GAN-based synthetic brain PET image generation.
Ontology highlight
ABSTRACT:
SUBMITTER: Islam J
PROVIDER: S-EPMC7105582 | biostudies-literature | 2020 Mar
REPOSITORIES: biostudies-literature
Publications
GAN-based synthetic brain PET image generation.
Brain informatics 20200330 1
In recent days, deep learning technologies have achieved tremendous success in computer vision-related tasks with the help of large-scale annotated dataset. Obtaining such dataset for medical image analysis is very challenging. Working with the limited dataset and small amount of annotated samples makes it difficult to develop a robust automated disease diagnosis model. We propose a novel approach to generate synthetic medical images using generative adversarial networks (GANs). Our proposed mod ...[more]
Similar Datasets
Project description:No previous works have attempted to combine generative adversarial network (GAN) architectures and the biomathematical modeling of positron emission tomography (PET) radiotracer uptake in tumors to generate extra training samples. Here, we developed a novel computational model to produce synthetic 18F-fluorodeoxyglucose (18F-FDG) PET images of solid tumors in different stages of progression and angiogenesis. First, a comprehensive biomathematical model is employed for creating tumor-induced angiogenesis, intravascular and extravascular fluid flow, as well as modeling of the transport phenomena and reaction processes of 18F-FDG in a tumor microenvironment. Then, a deep convolutional GAN (DCGAN) model is employed for producing synthetic PET images using 170 input images of 18F-FDG uptake in each of 10 different tumor microvascular networks. The interstitial fluid parameters and spatiotemporal distribution of 18F-FDG uptake in tumor and healthy tissues have been compared against previously published numerical and experimental studies, indicating the accuracy of the model. The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) of the generated PET sample and the experimental one are 0.72 and 28.53, respectively. Our results demonstrate that a combination of biomathematical modeling and GAN-based augmentation models provides a robust framework for the non-invasive and accurate generation of synthetic PET images of solid tumors in different stages.
| S-EPMC9179454 | biostudies-literature
Project description:PurposeStereotactic radiotherapy (SRT) has become widely accepted as a treatment of choice for patients with a small number of brain metastases that are of an acceptable size, allowing for better target dose conformity, resulting in high local control rates and better sparing of organs at risk. An MRI-only workflow could reduce the risk of misalignment between magnetic resonance imaging (MRI) brain studies and computed tomography (CT) scanning for SRT planning, while shortening delays in planning. Given the absence of a calibrated electronic density in MRI, we aimed to assess the equivalence of synthetic CTs generated by a generative adversarial network (GAN) for planning in the brain SRT setting.MethodsAll patients with available MRIs and treated with intra-cranial SRT for brain metastases from 2014 to 2018 in our institution were included. After co-registration between the diagnostic MRI and the planning CT, a synthetic CT was generated using a 2D-GAN (2D U-Net). Using the initial treatment plan (Pinnacle v9.10, Philips Healthcare), dosimetric comparison was performed using main dose-volume histogram (DVH) endpoints in respect to ICRU 91 guidelines (Dmax, Dmean, D2%, D50%, D98%) as well as local and global gamma analysis with 1%/1 mm, 2%/1 mm and 2%/2 mm criteria and a 10% threshold to the maximum dose. t-test analysis was used for comparison between the two cohorts (initial and synthetic dose maps).Results184 patients were included, with 290 treated brain metastases. The mean number of treated lesions per patient was 1 (range 1-6) and the median planning target volume (PTV) was 6.44 cc (range 0.12-45.41). Local and global gamma passing rates (2%/2 mm) were 99.1 CI95% (98.1-99.4) and 99.7 CI95% (99.6-99.7) respectively (CI: confidence interval). DVHs were comparable, with no significant statistical differences regarding ICRU 91's endpoints.ConclusionsOur study is the first to compare GAN-generated CT scans from diagnostic brain MRIs with initial CT scans for the planning of brain stereotactic radiotherapy. We found high similarity between the planning CT and the synthetic CT for both the organs at risk and the target volumes. Prospective validation is under investigation at our institution.
| S-EPMC7959466 | biostudies-literature
Project description:PurposeMany neurological diseases affect small structures in the brain and, as such, reliable visual evaluation and accurate quantification are required. Recent technological developments made the clinical use of hybrid positron emission tomography/magnetic resonance (PET/MR) systems possible, providing both functional and anatomical information in a single imaging session. Nevertheless, there is a trade-off between spatial resolution and image quality (contrast and noise), which is dictated mainly by the chosen acquisition and reconstruction protocols. Image reconstruction algorithms using spherical symmetric basis functions (blobs) for image representation have a number of additional parameters that impact both the qualitative and quantitative image characteristics. Hence, a detailed investigation of the blob-based reconstruction characteristics using different parameters is needed to achieve optimal reconstruction results.ProceduresThis work evaluated the impact of a range of blob parameters on image quality and quantitative accuracy of brain PET images acquired on the Ingenuity Time-of-Flight (TOF) PET/MR system. Two different phantoms were used to simulate brain imaging applications. Image contrast and noise characteristics were assessed using an image quality phantom. Quantitative performance in a clinical setting was investigated using the Hoffman 3D brain phantom at various count levels. Furthermore, the visual quality of four clinical studies was scored blindly by two experienced physicians to qualitatively evaluate the influence of different reconstruction protocols, hereby providing indications on parameters producing the best image quality.ResultsQuantitative evaluation using the image quality phantom showed that larger basis function radii result in lower contrast recovery (∼2%) and lower variance levels (∼15%). The brain phantom and clinical studies confirmed these observations since lower contrast was seen between anatomical structures. High and low count statistics gave comparable values. The qualitative evaluation of the clinical studies, based on the assessment performed by the physicians, showed a preference towards lower image variance levels with a slightly lower contrast, favoring higher radii and four iterations.ConclusionThis study systematically evaluated a number of basis function parameters and their quantitative and qualitative effect within PET image reconstruction in the context of brain imaging. A range of blob parameters can minimize error and provided optimal image quality, where the anatomical structures could be recognized but the exact delineation of these structures is simplified in scans with lower image variance levels and thus, higher radii should be preferred. With the optimization of blob parameters, the reconstructed images were found to be qualitatively improved (optimum parameters {d = 2.0375, alpha = 10.4101, radius = 3.9451}) as assessed by the physicians compared to the current clinical protocol. However, this qualitative improvement is task specific, depending on the desired image characteristics to be extracted. Finally, this work could be used as a guide for application-specific optimal parameter selection.
| S-EPMC4768229 | biostudies-literature
Project description:Analyzing medical data to find abnormalities is a time-consuming and costly task, particularly for rare abnormalities, requiring tremendous efforts from medical experts. Therefore, artificial intelligence has become a popular tool for the automatic processing of medical data, acting as a supportive tool for doctors. However, the machine learning models used to build these tools are highly dependent on the data used to train them. Large amounts of data can be difficult to obtain in medicine due to privacy reasons, expensive and time-consuming annotations, and a general lack of data samples for infrequent lesions. In this study, we present a novel synthetic data generation pipeline, called SinGAN-Seg, to produce synthetic medical images with corresponding masks using a single training image. Our method is different from the traditional generative adversarial networks (GANs) because our model needs only a single image and the corresponding ground truth to train. We also show that the synthetic data generation pipeline can be used to produce alternative artificial segmentation datasets with corresponding ground truth masks when real datasets are not allowed to share. The pipeline is evaluated using qualitative and quantitative comparisons between real data and synthetic data to show that the style transfer technique used in our pipeline significantly improves the quality of the generated data and our method is better than other state-of-the-art GANs to prepare synthetic images when the size of training datasets are limited. By training UNet++ using both real data and the synthetic data generated from the SinGAN-Seg pipeline, we show that the models trained on synthetic data have very close performances to those trained on real data when both datasets have a considerable amount of training data. In contrast, we show that synthetic data generated from the SinGAN-Seg pipeline improves the performance of segmentation models when training datasets do not have a considerable amount of data. All experiments were performed using an open dataset and the code is publicly available on GitHub.
| S-EPMC9060378 | biostudies-literature
Project description:A binocular vision system is a common perception component of an intelligent vehicle. Benefiting from the biomimetic structure, the system is simple and effective. Which are extremely snesitive on external factors, especially missing vision signals. In this paper, a virtual view-generation algorithm based on generative adversarial networks (GAN) is proposed to enhance the robustness of binocular vision systems. The proposed model consists of two parts: generative network and discriminator network. To improve the quality of a virtual view, a generative network structure based on 3D convolutional neural networks (3D-CNN) and attentive mechanisms is introduced to extract the time-series features from image sequences. To avoid gradient vanish during training, the dense block structure is utilized to improve the discriminator network. Meanwhile, three kinds of image features, including image edge, depth map and optical flow are extracted to constrain the supervised training of model. The final results on KITTI and Cityscapes datasets demonstrate that our algorithm outperforms conventional methods, and the missing vision signal can be replaced by a generated virtual view.
| S-EPMC6358985 | biostudies-literature
Project description:[(11)C]TMSX ([7-N-methyl-(11)C]-(E)-8-(3,4,5-trimethoxystyryl)-1,3,7-trimethylxanthine) is a selective adenosine A2A receptor (A2AR) radioligand. In the central nervous system (CNS), A2AR are linked to dopamine D2 receptor function in striatum, but they are also important modulators of inflammation. The golden standard for kinetic modeling of brain [(11)C]TMSX positron emission tomography (PET) is to obtain arterial input function via arterial blood sampling. However, this method is laborious, prone to errors and unpleasant for study subjects. The aim of this work was to evaluate alternative input function acquisition methods for brain [(11)C]TMSX PET imaging. First, a noninvasive, automated method for the extraction of gray matter reference region using supervised clustering (SCgm) was developed. Second, a method for obtaining a population-based arterial input function (PBIF) was implemented. These methods were created using data from 28 study subjects (7 healthy controls, 12 multiple sclerosis patients, and 9 patients with Parkinson's disease). The results with PBIF correlated well with original plasma input, and the SCgm yielded similar results compared with cerebellum as a reference region. The clustering method for extracting reference region and the population-based approach for acquiring input for dynamic [(11)C]TMSX brain PET image analyses appear to be feasible and robust methods, that can be applied in patients with CNS pathology.
| S-EPMC4294409 | biostudies-literature
Project description:BackgroundPositron emission tomography (PET)/computed tomography (CT) with [18F]fluorodeoxyglucose {[18F]FDG} has been shown to be an effective imaging method for the lateralization and localization of epilepsy. However, the efficacy of PET/CT image processing and analysis needs to be improved for clinical application. Our previous research proposed a novel atlas-based image method for PET brain image segmentation and quantification; in this study, we evaluated its effectiveness in clinical patients.MethodsFor image segmentation, a head anatomy template was registered to the subject image by integrating dual-modality image registration and landmark-constraint. The localizations of abnormalities were examined by quantitative comparison using the collected database. The PET/CT images of 20 reference patients and 11 patients with epilepsy were used to compare results between the proposed manual method and statistical parameter mapping (SPM). A dice coefficient analysis was performed on the six central brain regions to assess the segmentation effectiveness, and the diagnostic results of the epileptic regions were examined using pathological results as a reference.ResultsThe dice results of the proposed method were generally higher than those of SPM, with the averaged dice values for the proposed method and SPM being 0.78 and 0.55, respectively, in the reference group (P<0.001), and 0.73 and 0.48, respectively, in the epileptic group (P<0.001). Our proposed method detected all the pathologically reported epileptic defects; however, using the visual assessment method, epileptic defects were missed in three patients. Both the proposed and visual assessment methods incorrectly identified non-epileptic areas as epileptic areas.ConclusionsThe results provide strong evidence of the feasibility of using our proposed method for accurate brain region segmentation in the diagnosis of epilepsy. Our atlas-based approach has promise for clinical application in the image processing and diagnosis of patients with epilepsy.
| S-EPMC9403573 | biostudies-literature
Project description:With the development of the Internet of Multimedia Things (IoMT), an increasing amount of image data is collected by various multimedia devices, such as smartphones, cameras, and drones. This massive number of images are widely used in each field of IoMT, which presents substantial challenges for privacy preservation. In this paper, we propose a new image privacy protection framework in an effort to protect the sensitive personal information contained in images collected by IoMT devices. We aim to use deep neural network techniques to identify the privacy-sensitive content in images, and then protect it with the synthetic content generated by generative adversarial networks (GANs) with differential privacy (DP). Our experiment results show that the proposed framework can effectively protect users' privacy while maintaining image utility.
| S-EPMC7795307 | biostudies-literature
Project description:PurposeRespiratory motion is one of the major challenges in radiotherapy. In this work, a comprehensive and clinically plausible set of 4D numerical phantoms, together with their corresponding "ground truths," have been developed and validated for 4D radiotherapy applications.MethodsThe phantoms are based on CTs providing density information and motion from multi-breathing-cycle 4D Magnetic Resonance imagings (MRIs). Deformable image registration (DIR) has been utilized to extract motion fields from 4DMRIs and to establish inter-subject correspondence by registering binary lung masks between Computer Tomography (CT) and MRI. The established correspondence is then used to warp the CT according to the 4DMRI motion. The resulting synthetic 4DCTs are called 4DCT(MRI)s. Validation of the 4DCT(MRI) workflow was conducted by directly comparing conventional 4DCTs to derived synthetic 4D images using the motion of the 4DCTs themselves (referred to as 4DCT(CT)s). Digitally reconstructed radiographs (DRRs) as well as 4D pencil beam scanned (PBS) proton dose calculations were used for validation.ResultsBased on the CT image appearance of 13 lung cancer patients and deformable motion of five volunteer 4DMRIs, synthetic 4DCT(MRI)s with a total of 871 different breathing cycles have been generated. The 4DCT(MRI)s exhibit an average superior-inferior tumor motion amplitude of 7 ± 5 mm (min: 0.5 mm, max: 22.7 mm). The relative change of the DRR image intensities of the conventional 4DCTs and the corresponding synthetic 4DCT(CT)s inside the body is smaller than 5% for at least 81% of the pixels for all studied cases. Comparison of 4D dose distributions calculated on 4DCTs and the synthetic 4DCT(CT)s using the same motion achieved similar dose distributions with an average 2%/2 mm gamma pass rate of 90.8% (min: 77.8%, max: 97.2%).ConclusionWe developed a series of numerical 4D lung phantoms based on real imaging and motion data, which give realistic representations of both anatomy and motion scenarios and the accessible "ground truth" deformation vector fields of each 4DCT(MRI). The open-source code and motion data allow foreseen users to generate further 4D data by themselves. These numeric 4D phantoms can be used for the development of new 4D treatment strategies, 4D dose calculations, DIR algorithm validations, as well as simulations of motion mitigation and different online image guidance techniques for both proton and photon radiation therapy.
| S-EPMC9313613 | biostudies-literature
Project description:Generating synthetic baseline populations is a fundamental step of agent-based modeling and simulation, which is growing fast in a wide range of socio-economic areas including transportation planning research. Traditionally, in many commercial and non-commercial microsimulation systems, the iterative proportional fitting (IPF) procedure has been used for creating the joint distribution of individuals when combining a reference joint distribution with target marginal distributions. Although IPF is simple, computationally efficient, and rigorously founded, it is unclear whether IPF well preserves the dependence structure of the reference joint table sufficiently when fitting it to target margins. In this paper, a novel method is proposed based on the copula concept in order to provide an alternative approach to the problem that IPF resolves. The dependency characteristic measures were computed and the results from the proposed method and IPF were compared. In most test cases, the proposed method outperformed IPF in preserving the dependence structure of the reference joint distribution.
| S-EPMC4973930 | biostudies-literature