Search

IntroductionTask-based language fMRI is a non-invasive method of identifying brain regions subserving language that is used to plan neurosurgical resections which potentially encroach on eloquent regions. The use of unstructured fMRI paradigms, such as naturalistic fMRI, to map language is of increasing interest. Their analysis necessitates the use of alternative methods such as machine learning (ML) and deep learning (DL) because task regressors may be difficult to define in these paradigms.MethodsUsing task-based language fMRI as a starting point, this study investigates the use of different categories of ML and DL algorithms to identify brain regions subserving language. Data comprising of seven task-based language fMRI paradigms were collected from 26 individuals, and ML and DL models were trained to classify voxel-wise fMRI time series.ResultsThe general machine learning and the interval-based methods were the most promising in identifying language areas using fMRI time series classification. The geneal machine learning method achieved a mean whole-brain Area Under the Receiver Operating Characteristic Curve (AUC) of 0.97±0.03, mean Dice coefficient of 0.6±0.34 and mean Euclidean distance of 2.7±2.4 mm between activation peaks across the evaluated regions of interest. The interval-based method achieved a mean whole-brain AUC of 0.96±0.03, mean Dice coefficient of 0.61±0.33 and mean Euclidean distance of 3.3±2.7 mm between activation peaks across the evaluated regions of interest.DiscussionThis study demonstrates the utility of different ML and DL methods in classifying task-based language fMRI time series. A potential application of these methods is the identification of language activation from unstructured paradigms.

Diffusional kurtosis imaging (DKI) is a methodology for measuring the extent of non-Gaussian diffusion in biological tissue, which has shown great promise in clinical diagnosis, treatment planning, and monitoring of many neurological diseases and disorders. However, robust, fast, and accurate estimation of kurtosis from clinically feasible data acquisitions remains a challenge. In this study, we first outline a new accurate approach of estimating mean kurtosis via the sub-diffusion mathematical framework. Crucially, this extension of the conventional DKI overcomes the limitation on the maximum b-value of the latter. Kurtosis and diffusivity can now be simply computed as functions of the sub-diffusion model parameters. Second, we propose a new fast and robust fitting procedure to estimate the sub-diffusion model parameters using two diffusion times without increasing acquisition time as for the conventional DKI. Third, our sub-diffusion-based kurtosis mapping method is evaluated using both simulations and the Connectome 1.0 human brain data. Exquisite tissue contrast is achieved even when the diffusion encoded data is collected in only minutes. In summary, our findings suggest robust, fast, and accurate estimation of mean kurtosis can be realised within a clinically feasible diffusion-weighted magnetic resonance imaging data acquisition time.

Abstract Background Accurate measurement of the arterial input function (AIF) is crucial for parametric PET studies, but the AIF is commonly derived from invasive arterial blood sampling. It is possible to use an image-derived input function (IDIF) obtained by imaging a large blood pool, but IDIF measurement in PET brain studies performed on standard field of view scanners is challenging due to lack of a large blood pool in the field-of-view. Here we describe a novel automated approach to estimate the AIF from brain images. Results Total body 18F-FDG PET data from 12 subjects were split into a model adjustment group (n = 6) and a validation group (n = 6). We developed an AIF estimation framework using wavelet-based methods and unsupervised machine learning to distinguish arterial and venous activity curves, compared to the IDIF from the descending aorta. All of the automatically extracted AIFs in the validation group had similar shape to the IDIF derived from the descending aorta IDIF. The average area under the curve error and normalised root mean square error across validation data were − 1.59 ± 2.93% and 0.17 ± 0.07. Conclusions Our automated AIF framework accurately estimates the AIF from brain images. It reduces operator-dependence, and could facilitate the clinical adoption of parametric PET.

IntroductionThe reconstruction of PET images involves converting sinograms, which represent the measured counts of radioactive emissions using detector rings encircling the patient, into meaningful images. However, the quality of PET data acquisition is impacted by physical factors, photon count statistics and detector characteristics, which affect the signal-to-noise ratio, resolution and quantitative accuracy of the resulting images. To address these influences, correction methods have been developed to mitigate each of these issues separately. Recently, generative adversarial networks (GANs) based on machine learning have shown promise in learning the complex mapping between acquired PET data and reconstructed tomographic images. This study aims to investigate the properties of training images that contribute to GAN performance when non-clinical images are used for training. Additionally, we describe a method to correct common PET imaging artefacts without relying on patient-specific anatomical images.MethodsThe modular GAN framework includes two GANs. Module 1, resembling Pix2pix architecture, is trained on non-clinical sinogram-image pairs. Training data are optimised by considering image properties defined by metrics. The second module utilises adaptive instance normalisation and style embedding to enhance the quality of images from Module 1. Additional perceptual and patch-based loss functions are employed in training both modules. The performance of the new framework was compared with that of existing methods, (filtered backprojection (FBP) and ordered subset expectation maximisation (OSEM) without and with point spread function (OSEM-PSF)) with respect to correction for attenuation, patient motion and noise in simulated, NEMA phantom and human imaging data. Evaluation metrics included structural similarity (SSIM), peak-signal-to-noise ratio (PSNR), relative root mean squared error (rRMSE) for simulated data, and contrast-to-noise ratio (CNR) for NEMA phantom and human data.ResultsFor simulated test data, the performance of the proposed framework was both qualitatively and quantitatively superior to that of FBP and OSEM. In the presence of noise, Module 1 generated images with a SSIM of 0.48 and higher. These images exhibited coarse structures that were subsequently refined by Module 2, yielding images with an SSIM higher than 0.71 (at least 22% higher than OSEM). The proposed method was robust against noise and motion. For NEMA phantoms, it achieved higher CNR values than OSEM. For human images, the CNR in brain regions was significantly higher than that of FBP and OSEM (p

BackgroundCross-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.MethodsWe 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.ResultsHigh 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.ConclusionSynthesis of SPECT from MRI or PET can potentially reduce the number of scans needed for epilepsy patient evaluation and reduce patient exposure to radiation.

Abstract Background In parametric PET, kinetic parameters are extracted from dynamic PET images. It is not commonly used in clinical practice because of long scan times and the requirement for an arterial input function (AIF). To address these limitations, we designed an 18F-fluorodeoxyglucose (18F-FDG) triple injection dynamic PET protocol for brain imaging with a standard field of view PET scanner using a 24-min imaging window and an input function modeled using measurements from a region of interest placed over the left ventricle. Methods To test the protocol in 6 healthy participants, we examined the quality of voxel-based maps of kinetic parameters in the brain generated using the two-tissue compartment model and compared estimated parameter values with previously published values. We also utilized data from a 36-min validation imaging window to compare (1) the modeled AIF against the input function measured in the validation window; and (2) the net influx rate ( $$K_{i}$$ K i ) computed using parameter estimates from the short imaging window against the net influx rate obtained using Patlak analysis in the validation window. Results Compared to the AIF measured in the validation window, the input function estimated from the short imaging window achieved a mean area under the curve error of 9%. The voxel-wise Pearson’s correlation between $$K_{i}$$ K i estimates from the short imaging window and the validation imaging window exceeded 0.95. Conclusion The proposed 24-min triple injection protocol enables parametric 18F-FDG neuroimaging with noninvasive estimation of the AIF from cardiac images using a standard field of view PET scanner.

Abstract Background The indirect method for generating parametric images in positron emission tomography (PET) involves the acquisition and reconstruction of dynamic images and temporal modelling of tissue activity given a measured arterial input function. This approach is not robust, as noise in each dynamic image leads to a degradation in parameter estimation. Direct methods incorporate into the image reconstruction step both the kinetic and noise models, leading to improved parametric images. These methods require extensive computational time and large computing resources. Machine learning methods have demonstrated significant potential in overcoming these challenges. But they are limited by the requirement of a paired training dataset. A further challenge within the existing framework is the use of state-of-the-art arterial input function estimation via temporal arterial blood sampling, which is an invasive procedure, or an additional magnetic resonance imaging (MRI) scan for selecting a region where arterial blood signal can be measured from the PET image. We propose a novel machine learning approach for reconstructing high-quality parametric brain images from histoimages produced from time-of-flight PET data without requiring invasive arterial sampling, an MRI scan, or paired training data from standard field-of-view scanners. Result The proposed is tested on a simulated phantom and five oncological subjects undergoing an 18F-FDG-PET scan of the brain using Siemens Biograph Vision Quadra. Kinetic parameters set in the brain phantom correlated strongly with the estimated parameters (K 1 , k 2 and k 3, Pearson correlation coefficient of 0.91, 0.92 and 0.93) and a mean squared error of less than 0.0004. In addition, our method significantly outperforms (p

Quantitative susceptibility mapping (QSM) is an MRI post-processing technique that produces spatially resolved magnetic susceptibility maps from phase data. However, the traditional QSM reconstruction pipeline involves multiple non-trivial steps, including phase unwrapping, background field removal, and dipole inversion. These intermediate steps not only increase the reconstruction time but accumulates errors. This study aims to overcome existing limitations by developing a Laplacian-of-Trigonometric-functions (LoT) enhanced deep neural network for near-instant quantitative field and susceptibility mapping (i.e., iQFM and iQSM) from raw MRI phase data. The proposed iQFM and iQSM methods were compared with established reconstruction pipelines on simulated and in vivo datasets. In addition, experiments on patients with intracranial hemorrhage and multiple sclerosis were also performed to test the generalization of the proposed neural networks. The proposed iQFM and iQSM methods in healthy subjects yielded comparable results to those involving the intermediate steps while dramatically improving reconstruction accuracies on intracranial hemorrhages with large susceptibilities. High susceptibility contrast between multiple sclerosis lesions and healthy tissue was also achieved using the proposed methods. Comparative studies indicated that the most significant contributor to iQFM and iQSM over conventional multi-step methods was the elimination of traditional Laplacian unwrapping. The reconstruction time on the order of minutes for traditional approaches was shortened to around 0.1 s using the trained iQFM and iQSM neural networks.

Diffusion MRI measures of the human brain provide key insight into microstructural variations across individuals and into the impact of central nervous system diseases and disorders. One approach to extract information from diffusion signals has been to use biologically relevant analytical models to link millimetre scale diffusion MRI measures with microscale influences. The other approach has been to represent diffusion as an anomalous transport process and infer microstructural information from the different anomalous diffusion equation parameters. In this study, we investigated how parameters of various anomalous diffusion models vary with age in the human brain white matter, particularly focusing on the corpus callosum. We first unified several established anomalous diffusion models (the super-diffusion, sub-diffusion, quasi-diffusion and fractional Bloch-Torrey models) under the continuous time random walk modelling framework. This unification allows a consistent parameter fitting strategy to be applied from which meaningful model parameter comparisons can be made. We then provided a novel way to derive the diffusional kurtosis imaging (DKI) model, which is shown to be a degree two approximation of the sub-diffusion model. This link between the DKI and sub-diffusion models led to a new robust technique for generating maps of kurtosis and diffusivity using the sub-diffusion parameters βSUB and DSUB. Superior tissue contrast is achieved in kurtosis maps based on the sub-diffusion model. 7T diffusion weighted MRI data for 65 healthy participants in the age range 19–78 years was used in this study. Results revealed that anomalous diffusion model parameters α and β have shown consistent positive correlation with age in the corpus callosum, indicating α and β are sensitive to tissue microstructural changes in ageing.