A generalized Gaussian image model for edge-preserving MAP estimation

Attentional Ptycho-Tomography (APT) for three-dimensional nanoscale X-ray imaging with minimal data acquisition and computation time

Noninvasive X-ray imaging of nanoscale three-dimensional objects, such as integrated circuits (ICs), generally requires two types of scanning: ptychographic, which is translational and returns estimates of the complex electromagnetic field through the IC; combined with a tomographic scan, which collects these complex field projections from multiple angles. Here, we present Attentional Ptycho-Tomography (APT), an approach to drastically reduce the amount of angular scanning, and thus the total acquisition time. APT is machine learning-based, utilizing axial self-Attention for Ptycho-Tomographic reconstruction. APT is trained to obtain accurate reconstructions of the ICs, despite the incompleteness of the measurements. The training process includes regularizing priors in the form of typical patterns found in IC interiors, and the physics of X-ray propagation through the IC. We show that APT with ×12 reduced angles achieves fidelity comparable to the gold standard Simultaneous Algebraic Reconstruction Technique (SART) with the original set of angles. When using the same set of reduced angles, then APT also outperforms Filtered Back Projection (FBP), Simultaneous Iterative Reconstruction Technique (SIRT) and SART. The time needed to compute the reconstruction is also reduced, because the trained neural network is a forward operation, unlike the iterative nature of these alternatives. Our experiments show that, without loss in quality, for a 4.48 × 93.2 × 3.92 µm³ IC (≃6 × 10⁸ voxels), APT reduces the total data acquisition and computation time from 67.96 h to 38 min. We expect our physics-assisted and attention-utilizing machine learning framework to be applicable to other branches of nanoscale imaging, including materials science and biological imaging.

Noise-resilient deep learning for integrated circuit tomography

X-ray tomography is a non-destructive imaging technique that reveals the interior of an object from its projections at different angles. Under sparse-view and low-photon sampling, regularization priors are required to retrieve a high-fidelity reconstruction. Recently, deep learning has been used in X-ray tomography. The prior learned from training data replaces the general-purpose priors in iterative algorithms, achieving high-quality reconstructions with a neural network. Previous studies typically assume the noise statistics of test data are acquired a priori from training data, leaving the network susceptible to a change in the noise characteristics under practical imaging conditions. In this work, we propose a noise-resilient deep-reconstruction algorithm and apply it to integrated circuit tomography. By training the network with regularized reconstructions from a conventional algorithm, the learned prior shows strong noise resilience without the need for additional training with noisy examples, and allows us to obtain acceptable reconstructions with fewer photons in test data. The advantages of our framework may further enable low-photon tomographic imaging where long acquisition times limit the ability to acquire a large training set.

A tabletop X-ray tomography instrument for nanometer-scale imaging: reconstructions

We show three-dimensional reconstructions of a region of an integrated circuit from a 130 nm copper process. The reconstructions employ x-ray computed tomography, measured with a new and innovative high-magnification x-ray microscope. The instrument uses a focused electron beam to generate x-rays in a 100 nm spot and energy-resolving x-ray detectors that minimize backgrounds and hold promise for the identification of materials within the sample. The x-ray generation target, a layer of platinum, is fabricated on the circuit wafer itself. A region of interest is imaged from a limited range of angles and without physically removing the region from the larger circuit. The reconstruction is consistent with the circuit's design file.

A Novel Strong S-Box Design Using Quantum Crossover and Chaotic Boolean Functions for Symmetric Cryptosystems

In this paper, we propose a new method for drawing a cryptographically strong substitution box using the Lorenz system and quantum genetic algorithm techniques. We used the chaotic function to generate an initial random sequence of bits and the quantum crossover to provide a new and improved substitution box with increased non-linearity. The aim of the proposed algorithm was to generate a strong and secure substitution box that can be utilized in symmetric cryptosystems. The use of chaotic Boolean functions, genetic algorithm techniques, and the quantum crossover helped achieve this goal, and statistical tests further confirmed the randomness and efficiency of the generated substitution box. The results of the statistical test suite showed that the substitution box produced by the proposed algorithm is a “pass” in terms of randomness and has strong cryptographic properties. The tests include a frequency (monobit) test, a frequency test within a block, a linear complexity test, an approximate entropy test, and a cumulative sums test among others. The p-values obtained in the tests indicate that the randomness of the generated substitution box meets the requirements of a cryptographically secure substitution box.

A domain-agnostic MR reconstruction framework using a randomly weighted neural network

PURPOSE

To design a randomly-weighted neural network that performs domain-agnostic MR image reconstruction from undersampled k-space data without the need for ground truth or extensive in-vivo training datasets. The network performance must be similar to the current state-of-the-art algorithms that require large training datasets.

METHODS

We propose a Weight Agnostic randomly weighted Network method for MRI reconstruction (termed WAN-MRI) which does not require updating the weights of the neural network but rather chooses the most appropriate connections of the network to reconstruct the data from undersampled k-space measurements. The network architecture has three components, i.e. (1) Dimensionality Reduction Layers comprising of 3d convolutions, ReLu, and batch norm; (2) Reshaping Layer is Fully Connected layer; and (3) Upsampling Layers that resembles the ConvDecoder architecture. The proposed methodology is validated on fastMRI knee and brain datasets.

RESULTS

The proposed method provides a significant boost in performance for structural similarity index measure (SSIM) and root mean squared error (RMSE) scores on fastMRI knee and brain datasets at an undersampling factor of R=4 and R=8 while trained on fractal and natural images, and fine-tuned with only 20 samples from the fastMRI training k-space dataset. Qualitatively, we see that classical methods such as GRAPPA and SENSE fail to capture the subtle details that are clinically relevant. We either outperform or show comparable performance with several existing deep learning techniques (that require extensive training) like GrappaNET, VariationNET, J-MoDL, and RAKI.

CONCLUSION

The proposed algorithm (WAN-MRI) is agnostic to reconstructing images of different body organs or MRI modalities and provides excellent scores in terms of SSIM, PSNR, and RMSE metrics and generalizes better to out-of-distribution examples. The methodology does not require ground truth data and can be trained using very few undersampled multi-coil k-space training samples.

Using Mean Arterial Pressure in Hypertension Diagnosis versus Using Either Systolic or Diastolic Blood Pressure Measurements

Hypertension is a severe and highly prevalent disease. It is considered a leading contributor to mortality worldwide. Diagnosis guidelines for hypertension use systolic and diastolic blood pressure (BP) together. Mean arterial pressure (MAP), which refers to the average of the arterial blood pressure through a single cardiac cycle, can be an alternative index that may capture the overall exposure of the person to a heightened pressure. A clinical hypothesis, however, suggests that in patients over 50 years old in age, systolic BP may be more predictive of adverse events, while in patients under 50 years old, diastolic BP may be slightly more predictive. In this study, we investigated the correlation between cerebrovascular changes, (impacted by hypertension), and MAP, systolic BP, and diastolic BP separately. Several experiments were conducted using real and synthetic magnetic resonance angiography (MRA) data, along with corresponding BP measurements. Each experiment employs the following methodology: First, MRA data were processed to remove noise, bias, or inhomogeneity. Second, the cerebrovasculature was delineated for MRA subjects using a 3D adaptive region growing connected components algorithm. Third, vascular features (changes in blood vessel’s diameters and tortuosity) that describe cerebrovascular alterations that occur prior to and during the development of hypertension were extracted. Finally, feature vectors were constructed, and data were classified using different classifiers, such as SVM, KNN, linear discriminant, and logistic regression, into either normotensives or hypertensives according to the cerebral vascular alterations and the BP measurements. The initial results showed that MAP would be more beneficial and accurate in identifying the cerebrovascular impact of hypertension (accuracy up to 95.2%) than just using either systolic BP (accuracy up to 89.3%) or diastolic BP (accuracy up to 88.9%). This result emphasizes the pathophysiological significance of MAP and supports prior views that this simple measure may be a superior index for the definition of hypertension and research on hypertension.

Comparison of supervised-learning approaches for designing a channelized observer for image quality assessment in CT

BACKGROUND

The current paradigm for evaluating computed tomography (CT) system performance relies on a task-based approach. As the Hotelling observer (HO) provides an upper bound of observer performances in specific signal detection tasks, the literature advocates HO use for optimization purposes. However, computing the HO requires calculating the inverse of the image covariance matrix, which is often intractable in medical applications. As an alternative, dimensionality reduction has been extensively investigated to extract the task-relevant features from the raw images. This can be achieved by using channels, which yields the channelized-HO (CHO). The channels are only considered efficient when the channelized observer (CO) can approximate its unconstrained counterpart. Previous work has demonstrated that supervised learning-based methods can usually benefit CO design, either for generating efficient channels using partial least squares (PLS) or for replacing the Hotelling detector with machine-learning (ML) methods.

PURPOSE

Here we investigated the efficiency of a supervised ML-algorithm used to design a CO for predicting the performance of unconstrained HO. The ML-algorithm was applied either (1) in the estimator for dimensionality reduction, or (2) in the detector function.

METHODS

A channelized support vector machine (CSVM) was employed and compared against the CHO in terms of ability to predict HO performances. Both the CSVM and the CHO were estimated with channels derived from the singular value decomposition (SVD) of the system operator, principal component analysis (PCA), and PLS. The huge variety of regularization strategies proposed by CT system vendors for statistical image reconstruction (SIR) make the generalization capability of an observer a key point to consider upfront of implementation in clinical practice. To evaluate the generalization properties of the observers, we adopted a 2-step testing process: (1) achieved with the same regularization strategy (as in the training phase) and (2) performed using different reconstruction properties. We generated simulated- signal-known-exactly/background-known-exactly (SKE/BKE) tasks in which different noise structures were generated using Markov random field (MRF) regularizations using either a Green or a quadratic, function.

RESULTS

The CSVM outperformed the CHO for all types of channels and regularization strategies. Furthermore, even though both COs generalized well to images reconstructed with the same regularization strategy as the images considered in the training phase, the CHO failed to generalize to images reconstructed differently whereas the CSVM managed to successfully generalize. Lastly, the proposed CSVM observer used with PCA channels outperformed the CHO with PLS channels while using a smaller training data set.

CONCLUSION

These results argue for introducing the supervised-learning paradigm in the detector function rather than in the operator of the channels when designing a CO to provide an accurate estimate of HO performance. The CSVM with PCA channels proposed here could be used as a surrogate for HO in image quality assessment.

Sparse-view and limited-angle CT reconstruction with untrained networks and deep image prior

BACKGROUND AND OBJECTIVE

Neural network based image reconstruction methods are becoming increasingly popular. However, limited training data and the lack of theoretical guarantees for generalizability raised concerns, especially in biomedical imaging applications. These challenges are known to lead to an unstable reconstruction process that poses significant problems in biomedical image reconstruction. In this paper, we present a new framework that uses untrained generator networks to tackle this challenge, leveraging the structure of deep networks for regularizing solutions based on a technique known as Deep Image Prior (DIP).

METHODS

To achieve a high reconstruction accuracy, we propose a framework optimizing both the latent vector and the weights of a generator network during the reconstruction process. We also propose the corresponding reconstruction strategies to improve the stability and convergent performance of the proposed framework. Furthermore, instead of calculating forward projection in each iteration, we propose implementing its normal operator as a convolutional kernel under parallel beam geometry, thus greatly accelerating the calculation.

RESULTS

Our experiments show that the proposed framework has significant improvements over other state-of-the-art conventional, pre-trained, and untrained methods under sparse-view, limited-angle, and low-dose conditions.

CONCLUSIONS

Applying to parallel beam X-ray imaging, our framework shows advantages in speed, accuracy, and stability of the reconstruction process. We also show that the proposed framework is compatible with all differentiable regularizations that are commonly used in biomedical image reconstruction literature. Our framework can also be used as a post-processing technique to further improve the reconstruction generated by any other reconstruction methods. Furthermore, the proposed framework requires no training data and can be adjusted on-demand to adapt to different conditions (e.g. noise level, geometry, and imaged object).

Physics-assisted generative adversarial network for X-ray tomography

X-ray tomography is capable of imaging the interior of objects in three dimensions non-invasively, with applications in biomedical imaging, materials science, electronic inspection, and other fields. The reconstruction process can be an ill-conditioned inverse problem, requiring regularization to obtain satisfactory results. Recently, deep learning has been adopted for tomographic reconstruction. Unlike iterative algorithms which require a distribution that is known a priori, deep reconstruction networks can learn a prior distribution through sampling the training distributions. In this work, we develop a Physics-assisted Generative Adversarial Network (PGAN), a two-step algorithm for tomographic reconstruction. In contrast to previous efforts, our PGAN utilizes maximum-likelihood estimates derived from the measurements to regularize the reconstruction with both known physics and the learned prior. Compared with methods with less physics assisting in training, PGAN can reduce the photon requirement with limited projection angles to achieve a given error rate. The advantages of using a physics-assisted learned prior in X-ray tomography may further enable low-photon nanoscale imaging.

Segmentation of Infant Brain Using Nonnegative Matrix Factorization

This study develops an atlas-based automated framework for segmenting infants’ brains from magnetic resonance imaging (MRI). For the accurate segmentation of different structures of an infant’s brain at the isointense age (6–12 months), our framework integrates features of diffusion tensor imaging (DTI) (e.g., the fractional anisotropy (FA)). A brain diffusion tensor (DT) image and its region map are considered samples of a Markov–Gibbs random field (MGRF) that jointly models visual appearance, shape, and spatial homogeneity of a goal structure. The visual appearance is modeled with an empirical distribution of the probability of the DTI features, fused by their nonnegative matrix factorization (NMF) and allocation to data clusters. Projecting an initial high-dimensional feature space onto a low-dimensional space of the significant fused features with the NMF allows for better separation of the goal structure and its background. The cluster centers in the latter space are determined at the training stage by the K-means clustering. In order to adapt to large infant brain inhomogeneities and segment the brain images more accurately, appearance descriptors of both the first-order and second-order are taken into account in the fused NMF feature space. Additionally, a second-order MGRF model is used to describe the appearance based on the voxel intensities and their pairwise spatial dependencies. An adaptive shape prior that is spatially variant is constructed from a training set of co-aligned images, forming an atlas database. Moreover, the spatial homogeneity of the shape is described with a spatially uniform 3D MGRF of the second-order for region labels. In vivo experiments on nine infant datasets showed promising results in terms of the accuracy, which was computed using three metrics: the 95-percentile modified Hausdorff distance (MHD), the Dice similarity coefficient (DSC), and the absolute volume difference (AVD). Both the quantitative and visual assessments confirm that integrating the proposed NMF-fused DTI feature and intensity MGRF models of visual appearance, the adaptive shape prior, and the shape homogeneity MGRF model is promising in segmenting the infant brain DTI.

Studying the Role of Cerebrovascular Changes in Different Compartments in Human Brains in Hypertension Prediction

Hypertension is a major cause of mortality of millions of people worldwide. Cerebral vascular changes are clinically observed to precede the onset of hypertension. The early detection and quantification of these cerebral changes would help greatly in the early prediction of the disease. Hence, preparing appropriate medical plans to avoid the disease and mitigate any adverse events. This study aims to investigate whether studying the cerebral changes in specific regions of human brains (specifically, the anterior, and the posterior compartments) separately, would increase the accuracy of hypertension prediction compared to studying the vascular changes occurring over the entire brain’s vasculature. This was achieved by proposing a computer-aided diagnosis system (CAD) to predict hypertension based on cerebral vascular changes that occur at the anterior compartment, the posterior compartment, and the whole brain separately, and comparing corresponding prediction accuracy. The proposed CAD system works in the following sequence: (1) an MRA dataset of 72 subjects was preprocessed to enhance MRA image quality, increase homogeneity, and remove noise artifacts. (2) each MRA scan was then segmented using an automatic adaptive local segmentation algorithm. (3) the segmented vascular tree was then processed to extract and quantify hypertension descriptive vascular features (blood vessels’ diameters and tortuosity indices) the change of which has been recorded over the time span of the 2-year study. (4) a classification module used these descriptive features along with corresponding differences in blood pressure readings for each subject, to analyze the accuracy of predicting hypertension by examining vascular changes in the anterior, the posterior, and the whole brain separately. Experimental results presented evidence that studying the vascular changes that take place in specific regions of the brain, specifically the anterior compartment reported promising accuracy percentages of up to 90%. However, studying the vascular changes occurring over the entire brain still achieve the best accuracy (of up to 100%) in hypertension prediction compared to studying specific compartments.

A deep learning framework for automated classification of histopathological kidney whole-slide images

Background

Methods

Results

Conclusions

Penalized-Likelihood PET Image Reconstruction Using Similarity-Driven Median Regularization

In this paper, we present a new regularized image reconstruction method for positron emission tomography (PET), where an adaptive weighted median regularizer is used in the context of a penalized-likelihood framework. The motivation of our work is to overcome the limitation of the conventional median regularizer, which has proven useful for tomographic reconstruction but suffers from the negative effect of removing fine details in the underlying image when the edges occupy less than half of the window elements. The crux of our method is inspired by the well-known non-local means denoising approach, which exploits the measure of similarity between the image patches for weighted smoothing. However, our method is different from the non-local means denoising approach in that the similarity measure between the patches is used for the median weights rather than for the smoothing weights. As the median weights, in this case, are spatially variant, they provide adaptive median regularization achieving high-quality reconstructions. The experimental results indicate that our similarity-driven median regularization method not only improves the reconstruction accuracy, but also has great potential for super-resolution reconstruction for PET.

Texture and shape analysis of diffusion-weighted imaging for thyroid nodules classification using machine learning

PURPOSE

To assess whether the integration between (a) functional imaging features that will be extracted from diffusion-weighted imaging (DWI); and (b) shape and texture imaging features as well as volumetric features that will be extracted from T2-weighted magnetic resonance imaging (MRI) can noninvasively improve the diagnostic accuracy of thyroid nodules classification.

PATIENTS AND METHODS

In a retrospective study of 55 patients with pathologically proven thyroid nodules, T2-weighted and diffusion-weighted MRI scans of the thyroid gland were acquired. Spatial maps of the apparent diffusion coefficient (ADC) were reconstructed in all cases. To quantify the nodules' morphology, we used spherical harmonics as a new parametric shape descriptor to describe the complexity of the thyroid nodules in addition to traditional volumetric descriptors (e.g., tumor volume and cuboidal volume). To capture the inhomogeneity of the texture of the thyroid nodules, we used the histogram-based statistics (e.g., kurtosis, entropy, skewness, etc.) of the T2-weighted signal. To achieve the main goal of this paper, a fusion system using an artificial neural network (NN) is proposed to integrate both the functional imaging features (ADC) with the structural morphology and texture features. This framework has been tested on 55 patients (20 patients with malignant nodules and 35 patients with benign nodules), using leave-one-subject-out (LOSO) for training/testing validation tests.

RESULTS

The functionality, morphology, and texture imaging features were estimated for 55 patients. The accuracy of the computer-aided diagnosis (CAD) system steadily improved as we integrate the proposed imaging features. The fusion system combining all biomarkers achieved a sensitivity, specificity, positive predictive value, negative predictive value, F1-score, and accuracy of 92.9 % (confidence interval [CI]: 78.9 % -- 99.5 % ), 95.8 % (CI: 87.4 % -- 99.7 % ), 93 % (CI: 80.7 % -- 99.5 % ), 96 % (CI: 88.8 % -- 99.7 % ), 92.8 % (CI: 83.5 % -- 98.5 % ), and 95.5 % (CI: 88.8 % -- 99.2 % ), respectively, using the LOSO cross-validation approach.

CONCLUSION

The results demonstrated in this paper show the promise that integrating the functional features with morphology as well as texture features by using the current state-of-the-art machine learning approaches will be extremely useful for identifying thyroid nodules as well as diagnosing their malignancy.

A pyramidal deep learning pipeline for kidney whole-slide histology images classification

Renal cell carcinoma is the most common type of kidney cancer. There are several subtypes of renal cell carcinoma with distinct clinicopathologic features. Among the subtypes, clear cell renal cell carcinoma is the most common and tends to portend poor prognosis. In contrast, clear cell papillary renal cell carcinoma has an excellent prognosis. These two subtypes are primarily classified based on the histopathologic features. However, a subset of cases can a have a significant degree of histopathologic overlap. In cases with ambiguous histologic features, the correct diagnosis is dependent on the pathologist’s experience and usage of immunohistochemistry. We propose a new method to address this diagnostic task based on a deep learning pipeline for automated classification. The model can detect tumor and non-tumoral portions of kidney and classify the tumor as either clear cell renal cell carcinoma or clear cell papillary renal cell carcinoma. Our framework consists of three convolutional neural networks and the whole slide images of kidney which were divided into patches of three different sizes for input into the networks. Our approach can provide patchwise and pixelwise classification. The kidney histology images consist of 64 whole slide images. Our framework results in an image map that classifies the slide image on the pixel-level. Furthermore, we applied generalized Gauss-Markov random field smoothing to maintain consistency in the map. Our approach classified the four classes accurately and surpassed other state-of-the-art methods, such as ResNet (pixel accuracy: 0.89 Resnet18, 0.92 proposed). We conclude that deep learning has the potential to augment the pathologist’s capabilities by providing automated classification for histopathological images.

X-ray computed tomography using partially coherent Fresnel diffraction with application to an optical fiber

A reconstruction algorithm for partially coherent x-ray computed tomography (XCT) including Fresnel diffraction is developed and applied to an optical fiber. The algorithm is applicable to a high-resolution tube-based laboratory-scale x-ray tomography instrument. The computing time is only a few times longer than the projective counterpart. The algorithm is used to reconstruct, with projections and diffraction, a tilt series acquired at the micrometer scale of a graded-index optical fiber using maximum likelihood and a Bayesian method based on the work of Bouman and Sauer. The inclusion of Fresnel diffraction removes some reconstruction artifacts and use of a Bayesian prior probability distribution removes others, resulting in a substantially more accurate reconstruction.

Design of a 3000-Pixel Transition-Edge Sensor X-Ray Spectrometer for Microcircuit Tomography

Feature sizes in integrated circuits have decreased substantially over time, and it has become increasingly difficult to three-dimensionally image these complex circuits after fabrication. This can be important for process development, defect analysis, and detection of unexpected structures in externally sourced chips, among other applications. Here, we report on a non-destructive, tabletop approach that addresses this imaging problem through x-ray tomography, which we uniquely realize with an instrument that combines a scanning electron microscope (SEM) with a transition-edge sensor (TES) x-ray spectrometer. Our approach uses the highly focused SEM electron beam to generate a small x-ray generation region in a carefully designed target layer that is placed over the sample being tested. With the high collection efficiency and resolving power of a TES spectrometer, we can isolate x-rays generated in the target from background and trace their paths through regions of interest in the sample layers, providing information about the various materials along the x-ray paths through their attenuation functions. We have recently demonstrated our approach using a 240 Mo/Cu bilayer TES prototype instrument on a simplified test sample containing features with sizes of ∼ 1 μm. Currently, we are designing and building a 3000 Mo/Au bilayer TES spectrometer upgrade, which is expected to improve the imaging speed by factor of up to 60 through a combination of increased detector number and detector speed.

A New Framework for Performing Cardiac Strain Analysis from Cine MRI Imaging in Mice

Cardiac magnetic resonance (MR) imaging is one of the most rigorous form of imaging to assess cardiac function in vivo. Strain analysis allows comprehensive assessment of diastolic myocardial function, which is not indicated by measuring systolic functional parameters using with a normal cine imaging module. Due to the small heart size in mice, it is not possible to perform proper tagged imaging to assess strain. Here, we developed a novel deep learning approach for automated quantification of strain from cardiac cine MR images. Our framework starts by an accurate localization of the LV blood pool center-point using a fully convolutional neural network (FCN) architecture. Then, a region of interest (ROI) that contains the LV is extracted from all heart sections. The extracted ROIs are used for the segmentation of the LV cavity and myocardium via a novel FCN architecture. For strain analysis, we developed a Laplace-based approach to track the LV wall points by solving the Laplace equation between the LV contours of each two successive image frames over the cardiac cycle. Following tracking, the strain estimation is performed using the Lagrangian-based approach. This new automated system for strain analysis was validated by comparing the outcome of these analysis with the tagged MR images from the same mice. There were no significant differences between the strain data obtained from our algorithm using cine compared to tagged MR imaging. Furthermore, we demonstrated that our new algorithm can determine the strain differences between normal and diseased hearts.

Far-field thermal imaging below diffraction limit

Non-uniform self-heating and temperature hotspots are major concerns compromising the performance and reliability of submicron electronic and optoelectronic devices. At deep submicron scales where effects such as contact-related artifacts and diffraction limits accurate measurements of temperature hotspots, non-contact thermal characterization can be extremely valuable. In this work, we use a Bayesian optimization framework with generalized Gaussian Markov random field (GGMRF) prior model to obtain accurate full-field temperature distribution of self-heated metal interconnects from their thermoreflectance thermal images (TRI) with spatial resolution 2.5 times below Rayleigh limit for 530nm illumination. Finite element simulations along with TRI experimental data were used to characterize the point spread function of the optical imaging system. In addition, unlike iterative reconstruction algorithms that use ad hoc regularization parameters in their prior models to obtain the best quality image, we used numerical experiments and finite element modeling to estimate the regularization parameter for solving a real experimental inverse problem.

Bayesian reconstruction method for underwater 3D range-gated imaging enhancement

We investigate a systematic improvement for 3D range-gated imaging in scattering environments. Drawbacks including absorption, ambient light, and scattering effect are studied. The former two are compensated through parameter estimation and preprocessing. With regard to the scattering effect, we propose a new 3D reconfiguration algorithm using a Bayesian approach that incorporates spatial constraints through a general Gaussian Markov random field. The model takes both scene depth and albedo into account, which provides a more informative and accurate restoration result. Hyper-parameters for the statistical mechanism are evaluated adaptively in the procedure and an iterated conditional mode optimization algorithm is employed to find an optimum solution. The performance of our method was assessed via conducting various experiments and the results also indicate that the proposed method is helpful for restoring the 2D image of a scene with improved visibility.

A computer-aided diagnosis system for differentiation and delineation of malignant regions on whole-slide prostate histopathology image using spatial statistics and multidimensional DenseNet

PURPOSE

Prostate cancer (PCa) is a major health concern in aging males, and proper management of the disease depends on accurately interpreting pathology specimens. However, reading prostatectomy histopathology slides, which is basically for staging, is usually time consuming and differs from reading small biopsy specimens, which is mainly used for diagnosis. Generally, each prostatectomy specimen generates tens of large tissue sections and for each section, the malignant region needs to be delineated to assess the amount of tumor and its burden. With the aim of reducing the workload of pathologists, in this study, we focus on developing a computer-aided diagnosis (CAD) system based on a densely connected convolutional neural network (DenseNet) for whole-slide histopathology images to outline the malignant regions.

METHODS

We use an efficient color normalization process based on ranklet transformation to automatically correct the intensity of the images. Additionally, we use spatial probability to segment the tissue structure regions for different tissue recognition patterns. Based on the segmentation, we incorporate a multidimensional structure into DenseNet to determine if a particular prostatic region is benign or malignant.

RESULTS

As demonstrated by the experimental results with a test set of 2,663 images from 32 whole-slide prostate histopathology images, our proposed system achieved 0.726, 0.6306, and 0.5209 in the average of the Dice coefficient, Jaccard similarity coefficient, and Boundary F1 score measures, respectively. Then, the accuracy, sensitivity, specificity, and the area under the ROC curve (AUC) of the proposed classification method were observed to be 95.0% (2544/2663), 96.7% (1210/1251), 93.9% (1334/1412), and 0.9831, respectively.

DISCUSSIONS

We provide a detailed discussion on how our proposed system demonstrates considerable improvement compared with similar methods considered in previous researches as well as how it can be used for delineating malignant regions.

Sparse Matrix-Based HPC Tomography

Tomographic imaging has benefited from advances in X-ray sources, detectors and optics to enable novel observations in science, engineering and medicine. These advances have come with a dramatic increase of input data in the form of faster frame rates, larger fields of view or higher resolution, so high performance solutions are currently widely used for analysis. Tomographic instruments can vary significantly from one to another, including the hardware employed for reconstruction: from single CPU workstations to large scale hybrid CPU/GPU supercomputers. Flexibility on the software interfaces and reconstruction engines are also highly valued to allow for easy development and prototyping. This paper presents a novel software framework for tomographic analysis that tackles all aforementioned requirements. The proposed solution capitalizes on the increased performance of sparse matrix-vector multiplication and exploits multi-CPU and GPU reconstruction over MPI. The solution is implemented in Python and relies on CuPy for fast GPU operators and CUDA kernel integration, and on SciPy for CPU sparse matrix computation. As opposed to previous tomography solutions that are tailor-made for specific use cases or hardware, the proposed software is designed to provide flexible, portable and high-performance operators that can be used for continuous integration at different production environments, but also for prototyping new experimental settings or for algorithmic development. The experimental results demonstrate how our implementation can even outperform state-of-the-art software packages used at advanced X-ray sources worldwide.

Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning

The field of medical image reconstruction has seen roughly four types of methods. The first type tended to be analytical methods, such as filtered back-projection (FBP) for X-ray computed tomography (CT) and the inverse Fourier transform for magnetic resonance imaging (MRI), based on simple mathematical models for the imaging systems. These methods are typically fast, but have suboptimal properties such as poor resolution-noise trade-off for CT. A second type is iterative reconstruction methods based on more complete models for the imaging system physics and, where appropriate, models for the sensor statistics. These iterative methods improved image quality by reducing noise and artifacts. The FDA-approved methods among these have been based on relatively simple regularization models. A third type of methods has been designed to accommodate modified data acquisition methods, such as reduced sampling in MRI and CT to reduce scan time or radiation dose. These methods typically involve mathematical image models involving assumptions such as sparsity or low-rank. A fourth type of methods replaces mathematically designed models of signals and systems with data-driven or adaptive models inspired by the field of machine learning. This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.

A novel computer-aided diagnosis system for the early detection of hypertension based on cerebrovascular alterations

•

3-D CNN segmentation succeeded in delineating cerebrovasculature accurately.

•

Segmentation approach is automatic and applicable on healthy/pathological vessels.

•

Blood flow variability challenge was addressed by processing MRA scans locally.

•

Proposed vascular features were efficient to quantify cerebral changes.

•

Proposed CAD system could help clinicians predict hypertension before its onset.

Hypertension is a leading cause of mortality in the USA. While simple tools such as the sphygmomanometer are widely used to diagnose hypertension, they could not predict the disease before its onset. Clinical studies suggest that alterations in the structure of human brains’ cerebrovasculature start to develop years before the onset of hypertension. In this research, we present a novel computer-aided diagnosis (CAD) system for the early detection of hypertension. The proposed CAD system analyzes magnetic resonance angiography (MRA) data of human brains to detect and track the cerebral vascular alterations and this is achieved using the following steps: i) MRA data are preprocessed to eliminate noise effects, correct the bias field effect, reduce the contrast inhomogeneity using the generalized Gauss-Markov random field (GGMRF) model, and normalize the MRA data, ii) the cerebral vascular tree of each MRA volume is segmented using a 3-D convolutional neural network (3D-CNN), iii) cerebral features in terms of diameters and tortuosity of blood vessels are estimated and used to construct feature vectors, iv) feature vectors are then used to train and test various artificial neural networks to classify data into two classes; normal and hypertensive. A balanced data set of 66 subjects were used to test the CAD system. Experimental results reported a classification accuracy of 90.9% which supports the efficacy of the CAD system components to accurately model and discriminate between normal and hypertensive subjects. Clinicians would benefit from the proposed CAD system to detect and track cerebral vascular alterations over time for people with high potential of developing hypertension and to prepare appropriate treatment plans to mitigate adverse events.

An iterative reconstruction algorithm for pole figure inversion using total variation regularization

This paper describes a new discrete method for inverting X-ray pole figures to estimate the orientation distribution function (ODF). The method employs the equal-volume `cubochoric' representation for uniform discretization of orientation space, SO(3). The forward-projection model is combined with an anisotropic total variation term to iteratively determine the ODF. The efficacy of the new method is evaluated with both model and experimental data and compared with existing discrete and series expansion methods.

Nonconvex image reconstruction via expectation propagation

The problem of efficiently reconstructing tomographic images can be mapped into a Bayesian inference problem over the space of pixels densities. Solutions to this problem are given by pixels assignments that are compatible with tomographic measurements and maximize a posterior probability density. This maximization can be performed with standard local optimization tools when the log-posterior is a convex function, but it is generally intractable when introducing realistic nonconcave priors that reflect typical images features such as smoothness or sharpness. We introduce a new method to reconstruct images obtained from Radon projections by using expectation propagation, which allows us to approximate the intractable posterior. We show, by means of extensive simulations, that, compared to state-of-the-art algorithms for this task, expectation propagation paired with very simple but non-log-concave priors is often able to reconstruct images up to a smaller error while using a lower amount of information per pixel. We provide estimates for the critical rate of information per pixel above which recovery is error-free by means of simulations on ensembles of phantom and real images.

Known-component 3D image reconstruction for improved intraoperative imaging in spine surgery: A clinical pilot study

PURPOSE

Intraoperative imaging plays an increased role in support of surgical guidance and quality assurance for interventional approaches. However, image quality sufficient to detect complications and provide quantitative assessment of the surgical product is often confounded by image noise and artifacts. In this work, we translated a three-dimensional model-based image reconstruction (referred to as "Known-Component Reconstruction," KC-Recon) for the first time to clinical studies with the aim of resolving both limitations.

METHODS

KC-Recon builds upon a penalized weighted least-squares (PWLS) method by incorporating models of surgical instrumentation ("known components") within a joint image registration-reconstruction process to improve image quality. Under IRB approval, a clinical pilot study was conducted with 17 spine surgery patients imaged under informed consent using the O-arm cone-beam CT system (Medtronic, Littleton MA) before and after spinal instrumentation. Volumetric images were generated for each patient using KC-Recon in comparison to conventional filtered backprojection (FBP). Imaging performance prior to instrumentation ("preinstrumentation") was evaluated in terms of soft-tissue contrast-to-noise ratio (CNR) and spatial resolution. The quality of images obtained after the instrumentation ("postinstrumentation") was assessed by quantifying the magnitude of metal artifacts (blooming and streaks) arising from pedicle screws. The potential low-dose advantages of the algorithm were tested by simulating low-dose data (down to one-tenth of the dose of standard protocols) from images acquired at normal dose.

RESULTS

Preinstrumentation images (at normal clinical dose and matched resolution) exhibited an average 24.0% increase in soft-tissue CNR with KC-Recon compared to FBP (N = 16, P = 0.02), improving visualization of paraspinal muscles, major vessels, and other soft-tissues about the spine and abdomen. For a total of 72 screws in postinstrumentation images, KC-Recon yielded a significant reduction in metal artifacts: 66.3% reduction in overestimation of screw shaft width due to blooming (P < 0.0001) and reduction in streaks at the screw tip (65.8% increase in attenuation accuracy, P < 0.0001), enabling clearer depiction of the screw within the pedicle and vertebral body for an assessment of breach. Depending on the imaging task, dose reduction up to an order of magnitude appeared feasible while maintaining soft-tissue visibility and metal artifact reduction.

CONCLUSIONS

KC-Recon offers a promising means to improve visualization in the presence of surgical instrumentation and reduce patient dose in image-guided procedures. The improved soft-tissue visibility could facilitate the use of cone-beam CT to soft-tissue surgeries, and the ability to precisely quantify and visualize instrument placement could provide a valuable check against complications in the operating room (cf., postoperative CT).

A Novel Framework for Early Detection of Hypertension using Magnetic Resonance Angiography

Hypertension is a leading mortality cause of 410,000 patients in USA. Cerebrovascular structural changes that occur as a result of chronically elevated cerebral perfusion pressure are hypothesized to precede the onset of systemic hypertension. A novel framework is presented in this manuscript to detect and quantify cerebrovascular changes (i.e. blood vessel diameters and tortuosity changes) using magnetic resonance angiography (MRA) data. The proposed framework consists of: 1) A novel adaptive segmentation algorithm to delineate large as well as small blood vessels locally using 3-D spatial information and appearance features of the cerebrovascular system; 2) Estimating the cumulative distribution function (CDF) of the 3-D distance map of the cerebrovascular system to quantify alterations in cerebral blood vessels' diameters; 3) Calculation of mean and Gaussian curvatures to quantify cerebrovascular tortuosity; and 4) Statistical and correlation analyses to identify the relationship between mean arterial pressure (MAP) and cerebral blood vessels' diameters and tortuosity alterations. The proposed framework was validated using MAP and MRA data collected from 15 patients over a 700-days period. The novel adaptive segmentation algorithm recorded a 92.23% Dice similarity coefficient (DSC), a 94.82% sensitivity, a 99.00% specificity, and a 10.00% absolute vessels volume difference (AVVD) in delineating cerebral blood vessels from surrounding tissues compared to the ground truth. Experiments demonstrated that MAP is inversely related to cerebral blood vessel diameters (p-value < 0.05) globally (over the whole brain) and locally (at circle of Willis and below). A statistically significant direct correlation (p-value < 0.05) was found between MAP and tortuosity (medians of Gaussian and mean curvatures, and average of mean curvature) globally and locally (at circle of Willis and below). Quantification of the cerebrovascular diameter and tortuosity changes may enable clinicians to predict elevated blood pressure before its onset and optimize medical treatment plans of pre-hypertension and hypertension.

Compressed Sensing Radar Imaging: Fundamentals, Challenges, and Advances

In recent years, sparsity-driven regularization and compressed sensing (CS)-based radar imaging methods have attracted significant attention. This paper provides an introduction to the fundamental concepts of this area. In addition, we will describe both sparsity-driven regularization and CS-based radar imaging methods, along with other approaches in a unified mathematical framework. This will provide readers with a systematic overview of radar imaging theories and methods from a clear mathematical viewpoint. The methods presented in this paper include the minimum variance unbiased estimation, least squares (LS) estimation, Bayesian maximum a posteriori (MAP) estimation, matched filtering, regularization, and CS reconstruction. The characteristics of these methods and their connections are also analyzed. Sparsity-driven regularization and CS based radar imaging methods represent an active research area; there are still many unsolved or open problems, such as the sampling scheme, computational complexity, sparse representation, influence of clutter, and model error compensation. We will summarize the challenges as well as recent advances related to these issues.

Automated framework for accurate segmentation of leaf images for plant health assessment

Leaf segmentation is significantly important in assisting ecologists to automatically detect symptoms of disease and other stressors affecting trees. This paper employs state-of-the-art techniques in image processing to introduce an accurate framework for segmenting leaves and diseased leaf spots from images. The proposed framework integrates an appearance model that visually represents the current input image with the color prior information generated from RGB color images that were formerly saved in our database. Our framework consists of four main steps: (1) Enhancing the accuracy of the segmentation at minimum time by making use of contrast changes to automatically identify the region of interest (ROI) of the entire leaf, where the pixel-wise intensity relations are described by an electric field energy model. (2) Modeling the visual appearance of the input image using a linear combination of discrete Gaussians (LCDG) to predict the marginal probability distributions of the grayscale ROI main three classes. (3) Calculating the pixel-wise probabilities of these three classes for the color ROI based on the color prior information of database images that are segmented manually, where the current and prior pixel-wise probabilities are used to find the initial labels. (4) Refining the labels with the generalized Gauss-Markov random field model (GGMRF), which maintains the continuity. The proposed segmentation approach was applied to the leaves of mangrove trees in Abu Dhabi in the United Arab Emirates. Experimental validation showed high accuracy, with a Dice similarity coefficient 90% for distinguishing leaf spot from healthy leaf area.

Prior-Guided Metal Artifact Reduction for Iterative X-Ray Computed Tomography

High-attenuation materials pose significant challenges to computed tomographic imaging. Formed of high mass-density and high atomic number elements, they cause more severe beam hardening and scattering artifacts than do water-like materials. Pre-corrected line-integral density measurements are no longer linearly proportional to the path lengths, leading to reconstructed image suffering from streaking artifacts extending from metal, often along highest-density directions. In this paper, a novel prior-based iterative approach is proposed to reduce metal artifacts. It combines the superiority of statistical methods with the benefits of sinogram completion methods to estimate and correct metal-induced biases. Preliminary results show minimized residual artifacts and significantly improved image quality.

Regularization with Metric Double Integrals of Functions with Values in a Set of Vectors

We present an approach for variational regularization of inverse and imaging problems for recovering functions with values in a set of vectors. We introduce regularization functionals, which are derivative-free double integrals of such functions. These regularization functionals are motivated from double integrals, which approximate Sobolev semi-norms of intensity functions. These were introduced in Bourgain et al. (Another look at Sobolev spaces. In: Menaldi, Rofman, Sulem (eds) Optimal control and partial differential equations-innovations and applications: in honor of professor Alain Bensoussan's 60th anniversary, IOS Press, Amsterdam, pp 439-455, 2001). For the proposed regularization functionals, we prove existence of minimizers as well as a stability and convergence result for functions with values in a set of vectors.

Scatter Corrections in X-Ray Computed Tomography: A Physics-Based Analysis

Fundamental limits for the calculation of scattering corrections within X-ray computed tomography (CT) are found within the independent atom approximation from an analysis of the cross sections, CT geometry, and the Nyquist sampling theorem, suggesting large reductions in computational time compared to existing methods. By modifying the scatter by less than 1 %, it is possible to treat some of the elastic scattering in the forward direction as inelastic to achieve a smoother elastic scattering distribution. We present an analysis showing that the number of samples required for the smoother distribution can be greatly reduced. We show that fixed forced detection can be used with many fewer points for inelastic scattering, but that for pure elastic scattering, a standard Monte Carlo calculation is preferred. We use smoothing for both elastic and inelastic scattering because the intrinsic angular resolution is much poorer than can be achieved for projective tomography. Representative numerical examples are given.

Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network

Low-dose computed tomography (LDCT) has offered tremendous benefits in radiation-restricted applications, but the quantum noise as resulted by the insufficient number of photons could potentially harm the diagnostic performance. Current image-based denoising methods tend to produce a blur effect on the final reconstructed results especially in high noise levels. In this paper, a deep learning-based approach was proposed to mitigate this problem. An adversarially trained network and a sharpness detection network were trained to guide the training process. Experiments on both simulated and real dataset show that the results of the proposed method have very small resolution loss and achieves better performance relative to state-of-the-art methods both quantitatively and visually.

Regularization strategies in statistical image reconstruction of low-dose x-ray CT: A review

Statistical image reconstruction (SIR) methods have shown potential to substantially improve the image quality of low-dose x-ray computed tomography (CT) as compared to the conventional filtered back-projection (FBP) method. According to the maximum a posteriori (MAP) estimation, the SIR methods are typically formulated by an objective function consisting of two terms: (a) a data-fidelity term that models imaging geometry and physical detection processes in projection data acquisition, and (b) a regularization term that reflects prior knowledge or expectations of the characteristics of the to-be-reconstructed image. SIR desires accurate system modeling of data acquisition, while the regularization term also has a strong influence on the quality of reconstructed images. A variety of regularization strategies have been proposed for SIR in the past decades, based on different assumptions, models, and prior knowledge. In this paper, we review the conceptual and mathematical bases of these regularization strategies and briefly illustrate their efficacies in SIR of low-dose CT.

A Bayesian Approach to Eigenspectra Optoacoustic Tomography

The quantification of hemoglobin oxygen saturation (sO2) with multispectral optoacoustic (OA) (photoacoustic) tomography (MSOT) is a complex spectral unmixing problem, since the OA spectra of hemoglobin are modified with tissue depth due to depth (location) and wavelength dependencies of optical fluence in tissue. In a recent work, a method termed eigenspectra MSOT (eMSOT) was proposed for addressing the dependence of spectra on fluence and quantifying blood sO2 in deep tissue. While eMSOT offers enhanced sO2 quantification accuracy over conventional unmixing methods, its performance may be compromised by noise and image reconstruction artifacts. In this paper, we propose a novel Bayesian method to improve eMSOT performance in noisy environments. We introduce a spectral reliability map, i.e., a method that can estimate the level of noise superimposed onto the recorded OA spectra. Using this noise estimate, we formulate eMSOT as a Bayesian inverse problem where the inversion constraints are based on probabilistic graphical models. Results based on numerical simulations indicate that the proposed method offers improved accuracy and robustness under high noise levels due the adaptive nature of the Bayesian method.

CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction

We present a new image reconstruction method that replaces the projector in a projected gradient descent (PGD) with a convolutional neural network (CNN). Recently, CNNs trained as image-to-image regressors have been successfully used to solve inverse problems in imaging. However, unlike existing iterative image reconstruction algorithms, these CNN-based approaches usually lack a feedback mechanism to enforce that the reconstructed image is consistent with the measurements. We propose a relaxed version of PGD wherein gradient descent enforces measurement consistency, while a CNN recursively projects the solution closer to the space of desired reconstruction images. We show that this algorithm is guaranteed to converge and, under certain conditions, converges to a local minimum of a non-convex inverse problem. Finally, we propose a simple scheme to train the CNN to act like a projector. Our experiments on sparse-view computed-tomography reconstruction show an improvement over total variation-based regularization, dictionary learning, and a state-of-the-art deep learning-based direct reconstruction technique.

Effective Pneumothorax Detection for Chest X-Ray Images Using Local Binary Pattern and Support Vector Machine

Automatic image segmentation and feature analysis can assist doctors in the treatment and diagnosis of diseases more accurately. Automatic medical image segmentation is difficult due to the varying image quality among equipment. In this paper, the automatic method employed image multiscale intensity texture analysis and segmentation to solve this problem. In this paper, firstly, SVM is applied to identify common pneumothorax. Features are extracted from lung images with the LBP (local binary pattern). Then, classification of pneumothorax is determined by SVM. Secondly, the proposed automatic pneumothorax detection method is based on multiscale intensity texture segmentation by removing the background and noises in chest images for segmenting abnormal lung regions. The segmentation of abnormal regions is used for texture transformed from computing multiple overlapping blocks. The rib boundaries are identified with Sobel edge detection. Finally, in obtaining a complete disease region, the rib boundary is filled up and located between the abnormal regions.

Automated diabetic retinopathy detection using optical coherence tomography angiography: a pilot study

BACKGROUND

Optical coherence tomography angiography (OCTA) is increasingly being used to evaluate diabetic retinopathy, but the interpretation of OCTA remains largely subjective. The purpose of this study was to design a computer-aided diagnostic (CAD) system to diagnose non-proliferative diabetic retinopathy (NPDR) in an automated fashion using OCTA images.

METHODS

This was a two-centre, cross-sectional study. Adults with type II diabetes mellitus (DMII) were eligible for inclusion. OCTA scans of the macula were taken, and the five vascular maps generated per eye were analysed by a novel CAD system. For the purpose of classification/diagnosis, three different local features-blood vessel density, blood vessel calibre and the size of the foveal avascular zone (FAZ)-were segmented from these images and used to train a new, automated classifier.

RESULTS

One hundred and six patients with DMII were included in the study, 23 with no DR and 83 with mild NPDR. When using features of the superficial retinal map alone, the system demonstrated an accuracy of 80.0% and area under the curve (AUC) of 76.2%. Using the features of the deep retinal map alone, accuracy was 91.4% and AUC 89.2%. When data from both maps were combined, the presented CAD system demonstrated overall accuracy of 94.3%, sensitivity of 97.9%, specificity of 87.0%, area under curve (AUC) of 92.4% and dice similarity coefficient of 95.8%.

CONCLUSION

Automated diagnosis of NPDR using OCTA images is feasible and accurate. Combining this system with OCT data is a plausible next step that would likely improve its robustness.

Spectroscopic stimulated Raman scattering imaging of highly dynamic specimens through matrix completion

Spectroscopic stimulated Raman scattering (SRS) imaging generates chemical maps of intrinsic molecules, with no need for prior knowledge. Despite great advances in instrumentation, the acquisition speed for a spectroscopic SRS image stack is fundamentally bounded by the pixel integration time. In this work, we report three-dimensional sparsely sampled spectroscopic SRS imaging that measures ~20% of pixels throughout the stack. In conjunction with related work in low-rank matrix completion (e.g., the Netflix Prize), we develop a regularized non-negative matrix factorization algorithm to decompose the sub-sampled image stack into spectral signatures and concentration maps. This design enables an acquisition speed of 0.8 s per image stack, with 50 frames in the spectral domain and 40,000 pixels in the spatial domain, which is faster than the conventional raster laser-scanning scheme by one order of magnitude. Such speed allows real-time metabolic imaging of living fungi suspended in a growth medium while effectively maintaining the spatial and spectral resolutions. This work is expected to promote broad application of matrix completion in spectroscopic laser-scanning imaging.

Generalized Adaptive Gaussian Markov Random Field for X-Ray Luminescence Computed Tomography

OBJECTIVE

X-ray luminescence computed tomography (XLCT) is an emerging and promising modality, but suffers from inferior reconstructions and smoothed target shapes. This work aims to improve the image quality with new mathematical framework.

METHODS

We present a Bayesian local regularization framework to tackle the ill-conditioness of XLCT. Different from traditional overall regularization strategies, the proposed method utilizes correlations of neighboring voxels to regularize the solution locally based on generalized adaptive Gaussian Markov random field (GAGMRF), and provides an adjustable parameter to facilitate the edge-preserving property.

RESULTS

Numerical simulations and phantom experiments show that the GAGMRF method yields both high image quality and accurate target shapes.

CONCLUSION

Compared to conventional L2 and L1 regularizations, GAGMRF provides a new and efficient model for high quality imaging based on the Bayesian framework.

SIGNIFICANCE

The GAGMRF method offers a flexible regularization framework to adapt to a wide range of biomedical applications.

A fast stochastic framework for automatic MR brain images segmentation

This paper introduces a new framework for the segmentation of different brain structures (white matter, gray matter, and cerebrospinal fluid) from 3D MR brain images at different life stages. The proposed segmentation framework is based on a shape prior built using a subset of co-aligned training images that is adapted during the segmentation process based on first- and second-order visual appearance characteristics of MR images. These characteristics are described using voxel-wise image intensities and their spatial interaction features. To more accurately model the empirical grey level distribution of the brain signals, we use a linear combination of discrete Gaussians (LCDG) model having positive and negative components. To accurately account for the large inhomogeneity in infant MRIs, a higher-order Markov-Gibbs Random Field (MGRF) spatial interaction model that integrates third- and fourth- order families with a traditional second-order model is proposed. The proposed approach was tested and evaluated on 102 3D MR brain scans using three metrics: the Dice coefficient, the 95-percentile modified Hausdorff distance, and the absolute brain volume difference. Experimental results show better segmentation of MR brain images compared to current open source segmentation tools.

A novel approach for automatic visualization and activation detection of evoked potentials induced by epidural spinal cord stimulation in individuals with spinal cord injury

Voluntary movements and the standing of spinal cord injured patients have been facilitated using lumbosacral spinal cord epidural stimulation (scES). Identifying the appropriate stimulation parameters (intensity, frequency and anode/cathode assignment) is an arduous task and requires extensive mapping of the spinal cord using evoked potentials. Effective visualization and detection of muscle evoked potentials induced by scES from the recorded electromyography (EMG) signals is critical to identify the optimal configurations and the effects of specific scES parameters on muscle activation. The purpose of this work was to develop a novel approach to automatically detect the occurrence of evoked potentials, quantify the attributes of the signal and visualize the effects across a high number of scES parameters. This new method is designed to automate the current process for performing this task, which has been accomplished manually by data analysts through observation of raw EMG signals, a process that is laborious and time-consuming as well as prone to human errors. The proposed method provides a fast and accurate five-step algorithms framework for activation detection and visualization of the results including: conversion of the EMG signal into its 2-D representation by overlaying the located signal building blocks; de-noising the 2-D image by applying the Generalized Gaussian Markov Random Field technique; detection of the occurrence of evoked potentials using a statistically optimal decision method through the comparison of the probability density functions of each segment to the background noise utilizing log-likelihood ratio; feature extraction of detected motor units such as peak-to-peak amplitude, latency, integrated EMG and Min-max time intervals; and finally visualization of the outputs as Colormap images. In comparing the automatic method vs. manual detection on 700 EMG signals from five individuals, the new approach decreased the processing time from several hours to less than 15 seconds for each set of data, and demonstrated an average accuracy of 98.28% based on the combined false positive and false negative error rates. The sensitivity of this method to the signal-to-noise ratio (SNR) was tested using simulated EMG signals and compared to two existing methods, where the novel technique showed much lower sensitivity to the SNR.