain [[Formula: see text]F]FDG datasets and 140 brain [[Formula: see text]F]MK-6240 (imaging neurofibrillary tangles deposition) datasets were utilized to evaluate the proposed DDPM-based methods. RESULTS Quantification showed that the DDPM-based frameworks with PET information included generated better results than the nonlocal mean, Unet and generative adversarial network (GAN)-based denoising methods. Adding additional MR prior in the model helped achieved better performance and further reduced the uncertainty during image denoising. Solely relying on MR prior while ignoring the PET information resulted in large bias. Regional and surface quantification showed that employing MR prior as the network input while embedding PET image as a data-consistency constraint during inference achieved the best performance. CONCLUSION DDPM-based PET image denoising is a flexible framework, which can efficiently utilize prior information and achieve better performance than the nonlocal mean, Unet and GAN-based denoising methods.
Collapse
Affiliation(s)
- Kuang Gong
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, 32611, FL, USA.
- Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, 02114, MA, USA.
- Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, 02114, MA, USA.
| | - Keith Johnson
- Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, 02114, MA, USA
| | - Georges El Fakhri
- Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, 02114, MA, USA
| | - Quanzheng Li
- Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, 02114, MA, USA
| | - Tinsu Pan
- Department of Imaging Physics, University of Texas MD Anderson Cancer Center, Houston, 77030, TX, USA
| |
Collapse
|
7
|
Bevington CWJ, Cheng JC, Sossi V. A 4-D Iterative HYPR Denoising Operator Improves PET Image Quality. IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2022. [DOI: 10.1109/trpms.2021.3123537] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
Affiliation(s)
- Connor W. J. Bevington
- Department of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada
| | - Ju-Chieh Cheng
- Department of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada
| | - Vesna Sossi
- Department of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada
| |
Collapse
|
8
|
Shokraei Fard A, Reutens DC, Vegh V. From CNNs to GANs for cross-modality medical image estimation. Comput Biol Med 2022; 146:105556. [DOI: 10.1016/j.compbiomed.2022.105556] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/07/2022] [Revised: 04/03/2022] [Accepted: 04/22/2022] [Indexed: 11/03/2022]
|
9
|
Pain CD, Egan GF, Chen Z. Deep learning-based image reconstruction and post-processing methods in positron emission tomography for low-dose imaging and resolution enhancement. Eur J Nucl Med Mol Imaging 2022; 49:3098-3118. [PMID: 35312031 PMCID: PMC9250483 DOI: 10.1007/s00259-022-05746-4] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2021] [Accepted: 02/25/2022] [Indexed: 12/21/2022]
Abstract
Image processing plays a crucial role in maximising diagnostic quality of positron emission tomography (PET) images. Recently, deep learning methods developed across many fields have shown tremendous potential when applied to medical image enhancement, resulting in a rich and rapidly advancing literature surrounding this subject. This review encapsulates methods for integrating deep learning into PET image reconstruction and post-processing for low-dose imaging and resolution enhancement. A brief introduction to conventional image processing techniques in PET is firstly presented. We then review methods which integrate deep learning into the image reconstruction framework as either deep learning-based regularisation or as a fully data-driven mapping from measured signal to images. Deep learning-based post-processing methods for low-dose imaging, temporal resolution enhancement and spatial resolution enhancement are also reviewed. Finally, the challenges associated with applying deep learning to enhance PET images in the clinical setting are discussed and future research directions to address these challenges are presented.
Collapse
Affiliation(s)
- Cameron Dennis Pain
- Monash Biomedical Imaging, Monash University, Melbourne, Australia.
- Department of Electrical and Computer Systems Engineering, Monash University, Melbourne, Australia.
| | - Gary F Egan
- Monash Biomedical Imaging, Monash University, Melbourne, Australia
- Turner Institute for Brain and Mental Health, Monash University, Melbourne, Australia
| | - Zhaolin Chen
- Monash Biomedical Imaging, Monash University, Melbourne, Australia
- Department of Data Science and AI, Monash University, Melbourne, Australia
| |
Collapse
|
10
|
Matsubara K, Ibaraki M, Nemoto M, Watabe H, Kimura Y. A review on AI in PET imaging. Ann Nucl Med 2022; 36:133-143. [PMID: 35029818 DOI: 10.1007/s12149-021-01710-8] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/28/2021] [Accepted: 12/09/2021] [Indexed: 12/16/2022]
Abstract
Artificial intelligence (AI) has been applied to various medical imaging tasks, such as computer-aided diagnosis. Specifically, deep learning techniques such as convolutional neural network (CNN) and generative adversarial network (GAN) have been extensively used for medical image generation. Image generation with deep learning has been investigated in studies using positron emission tomography (PET). This article reviews studies that applied deep learning techniques for image generation on PET. We categorized the studies for PET image generation with deep learning into three themes as follows: (1) recovering full PET data from noisy data by denoising with deep learning, (2) PET image reconstruction and attenuation correction with deep learning and (3) PET image translation and synthesis with deep learning. We introduce recent studies based on these three categories. Finally, we mention the limitations of applying deep learning techniques to PET image generation and future prospects for PET image generation.
Collapse
Affiliation(s)
- Keisuke Matsubara
- Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Akita, Japan
| | - Masanobu Ibaraki
- Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Akita, Japan
| | - Mitsutaka Nemoto
- Faculty of Biology-Oriented Science and Technology, and Cyber Informatics Research Institute, Kindai University, Wakayama, Japan
| | - Hiroshi Watabe
- Cyclotron and Radioisotope Center (CYRIC), Tohoku University, Miyagi, Japan
| | - Yuichi Kimura
- Faculty of Biology-Oriented Science and Technology, and Cyber Informatics Research Institute, Kindai University, Wakayama, Japan.
| |
Collapse
|
11
|
Amirrashedi M, Sarkar S, Mamizadeh H, Ghadiri H, Ghafarian P, Zaidi H, Ay MR. Leveraging deep neural networks to improve numerical and perceptual image quality in low-dose preclinical PET imaging. Comput Med Imaging Graph 2021; 94:102010. [PMID: 34784505 DOI: 10.1016/j.compmedimag.2021.102010] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2021] [Revised: 10/25/2021] [Accepted: 10/26/2021] [Indexed: 01/24/2023]
Abstract
The amount of radiotracer injected into laboratory animals is still the most daunting challenge facing translational PET studies. Since low-dose imaging is characterized by a higher level of noise, the quality of the reconstructed images leaves much to be desired. Being the most ubiquitous techniques in denoising applications, edge-aware denoising filters, and reconstruction-based techniques have drawn significant attention in low-count applications. However, for the last few years, much of the credit has gone to deep-learning (DL) methods, which provide more robust solutions to handle various conditions. Albeit being extensively explored in clinical studies, to the best of our knowledge, there is a lack of studies exploring the feasibility of DL-based image denoising in low-count small animal PET imaging. Therefore, herein, we investigated different DL frameworks to map low-dose small animal PET images to their full-dose equivalent with quality and visual similarity on a par with those of standard acquisition. The performance of the DL model was also compared to other well-established filters, including Gaussian smoothing, nonlocal means, and anisotropic diffusion. Visual inspection and quantitative assessment based on quality metrics proved the superior performance of the DL methods in low-count small animal PET studies, paving the way for a more detailed exploration of DL-assisted algorithms in this domain.
Collapse
Affiliation(s)
- Mahsa Amirrashedi
- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran; Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran.
| | - Saeed Sarkar
- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran; Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran.
| | - Hojjat Mamizadeh
- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran; Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran.
| | - Hossein Ghadiri
- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran; Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran.
| | - Pardis Ghafarian
- Chronic Respiratory Diseases Research Center, National Research Institute of Tuberculosis and Lung Diseases (NRITLD), Shahid Beheshti University of Medical Sciences, Tehran, Iran; PET/CT and Cyclotron Center, Masih Daneshvari Hospital, Shahid Beheshti University of Medical, Tehran, Iran.
| | - Habib Zaidi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva CH-1211, Switzerland; Geneva University Neurocenter, Geneva University, Geneva, Switzerland; Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands; Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark.
| | - Mohammad Reza Ay
- Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran; Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran.
| |
Collapse
|
12
|
Song TA, Yang F, Dutta J. Noise2Void: unsupervised denoising of PET images. Phys Med Biol 2021; 66. [PMID: 34663767 DOI: 10.1088/1361-6560/ac30a0] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2020] [Accepted: 10/18/2021] [Indexed: 11/11/2022]
Abstract
Objective:Elevated noise levels in positron emission tomography (PET) images lower image quality and quantitative accuracy and are a confounding factor for clinical interpretation. The objective of this paper is to develop a PET image denoising technique based on unsupervised deep learning.Significance:Recent advances in deep learning have ushered in a wide array of novel denoising techniques, several of which have been successfully adapted for PET image reconstruction and post-processing. The bulk of the deep learning research so far has focused on supervised learning schemes, which, for the image denoising problem, require paired noisy and noiseless/low-noise images. This requirement tends to limit the utility of these methods for medical applications as paired training datasets are not always available. Furthermore, to achieve the best-case performance of these methods, it is essential that the datasets for training and subsequent real-world application have consistent image characteristics (e.g. noise, resolution, etc), which is rarely the case for clinical data. To circumvent these challenges, it is critical to develop unsupervised techniques that obviate the need for paired training data.Approach:In this paper, we have adapted Noise2Void, a technique that relies on corrupt images alone for model training, for PET image denoising and assessed its performance using PET neuroimaging data. Noise2Void is an unsupervised approach that uses a blind-spot network design. It requires only a single noisy image as its input, and, therefore, is well-suited for clinical settings. During the training phase, a single noisy PET image serves as both the input and the target. Here we present a modified version of Noise2Void based on a transfer learning paradigm that involves group-level pretraining followed by individual fine-tuning. Furthermore, we investigate the impact of incorporating an anatomical image as a second input to the network.Main Results:We validated our denoising technique using simulation data based on the BrainWeb digital phantom. We show that Noise2Void with pretraining and/or anatomical guidance leads to higher peak signal-to-noise ratios than traditional denoising schemes such as Gaussian filtering, anatomically guided non-local means filtering, and block-matching and 4D filtering. We used the Noise2Noise denoising technique as an additional benchmark. For clinical validation, we applied this method to human brain imaging datasets. The clinical findings were consistent with the simulation results confirming the translational value of Noise2Void as a denoising tool.
Collapse
Affiliation(s)
- Tzu-An Song
- University of Massachusetts Lowell, Lowell, MA 01854, United States of America
| | - Fan Yang
- University of Massachusetts Lowell, Lowell, MA 01854, United States of America
| | - Joyita Dutta
- University of Massachusetts Lowell, Lowell, MA 01854, United States of America.,Massachusetts General Hospital, Boston, MA 02114, United States of America
| |
Collapse
|
13
|
Liu J, Malekzadeh M, Mirian N, Song TA, Liu C, Dutta J. Artificial Intelligence-Based Image Enhancement in PET Imaging: Noise Reduction and Resolution Enhancement. PET Clin 2021; 16:553-576. [PMID: 34537130 PMCID: PMC8457531 DOI: 10.1016/j.cpet.2021.06.005] [Citation(s) in RCA: 31] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
High noise and low spatial resolution are two key confounding factors that limit the qualitative and quantitative accuracy of PET images. Artificial intelligence models for image denoising and deblurring are becoming increasingly popular for the postreconstruction enhancement of PET images. We present a detailed review of recent efforts for artificial intelligence-based PET image enhancement with a focus on network architectures, data types, loss functions, and evaluation metrics. We also highlight emerging areas in this field that are quickly gaining popularity, identify barriers to large-scale adoption of artificial intelligence models for PET image enhancement, and discuss future directions.
Collapse
Affiliation(s)
- Juan Liu
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | - Masoud Malekzadeh
- Department of Electrical and Computer Engineering, University of Massachusetts Lowell, 1 University Avenue, Ball 301, Lowell, MA 01854, USA
| | - Niloufar Mirian
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | - Tzu-An Song
- Department of Electrical and Computer Engineering, University of Massachusetts Lowell, 1 University Avenue, Ball 301, Lowell, MA 01854, USA
| | - Chi Liu
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.
| | - Joyita Dutta
- Department of Electrical and Computer Engineering, University of Massachusetts Lowell, 1 University Avenue, Ball 301, Lowell, MA 01854, USA; Gordon Center for Medical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
14
|
Gong K, Kim K, Cui J, Wu D, Li Q. The Evolution of Image Reconstruction in PET: From Filtered Back-Projection to Artificial Intelligence. PET Clin 2021; 16:533-542. [PMID: 34537129 DOI: 10.1016/j.cpet.2021.06.004] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
PET can provide functional images revealing physiologic processes in vivo. Although PET has many applications, there are still some limitations that compromise its precision: the absorption of photons in the body causes signal attenuation; the dead-time limit of system components leads to the loss of the count rate; the scattered and random events received by the detector introduce additional noise; the characteristics of the detector limit the spatial resolution; and the low signal-to-noise ratio caused by the scan-time limit (eg, dynamic scans) and dose concern. The early PET reconstruction methods are analytical approaches based on an idealized mathematical model.
Collapse
Affiliation(s)
- Kuang Gong
- Department of Radiology, Center for Advanced Medical Computing and Analysis, Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Kyungsang Kim
- Department of Radiology, Center for Advanced Medical Computing and Analysis, Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Jianan Cui
- Department of Radiology, Center for Advanced Medical Computing and Analysis, Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Dufan Wu
- Department of Radiology, Center for Advanced Medical Computing and Analysis, Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA
| | - Quanzheng Li
- Department of Radiology, Center for Advanced Medical Computing and Analysis, Gordon Center for Medical Imaging, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
15
|
Reader AJ, Corda G, Mehranian A, Costa-Luis CD, Ellis S, Schnabel JA. Deep Learning for PET Image Reconstruction. IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2021. [DOI: 10.1109/trpms.2020.3014786] [Citation(s) in RCA: 65] [Impact Index Per Article: 21.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
16
|
Whiteley W, Panin V, Zhou C, Cabello J, Bharkhada D, Gregor J. FastPET: Near Real-Time Reconstruction of PET Histo-Image Data Using a Neural Network. IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES 2021. [DOI: 10.1109/trpms.2020.3028364] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|