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.

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.

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.

A flexible approach for simulating physiological signals.

Generating synthetic physiological signals using information extracted from real world physiological signals plays an important role in the field of medical device development and education. Most of the existing approaches are limited in the sense that they either focus on a particular physiological signal or lack flexibility in generating signals that mimic real world scenarios. In this paper, we present a cubic B-Spline interpolator-based flexible signal generator intended for simulating a variety of physiological signals. A simulated artifact generator (SAG) is also included in the proposed scheme to add artifacts to the physiological signals mimicking signal deviations associated with real world scenarios. In addition, the proposed method offers the ability to easily present a parametric representation to model a case-specific physiological signal. To demonstrate the ability of the proposed method, case studies on electromyogram (EMG), electro-oculogram (EOG), and electrocardiogram (ECG) during ventricular fibrillation are presented. Using a database of 20 ECG signals, the proposed approach was compared with an existing-model-based method and the results confirm the flexibility of our proposed approach as well as higher signal reproduction accuracy (a mean root mean square error improvement of 47.9% for waveform-based modeling and 4.3% for parametric-based modeling).

Wavelets and fuzzy relational classifiers: a novel diffusion-weighted image analysis system for pediatric metabolic brain diseases.

The diffusion-weighted imaging (DWI) technique can be utilized to investigate a variety of diseases. We propose an automated pilot system, which assists in the diagnosis of metabolic brain diseases, utilizing the DWI. In this study, DWI images are preprocessed and exponential apparent diffusion coefficient (eADC) images are produced. The eADC images are later brain extracted and normalized to a standard brain template. Subsequently, we utilized wavelets to denoise the eADC images. The images are rectified, thresholded and now conspicuous abnormal regions are subsequently identified utilizing different brain atlases. Abnormal regions constitute the features that will be used by a fuzzy relational classifier in order to categorize the diseases. A sensitivity and specificity of 60% and 93.33%, respectively, in detecting metabolic brain diseases have been achieved.

PCA-SGA implementation in classification and disease specific feature extraction of the brain MRS signals.

The medical diagnostic systems often suffer from the high dimensional data. In this study, Principle Component Analysis (PCA) has been used for dimensionality reduction of the brain Magnetic Resonance Spectroscopy (MRS) signals. Afterwards, the Simple Genetic Algorithms (SGA) is utilized in order to classify different brain diseases. SGA is later used to extract MRS signal features in case of metabolic brain diseases (MD). The PCA-SGA implementation received the specificity of 89.91%. The SGA was able to achieve the sensitivity of 84.84% and positive predictivity of 88.46% in extracting disease specific MRS signal features.