An Efficient Capsule-based Network for 2D Left Ventricle Segmentation in Echocardiography Images.

The segmentation of cardiac chambers is essential for the clinical diagnosis and treatment of cardiovascular diseases. It is demonstrated that in cardiac disease, the left ventricle (LV) is extensively involved. Therefore, segmentation of the LV in echocardiographic images is critical for the precise evaluation of factors that influence cardiac function such as LV volume, ejection fraction, and LV mass. Although these measurements could be obtained by manual segmentation of the LV, it would be time-consuming and inaccurate because of the poor quality and low contrast of these images. Convolutional neural networks, commonly referred to as CNNs, have emerged as a highly favored deep learning technique for medical image segmentation. Despite their popularity, the pooling layers in CNNs ignore the spatial information and do not consider the part-whole hierarchy relationships. Furthermore, they require a large training dataset and a large number of parameters. Therefore, Capsule Networks are proposed to address the CNNs limitations. In this study, for the first time, an optimized capsule-based network for object segmentation called SegCaps is proposed to achieve accurate LV segmentation on echocardiography images applied to the CAMUS dataset. The result was compared against the standard 2D-UNet. The modified SegCaps and 2D-UNet achieved an average Dice similarity coefficient (DSC) of 84.48% and 83.28% on LV segmentation, respectively. The capabilities of the CapsNet led to an improvement of 1.44% in DSC with 92.77% fewer parameters than the U-Net. The results indicate that the proposed method leads to accurate and efficient LV segmentation.Clinical Relevance- From a clinical point of view, our findings lead to more precise evaluations of critical cardiac parameters, including ejection fraction as well as left ventricle volume at end-diastole and end-systole.

A Hybrid Capsule Network for Automatic 3D Mandible Segmentation applied in Virtual Surgical Planning.

Automatic mandible segmentation of CT images is an essential step to achieve an accurate preoperative prediction of an intended target in three-dimensional (3D) virtual surgical planning. Segmentation of the mandible is a challenging task due to the complexity of the mandible structure, imaging artifacts, and metal implants or dental filling materials. In recent years, utilizing convolutional neural networks (CNNs) have made significant improvements in mandible segmentation. However, aggregating data at pooling layers in addition to collecting and labeling a large volume of data for training CNNs are significant issues in medical practice. We have optimized data-efficient 3D-UCaps to achieve the advantages of both the capsule network and the CNN, for accurate mandible segmentation on volumetric CT images. A novel hybrid loss function based on a weighted combination of the focal and margin loss functions is also proposed to handle the problem of voxel class imbalance. To evaluate the performance of our proposed method, a similar experiment was conducted with the 3D-UNet. All experiments are performed on the public domain database for computational anatomy (PDDCA). The proposed method and 3D-UNet achieved an average dice coefficient of 90% and 88% on the PDDCA, respectively. The results indicate that the proposed method leads to accurate mandible segmentation and outperforms the popular 3D-UNet model. It is concluded that the proposed approach is very effective as it requires more than 50% fewer parameters than the 3D-UNet.

Accurate Automatic Glioma Segmentation in Brain MRI images Based on CapsNet.

Glioma is a highly invasive type of brain tumor with an irregular morphology and blurred infiltrative borders that may affect different parts of the brain. Therefore, it is a challenging task to identify the exact boundaries of the tumor in an MR image. In recent years, deep learning-based Convolutional Neural Networks (CNNs) have gained popularity in the field of image processing and have been utilized for accurate image segmentation in medical applications. However, due to the inherent constraints of CNNs, tens of thousands of images are required for training, and collecting and annotating such a large number of images poses a serious challenge for their practical implementation. Here, for the first time, we have optimized a network based on the capsule neural network called SegCaps, to achieve accurate glioma segmentation on MR images. We have compared our results with a similar experiment conducted using the commonly utilized U-Net. Both experiments were performed on the BraTS2020 challenging dataset. For U-Net, network training was performed on the entire dataset, whereas a subset containing only 20% of the whole dataset was used for the SegCaps. To evaluate the results of our proposed method, the Dice Similarity Coefficient (DSC) was used. SegCaps and U-Net reached DSC of 87.96% and 85.56% on glioma tumor core segmentation, respectively. The SegCaps uses convolutional layers as the basic components and has the intrinsic capability to generalize novel viewpoints. The network learns the spatial relationship between features using dynamic routing of capsules. These capabilities of the capsule neural network have led to a 3% improvement in results of glioma segmentation with fewer data while it contains 95.4% fewer parameters than U-Net.

Aluminum depletion induced by co-segregation of carbon and boron in a bcc-iron grain boundary.

The local variation of grain boundary atomic structure and chemistry caused by segregation of impurities influences the macroscopic properties of polycrystalline materials. Here, the effect of co-segregation of carbon and boron on the depletion of aluminum at a Σ5 (3 1 0 )[0 0 1] tilt grain boundary in a α - Fe-4 at%Al bicrystal is studied by combining atomic resolution scanning transmission electron microscopy, atom probe tomography and density functional theory calculations. The atomic grain boundary structural units mostly resemble kite-type motifs and the structure appears disrupted by atomic scale defects. Atom probe tomography reveals that carbon and boron impurities are co-segregating to the grain boundary reaching levels of >1.5 at%, whereas aluminum is locally depleted by approx. 2 at.%. First-principles calculations indicate that carbon and boron exhibit the strongest segregation tendency and their repulsive interaction with aluminum promotes its depletion from the grain boundary. It is also predicted that substitutional segregation of boron atoms may contribute to local distortions of the kite-type structural units. These results suggest that the co-segregation and interaction of interstitial impurities with substitutional solutes strongly influences grain boundary composition and with this the properties of the interface.

Fuzzy fractional-order model of the novel coronavirus.

In this paper, a novel coronavirus infection system with a fuzzy fractional differential equation defined in Caputo's sense is developed. By using the fuzzy Laplace method coupled with Adomian decomposition transform, numerical results are obtained for better understanding of the dynamical structures of the physical behavior of COVID-19. Such behavior on the general properties of RNA in COVID-19 is also investigated for the governing model. The results demonstrate the efficiency of the proposed approach to address the uncertainty condition in the pandemic situation.

Evaluation of multi-wavelengths LED-based photoacoustic imaging for maximum safe resection of glioma: a proof of concept study.

PURPOSE: A real-time intra-operative imaging modality is required to update the navigation systems during neurosurgery, since precise localization and safe maximal resection of gliomas are of utmost clinical importance. Different intra-operative imaging modalities have been proposed to delineate the resection borders, each with advantages and disadvantages. This preliminary study was designed to simulate the photoacoustic imaging (PAI) to illustrate the brain tumor margin vessels for safe maximal resection of glioma. METHODS: In this study, light emitting diode (LED)-based PAI was selected because of its lower cost, compact size and ease of use. We developed a simulation framework based on multi-wavelength LED-based PAI to further facilitate PAI during neurosurgery. This framework considers a multilayer model of the tumoral and normal brain tissue. The simulation of the optical fluence and absorption map in tissue at different depths was computed by Monte Carlo. Then, the propagation of initial photoacoustic pressure was simulated by using k-wave toolbox. RESULTS: To evaluate the LED-based PAI, we used three evaluation criteria: signal-to-noise ratio (SNR), contrast ratio (CR) and full width of half maximum (FWHM). Results showed that by using proper wavelengths, the vessels were recovered with the same axial and lateral FWHM. Furthermore, by increasing the wavelength from 532 to 1064 nm, SNR and CR were increased in the deep region. The results showed that vessels with larger diameters at same wavelength have a higher CR with average improvement 28%. CONCLUSION: Multi-wavelength LED-based PAI provides detailed images of the blood vessels which are crucial for detection of the residual glioma: The longer wavelengths like 1064 nm can be used for the deeper tumor margins, and the shorter wavelengths like 532 nm for tumor margins closer to the surface. LED-based PAI may be considered as a promising intra-operative imaging modality to delineate tumor margins.

Asymptotic solutions of fractional interval differential equations with nonsingular kernel derivative.

Realizing the behavior of the solution in the asymptotic situations is essential for repetitive applications in the control theory and modeling of the real-world systems. This study discusses a robust and definitive attitude to find the interval approximate asymptotic solutions of fractional differential equations (FDEs) with the Atangana-Baleanu (A-B) derivative. In fact, such critical tasks require to observe precisely the behavior of the noninterval case at first. In this regard, we initially shed light on the noninterval cases and analyze the behavior of the approximate asymptotic solutions, and then, we introduce the A-B derivative for FDEs under interval arithmetic and develop a new and reliable approximation approach for fractional interval differential equations with the interval A-B derivative to get the interval approximate asymptotic solutions. We exploit Laplace transforms to get the asymptotic approximate solution based on the interval asymptotic A-B fractional derivatives under interval arithmetic. The techniques developed here provide essential tools for finding interval approximation asymptotic solutions under interval fractional derivatives with nonsingular Mittag-Leffler kernels. Two cases arising in the real-world systems are modeled under interval notion and given to interpret the behavior of the interval approximate asymptotic solutions under different conditions as well as to validate this new approach. This study highlights the importance of the asymptotic solutions for FDEs regardless of interval or noninterval parameters.

Co-Sparse Analysis Model Based Image Registration to Compensate Brain Shift by Using Intra-Operative Ultrasound Imaging.

Notwithstanding the widespread use of image guided neurosurgery systems in recent years, the accuracy of these systems is strongly limited by the intra-operative deformation of the brain tissue, the so-called brain shift. Intra-operative ultrasound (iUS) imaging as an effective solution to compensate complex brain shift phenomena update patients coordinate during surgery by registration of the intra-operative ultrasound and the pre-operative MRI data that is a challenging problem.In this work a non-rigid multimodal image registration technique based on co-sparse analysis model is proposed. This model captures the interdependency of two image modalities; MRI as an intensity image and iUS as a depth image. Based on this model, the transformation between the two modalities is minimized by using a bimodal pair of analysis operators which are learned by optimizing a joint co-sparsity function using a conjugate gradient.Experimental validation of our algorithm confirms that our registration approach outperforms several of other state-of-the-art registration methods quantitatively. The evaluation was performed using seven patient dataset with the mean registration error of only 1.83 mm. Our intensity-based co-sparse analysis model has improved the accuracy of non-rigid multimodal medical image registration by 15.37% compared to the curvelet based residual complexity as a powerful registration method, in a computational time compatible with clinical use.

Curvelet based residual complexity objective function for non-rigid registration of pre-operative MRI with intra-operative ultrasound images.

Intra-operative ultrasound as an imaging based method has been recognized as an effective solution to compensate non rigid brain shift problem in recent years. Measuring brain shift requires registration of the pre-operative MRI images with the intra-operative ultrasound images which is a challenging task. In this study a novel hybrid method based on the matching echogenic structures such as sulci and tumor boundary in MRI with ultrasound images is proposed. The matching echogenic structures are achieved by optimizing the Residual Complexity (RC) in the curvelet domain. At the first step, the probabilistic map of the MR image is achieved and the residual image as the difference between this probabilistic map and intra-operative ultrasound is obtained. Then curvelet transform as a sparse function is used to minimize the complexity of residual image. The proposed method is a compromise between feature-based and intensity-based approaches. Evaluation was performed using 14 patients data set and the mean of registration error reached to 1.87 mm. This hybrid method based on RC improves accuracy of nonrigid multimodal image registration by 12.5% in a computational time compatible with clinical use.

Planning screw insertion trajectory in lumbar spinal fusion using pre-operative CT images.

Spinal fusion permanently connects two or more vertebrae in spine to improve stability, correct a deformity or reduce pain by immobilizing the vertebrae through pedicle screw fixation. Pedicle screws should be inserted very carefully to prevent possible irrecoverable damages to the spinal cord. Surgeons use CT/fluoroscopic images to find how to insert the screws safely. However, there is still human error, as determining precise trajectory in 3D space is difficult because of asymmetric structure of pedicle. In this study we attempt to propose a shape based method to help the surgeons to find the more accurate and safe path for screw insertion that minimizes the risk or invasiveness of the surgery using pre-operative CT images. We extracted two features for insertion paths from CT images, named "safety margin" and "pedicular screw fixation strength". By using weighted k-means different paths were clustered and compared with each other. Results of comparison between those paths obtained from surgeon's pre-operative planning, intra operative and the proposed method proves a great improvement on the rate of success in reaching a suitable insertion trajectory by using our method. It is observed that the risk of damage in intra operative stage can be potentially high and it can be reduced considerably by using the proposed planning approach.

Brain-shift compensation by non-rigid registration of intra-operative ultrasound images with preoperative MR images based on residual complexity.

PURPOSE: Compensation for brain shift is often necessary for image-guided neurosurgery, requiring registration of intra-operative ultrasound (US) images with preoperative magnetic resonance images (MRI). A new image similarity measure based on residual complexity (RC) to overcome challenges of registration of intra-operative US and preoperative MR images was developed and tested. METHOD: A new two-stage method based on the matching echogenic structures such as sulci is achieved by optimizing the residual complexity value in the wavelet domain between the ultrasound image and the probabilistic map of the MR image. The proposed method is a compromise between feature-based and intensity-based approaches. Evaluation was performed using a specially designed brain phantom and an in vivo patient data set. RESULT: The results of the phantom data set registration confirmed that the proposed objective function outperforms the accuracy of adapted RC for multi-modal cases by 48 %. The mean fiducial registration error reached 1.17 and 2.14 mm when the method was applied on phantom and clinical data sets, respectively. CONCLUSION: This improved objective function based on RC in the wavelet domain enables accurate non-rigid multi-modal (US and MRI) image registration which is robust to noise. This technology is promising for compensation of intra-operative brain shift in neurosurgery.

Two-stage point-based registration method between ultrasound and CT imaging of the liver based on ICP and unscented Kalman filter: a phantom study.

PURPOSE: In recent years, image-guided liver surgery based on intraoperative ultrasound (US) imaging has become common. Using an efficient point-based registration method to improve both accuracy and computational time for the registration of predeformation computer tomography, liver images with postdeformation US images are important during surgical procedure. Although iterative closest point (ICP) algorithm is widely used in surface-based registration, its performance strongly depends on the presence of noise and initial alignment. A registration technique based on unscented Kalman filter (UKF), which has been proposed recently, can used to overcome the noise and outliers on an incremental basis; however, the technique is associated with computational complexity. METHODS: To overcome the limitations of ICP and UKF algorithms, we proposed an incremental two-stage registration method based on the combination of ICP and UKF algorithms to update the registration process with the acquired new points from US images. The registration is based on both the vessels and surface information of the liver. RESULTS: The two-stage method was examined using numerical simulations and phantom data sets. The results of the phantom data set confirmed that the two-stage method outperforms the accuracy of ICP by 23% and reduces the running time of UKF by 60%. CONCLUSION: The convergence rate, computational speed, and accuracy of the UKF algorithm can be improved using the two-stage method.

A hybrid method for non-rigid registration of intra-operative ultrasound images with pre-operative MR images.

In recent years intra-operative ultrasound images have been used for many procedures in neurosurgery. The registration of intra-operative ultrasound images with preoperative magnetic resonance images is still a challenging problem. In this study a new hybrid method based on residual complexity is proposed for this problem. A new two stages method based on the matching echogenic structures such as sulci is achieved by optimizing the residual complexity (RC) value with quantized coefficients between the ultrasound image and the probabilistic map of MR image. The proposed method is a compromise between feature-based and intensity-based approaches. The evaluation is performed on both a brain phantom and patient data set. The results of the phantom data set confirmed that the proposed method outperforms the accuracy of conventional RC by 39%. Also the mean of fiducial registration errors reached to 1.45, 1.94 mm when the method was applied on phantom and clinical data set, respectively. This hybrid method based on RC enables non-rigid multimodal image registration in a computational time compatible with clinical use as well as being accurate.

A shape based rotation invariant method for ultrasound-MR image registration: A phantom study.

In this work, a new shape based method to improve the accuracy of Brain Ultrasound-MRI image registration is proposed. The method is based on modified Shape Context (SC) descriptor in combination with CPD algorithm. An extensive experiment was carried out to evaluate the robustness of this method against different initialization conditions. As the results prove, the overall performance of the proposed algorithm outperforms both SC and CPD methods. In order to have control over the registration procedure, we simulated the deformations, missing points and outliers according to our Phantom MRI images.

Cardiac manifestations of subarachnoid hemorrhage.

INTRODUCTION: Cardiac manifestations of intracranial subarachnoid hemorrhage patients include mild electrocardiogram variability, reversible left ventricular dysfunction (Takotsubo), non-ST elevation myocardial infarction, ST-elevation myocardial infarction and cardiac arrest, but their clinical relevance is unclear. The aim of the present study was to categorize the relative frequency of different cardiac abnormalities in patients with subarachnoid hemorrhage and determine the influence of each abnormality on outcome.  METHODS: A retrospective review of 617 consecutive patients who presented with non-traumatic aneurysmal subarachnoid hemorrhage at our institution was performed. A cohort of 87 (14.1%) patients who required concomitantly cardiological evaluation was selected for subgroup univariate and multi-variable analysis of radiographic, clinical and cardiac data.  RESULTS: Cardiac complications included myocardial infarction arrhythmia and congestive heart failure in 47%, 63% and 31% of the patients respectively. The overall mortality of our cohort (23%) was similar to that of national inpatient databases. In our cohort a high World Federation of Neurosurgical Surgeons grading scale and a troponin level >1.0 mcg/L were associated with a 33 times and 10 times higher risk of death respectively. CONCLUSIONS: Among patients suffering from cardiac events at the time of aneurysmal subarachnoid hemorrhage, those with myocardial infarction and in particular those with a troponin level greater than 1.0 mcg/L had a 10 times increased risk of death. 

Evaluation of whole-body MR to CT deformable image registration.

Multimodality image registration plays a crucial role in various clinical and research applications. The aim of this study is to present an optimized MR to CT whole-body deformable image registration algorithm and its validation using clinical studies. A 3D intermodality registration technique based on B-spline transformation was performed using optimized parameters of the elastix package based on the Insight Toolkit (ITK) framework. Twenty-eight (17 male and 11 female) clinical studies were used in this work. The registration was evaluated using anatomical landmarks and segmented organs. In addition to 16 anatomical landmarks, three key organs (brain, lungs, and kidneys) and the entire body volume were segmented for evaluation. Several parameters--such as the Euclidean distance between anatomical landmarks, target overlap, Dice and Jaccard coefficients, false positives and false negatives, volume similarity, distance error, and Hausdorff distance--were calculated to quantify the quality of the registration algorithm. Dice coefficients for the majority of patients (> 75%) were in the 0.8-1 range for the whole body, brain, and lungs, which satisfies the criteria to achieve excellent alignment. On the other hand, for kidneys, Dice coefficients for volumes of 25% of the patients meet excellent volume agreement requirement, while the majority of patients satisfy good agreement criteria (> 0.6). For all patients, the distance error was in 0-10 mm range for all segmented organs. In summary, we optimized and evaluated the accuracy of an MR to CT deformable registration algorithm. The registered images constitute a useful 3D whole-body MR-CT atlas suitable for the development and evaluation of novel MR-guided attenuation correction procedures on hybrid PET-MR systems.

MRI-guided attenuation correction in whole-body PET/MR: assessment of the effect of bone attenuation.

OBJECTIVE: Hybrid PET/MRI presents many advantages in comparison with its counterpart PET/CT in terms of improved soft-tissue contrast, decrease in radiation exposure, and truly simultaneous and multi-parametric imaging capabilities. However, the lack of well-established methodology for MR-based attenuation correction is hampering further development and wider acceptance of this technology. We assess the impact of ignoring bone attenuation and using different tissue classes for generation of the attenuation map on the accuracy of attenuation correction of PET data. METHODS: This work was performed using simulation studies based on the XCAT phantom and clinical input data. For the latter, PET and CT images of patients were used as input for the analytic simulation model using realistic activity distributions where CT-based attenuation correction was utilized as reference for comparison. For both phantom and clinical studies, the reference attenuation map was classified into various numbers of tissue classes to produce three (air, soft tissue and lung), four (air, lungs, soft tissue and cortical bones) and five (air, lungs, soft tissue, cortical bones and spongeous bones) class attenuation maps. RESULTS: The phantom studies demonstrated that ignoring bone increases the relative error by up to 6.8% in the body and up to 31.0% for bony regions. Likewise, the simulated clinical studies showed that the mean relative error reached 15% for lesions located in the body and 30.7% for lesions located in bones, when neglecting bones. These results demonstrate an underestimation of about 30% of tracer uptake when neglecting bone, which in turn imposes substantial loss of quantitative accuracy for PET images produced by hybrid PET/MRI systems. CONCLUSION: Considering bones in the attenuation map will considerably improve the accuracy of MR-guided attenuation correction in hybrid PET/MR to enable quantitative PET imaging on hybrid PET/MR technologies.

Computer-aided mass detection on digitized mammograms using adaptive thresholding and fuzzy entropy.

In this paper, a segmentation method for detection of masses in digitized mammograms has been developed using two parallel approaches: adaptive thresholding method and fuzzy entropy feature as a CAD scheme. The algorithm consists of the following steps: a) Preprocessing of the digitized mammograms including identification of region of interest (ROI) as candidate for massive lesion through breast region extraction, b) Image enhancement using linear transformation and subtracting enhanced from the original image, c) Characterization of the ROI by extracting the fuzzy entropy feature, d) Local adaptive thresholding for segmentation of mass areas, e) Combine expert of the last two parallel approaches for mass detection. The proposed method was tested on 78 mammograms (30 normal & 48 cancerous) from the BIRADS and local databases. The detected regions validated by comparing them with the radiologists' hand-sketched boundaries of real masses. The current algorithm can achieve a sensitivity of 90.73% and specificity of 89.17%. This approach showed that the behavior of local adaptive thresholding and fuzzy entropy technique could be a useful method for mass detection on digitized mammograms. Our results suggest that the proposed method could help radiologists as a second reader in mammographic screening of masses.

Modified fast marching tractography algorithm and its ability to detect fibre crossing.

White matter fibre tractography is a non-invasive method for reconstructing three dimensional trajectories of fibre pathways. Fast Marching is one of fibre tracking methods in which co-linearity of principal eigenvectors determines the speed of front's evolution. In this algorithm effect of tensor's eigenvalues are not considered. In the current work, the speed function of standard fast marching was modified by considering the strength of tensor's eigenvectors. The proposed speed function has an adaptive Fractional Anisotropy (FA) weighted factor which can be set by type of brain's environments (i.e. isotropic and anisotropic regions). This modification was found to have high accuracy for detecting fibres by reducing false pathways. The proposed method has performed high accuracy in detection of fibre crossing.

Morphological heart arrhythmia classification using Hermitian model of higher-order statistics.

This paper presents the results of morphological heart arrhythmia detection based on parameters which are obtained from modeling of the cumulants of the electrocardiography, ECG, signals. Cumulants possess many properties that make them effective tools to describe morphological variations of non-stationary signals. Among these properties, the two most attractive founded for analysis of ECG arrhythmia detections are the ability of suppressing morphological variations of different beats of ECG signals belonging to a specific class of heart arrhythmia and reducing the effect of Gaussian noise on the classification significantly. The proposed method combines these properties in conjunction with Hermitian model to perform an efficient classification method for five different heart arrhythmias. We achieved the sensitivity of 98.59% and specificity of 99.67% which are comparable to previous works. This novel combination has made the classification method much more accurate in discriminating different morphological based heart arrhythmias as well as making a good degree of robustness to remove additive Gaussian noises from ECG signals.