Understanding dynamic functional connectivity is pivotal in unraveling the intricate dynamics of neural activity. This research leverages Magnetoencephalography (MEG) and Instantaneous Amplitude Correlation (IAC) to explore the evolving patterns of dynamic functional connectivity in the human brain. The study meticulously compares IAC outcomes during resting state and task-based MEG, offering insights into the adaptability of brain connectivity. A comprehensive literature review contextualizes the study within existing research, highlighting the relevance of dynamic functional connectivity analysis. The MEG data preprocessing employs advanced techniques, including artifact reduction and source estimation. The IAC analysis, featuring tensor factorization and k-means clustering, reveals distinctive connectivity patterns in various frequency bands. Results demonstrate pronounced transitions between connectivity states, particularly in the beta frequency bands during resting state MEG. This comparative analysis enriches our understanding of neural dynamics and connectivity fluctuations, paving the way for potential clinical applications. The study underscores the need for broader validation through expanded datasets, emphasizing the implications for cognitive neuroscience and clinical practices.

To localize the unusual cardiac activities non-invasively, one has to build a prior forward model that relates the heart, torso, and detectors. This model has to be constructed to mathematically relate the geometrical and functional activities of the heart. Several methods are available to model the prior sources in the forward problem, which results in the lead field matrix generation. In the conventional technique, the lead field assumed the fixed prior sources, and the source vector orientations were presumed to be parallel to the detector plane with the unit strength in all directions. However, the anomalies cannot always be expected to occur in the same location and orientation, leading to misinterpretation and misdiagnosis. To overcome this, the work proposes a new forward model constructed using the VCG signals of the same subject. Furthermore, three transformation methods were used to extract VCG in constructing the time-varying lead fields to steer to the orientation of the source rather than just reconstructing its activities in the inverse problem. In addition, the unit VCG loop of the acute ischemia patient was extracted to observe the changes compared to the normal subject. The abnormality condition was achieved by delaying the depolarization time by 15ms. The results involving the unit vectors of VCG demonstrated the anisotropic nature of cardiac source orientations, providing information about the heart's electrical activity.

A non-invasive technique, magnetocardiography measures the weak magnetic fields generated by the heart’s electrical currents. This non-contact method, employing SQUIDs in a shielded environment, is highly expensive and sophisticated. At the same time, in non-shielded scenarios, it results in heavy, bulky, and cumbersome. As a development in cardiac magnetic field detection, a tiny array of coils has been used to passively monitor the heart’s magnetic field in an unshielded environment. This paper focuses on illustrating the forward problem of magnetocardiography through the miniature multi-coil practical experiment. The copper coils presumed to be cardiac sources were provided with normal and abnormal ventricular transmembrane potentials generated using Maeda’s cardiac cell model. The study’s primary goal is to demonstrate the practical experimental setup in an unshielded environment to detect the cardiac magnetic fields. The results indicated the presence of both normal and abnormal transmembrane potential signal components, which could be further utilized in reconstructing the electrical activity in the inverse problem of the heart.

Temporal Lobe Epilepsy (TLE) is a prevalent neurological disorder affecting millions worldwide, including a significant proportion in India. Precise diagnosis and effective treatment planning are critical for TLE patients, necessitating advanced neuroimaging techniques. Magnetoencephalography (MEG) offers a non-invasive method for evaluating brain function, providing detailed insights into TLE. In this study, we aim to evaluate the potential of functional connectivity metrics derived from MEG data at the source level for distinguishing TLE patients from healthy controls (HCs). We analyse the data across various brain frequency bands, including alpha, beta, delta, gamma, theta, broadband, and high-frequency oscillations (HFO), using amplitude envelope correlation and graph theory metrics. We employ machine learning algorithms to classify TLE and HC groups based on these metrics. Chi2 feature importance analysis reveals significant importance of connectivity metrics such as local efficiency, mean clustering coefficient, mean shortest path length, small worldness score, weighted degree centrality, binary degree centrality, global efficiency across frequency bands, particularly in theta, alpha, beta, broadband and HFO bands. Various machine learning models demonstrate high classification performance, with accuracies reaching up to 100% in particular frequency bands in agreement with the Chi2 feature importance analysis. Overall, the Subspace Discriminant Ensemble model, especially in the Theta and Alpha frequency bands, show exceptional potential for classifying TLE and HCs. Overall, this study underscores the potential of MEG and functional connectivity analysis using specific frequency bands and machine learning models for classifying TLE and HC with high accuracy, which may contribute to improved diagnosis and management of epilepsy.

The significance of fiducial marker detection in neuroimaging cannot be overstated, as these markers serve as vital reference points for accurate spatial alignment during image registration. Our proposed model addresses challenges in consistent marker placement and variability during MRI scanning, ensuring reliable localization for subsequent analysis. This paper introduces an innovative approach to fiducial marker detection in T1-weighted MRI volumes, specifically targeting the Left Preauricular Point (LPA), Right Pre-auricular Point (RPA), and Nasion. The implementation employs a 3D Convolutional Neural Network (CNN) to achieve precise localization of these crucial anatomical landmarks. Operating on a high-performance system our algorithm demonstrated exceptional accuracy and sensitivity using MATLAB R2023a as the primary tool for development and evaluation. Rigorous experiments on a diverse dataset showcased the algorithm’s robust performance. For RPA detection, the model achieved 96.55% accuracy, emphasizing sensitivity (96.78% recall) and precision (96.35%). LPA detection demonstrated an impressive accuracy of 96.88%, with heightened sensitivity (96.95%) and precision (96.83%). The nasion detection process exhibited precise localization, with a Mean Square Error (MSE) of 0.3439 for 36 volume data. These results highlight the algorithm’s potential to enhance accuracy and efficiency in fiducial point detection for improved neuroimaging studies.

Purpose The reliable estimation of the vertebral body posture helps to aid a safe and effective spine surgery. The proposed work aims to present an MR to X-ray image registration to assess the 3D pose of the vertebral body during spine surgery. The 3D assessment of vertebral pose assists in analyzing the position and orientation of the vertebral body to provide information during various clinical diagnosis conditions such as curvature estimation and pedicle screw insertion surgery. Methods The proposed feature-based registration framework extracted vertebral end plates to avoid the mismatch between the intensities of MR and X-ray images. Using the projection matrix, the segmented MRI is forward projected and then registered to the X-ray image using binary image matching similarity and the CMA-ES optimizer. Results The proposed method estimated the vertebral pose by registering the simulated X-ray onto pre-operative MRI. To evaluate the efficacy of the proposed approach, a certain number of experiments are carried out on the simulated dataset. Conclusion The proposed method is a fast and accurate registration method that can provide 3D information about the vertebral body. This 3D information is useful to improve accuracy during various clinical diagnoses.

One of the most common causes of death globally in the past few years is cardiac arrhythmia (irregular heartbeat), which occurs when the electric signals that coordinate the heartbeat don't work appropriately. As a result, there is a need to focus on understanding the basic mechanisms of heart rhythm variations. This paper focuses on cardiac excitation and uses a model replicating the electrical behavior of heart cells to generate an action potential. The activation times of the selected sources on the heart's surface from ECGSIM were compared with those generated using an electronic circuit model. The findings indicated a good match between the simulation results with a minimal error rate of milliseconds. The computational modeling of the electrical model of the cardiac cell was performed to explore the effect of the space or length constant (λ), which measures how well a potential spreads along the heart cell as a function of distance.

Pedicle screw placement for vertebral fixation is a complicated surgery for orthopaedic surgeons. The main challenge is to estimate the accurate trajectory's position to minimize post-operative complications related to pedicle screw placement. Different types of 3D to 2D registration techniques have been employed to avoid the misplacement of the screw during the surgery. However, these techniques cannot be applied directly to MR to X-ray registration due to differences in image intensity and tissue non-correspondence. To overcome these limitations, feature-based 3D to 2D registration technique was developed to map a trajectory position in the intra-operative X-ray image on to the pre-operative MR image. The registration framework validated by generating projection images that perfectly matched simulated X-ray images, then back-projecting the trajectory position on the pre-operative MR image using the estimated transformation parameters. The accuracy of the registered trajectory evaluated by measuring the displacement and directional errors between the registered and planned trajectory. The proposed method successfully registered the trajectory position in the simulated X-ray to pre-operative MR to estimate the trajectory position. A number of experiments are performed on the simulated dataset to assess the effectiveness of the proposed method. The Euclidean distance between the entry and end points and the directional error of the registered trajectory from the planned trajectory were below 1mm in AP, Lateral, and a combination of both planes. The mean trajectory length difference between the planned and registered trajectory was less than 1mm.

Accurate sleep stage detection is crucial for diagnosing sleep disorders and tailoring treatment plans. Polysomnography (PSG) is considered the gold standard for sleep assessment since it captures a diverse set of physiological signals. While various studies have employed complex neural networks for sleep staging using PSG, our research emphasises the efficacy of a simpler and more efficient architecture. We aimed to integrate a diverse set of feature extraction measures with straightforward machine learning, potentially offering a more efficient avenue for sleep staging. We also aimed to conduct a comprehensive comparative analysis of feature extraction measures, including the power spectral density, Higuchi fractal dimension, singular value decomposition entropy, permutation entropy, and detrended fluctuation analysis, coupled with several machine-learning models, including XGBoost, Extra Trees, Random Forest, and LightGBM. Furthermore, data augmentation methods like the Synthetic Minority Oversampling Technique were also employed to rectify the inherent class imbalance in sleep data. The subsequent results highlighted that the XGBoost classifier, when used with a combination of all feature extraction measures as an ensemble, achieved the highest performance, with accuracies of 87%, 90%, 93%, 96%, and 97% and average F1-scores of 84.6%, 89%, 90.33%, 93.5%, and 93.5% for distinguishing between five-stage, four-stage, three-stage, and two distinct two-stage sleep configurations, respectively. This combined feature extraction technique represents a novel addition to the body of research since it achieves higher performance than many recently developed deep neural networks by utilising simpler machine-learning models.

In this paper, an attempt is made to simulate and compare spatio-temporal VCG and VMCG derived from epicardial potentials. Electric (EHV) and Magnetic heart vectors (MHV) are computed from the ECG and MCG at various time instants and their orientations with respect to time are found to show a reasonable tilt of 90 to 100 degrees. The complimentary information with reference to the orientation of cardiac vector offered by MHV could be attributed to its sensitivity to intracellular myocardial currents, while EHV exhibits the orientation associated with only the extracellular currents owing to volume conduction. By comparing the orientations of EHV and MHV generated from a simulated equivalent current dipole model, the present work demonstrates the usefulness of these spatiotemporal vectors in tracing the cardiac current flow inside the thorax for a healthy heart. It could be thus expected that clinically relevant information could be obtained if the present analysis is extended to highly complex and irregular cardiac activation sequences that could be seen in arrhythmia and myocardial infarction. The main contribution of this paper is to mathematically model and derive the magnetic heart vectors from the MCG system extracted from IGCAR lab and verify it with the conventional VCG extraction..

The 3D to 2D registration technique in spine surgery is vital to aid surgeons in avoiding the wrong site surgery by estimating the vertebral pose. The vertebral poses are estimated by generating the spatial correspondence relationship between pre-operative MR with intra-operative x-ray images, then evaluated using a similarity measure. Different similarity measures are used in 3D to 2D registration techniques to assess the spatial correspondence between the pre-operative and intra-operative images. However, to evaluate the registration performance of the similarity measures, the proposed framework employs three different similarity measures: Binary Image Matching, Dice Coefficients, and Normalized Cross-correlation technique to compare the images based on pixel positions. The registration accuracy of the proposed similarity measures is compared based on the mean Target Registration Error, mean Iteration Times, and success rate. In the absence of simulated test images, the experiment is conducted on the simulated AP and Lateral test images. The experiment conducted on the simulated test images shows that all three similarity measures work well for the feature based 3D to 2D registration in that BIM gives better results. The experiment also indicates high registration accuracy when the initial displacements are varied up to ±20 mm and ±100of the translational and rotational parameters, respectively, for three similarity measures.

The vertebral pose estimation helps to assist the clinician during the surgery to avoid the wrong site surgery. The vertebral poses are estimated by establishing the spatial correspondence relationship between the pre-operative MR image and intra-operative X-ray, and then assessed by a similarity measure. Many similarity measure techniques such as mutual Information, normalized cross-correlation, etc., were used in 3D to 2D registration techniques. So the proposed framework employs three different similarity measures: Binary Image Matching, Dice Coefficients, and Normalized Cross-correlation technique to compare the images based on pixel positions to evaluate the registration performance. In the absence of Intra-operative X-ray images, the experiment is conducted on the simulated test images. Registration accuracy is estimated based on the mean Target Registration Error. The results demonstrated that the three similarity measures work well for feature-based 3D to 2D registration in that the Dice coefficient gives the best result.

The vertebral pose is accurately estimated by registering the pre-operative MRI with the intra-operative x-ray during the surgery. The registration task becomes considerably more challenging for multimodal images due to differences in image pixel intensities. The registration algorithm fails when there is a large initial displacement between the images. This paper proposes a feature-based 3D to 2D registration to accurately align pre-operative MRI with intra-operative X-ray with large displacement. The experiment was conducted on the simulated images by varying the initial displacements. The results demonstrate that the proposed method can increase the starting displacement upto a range of ±20mm and ±10° displacements in all translation and rotation parameters, respectively, by providing a high accuracy.

Epilepsy is the most common neurological disorder that has affected 50 million worldwide population. Epilepsy is a chronic condition that is characterized as recurrent and unprovoked seizures. A seizure is defined as abnormal, excessive paroxysmal discharge of the cerebral neurons. In general, epilepsy evaluation, the high time resolution (similar to 1-2 ms) electrophysiological data recorded using electroencephalography (EEG) is commonly used. The EEG data are visually inspected for epileptic seizure instances. However, the manual interpretationmay lead to subjective error-causing misdiagnosis, and identifying the seizure instances in high temporal resolution data may be time-consuming. To mitigate these problems, the proposed study uses a hand-crafted deep learning model to classify the epileptic and nonepileptic EEG data. This study used EEG data acquired from two databases-University of Bonn and Physiobank Children's Hospital Boston-Massachusetts Institute of Technology (CHB-MIT). We split the EEG data in 80:20 ratio for training and testing the model. The model was trained under three network specifications, which were designed based on the number of high-level features and low-level features. The result showed that the proposed study successfully classified epileptic and non-epileptic signals with the accuracy of 67% and 92% for University of Bonn data and CHB-MIT EEG data, respectively, for the network specification which had a high number of low-level features. We tested the model for optimal value of number of epochs (20) and learning rate (0.001). The study shows that the MIT-CHB data are suitable for classification as they have a good number of samples and balanced epileptic and non-epileptic signals.

In this paper, the inverse problems of cardiac sources using analytical and probabilistic methods are solved and discussed. The standard Tikhonov regularization technique is solved initially to estimate the under-determined heart surface potentials from Magnetocardiographic (MCG) signals. The results of the deterministic method subjected to noise in the measurements are discussed and compared with the probabilistic models. Hierarchical Bayesian modeling with fixed Gaussian prior is employed to quantify the uncertainties in source reconstructions. A novel application of Variational Bayesian inference approach has been presented to estimate the heart sources. The reconstruction results of Variational Bayesian model with non-stationary priors are compared with solutions of simplistic Bayesian approach; and the performances are evaluated using Root Mean Square Error (RMSE) and correlation co-efficient metrics. The Bayesian solutions in the study are also extended to localize the MCG sources for two types of Myocardial infarction cases.

Spine surgeries are vulnerable to wrong-level surgeries and postoperative complications because of their complex structure. Unavailability of the 3D intraoperative imaging device, low-contrast intraoperative X-ray images, variable clinical and patient conditions, manual analyses, lack of skilled technicians, and human errors increase the chances of wrong-site or wrong-level surgeries. State of the art work refers 3D-2D image registration systems and other medical image processing techniques to address the complications associated with spine surgeries. Intensity-based 3D-2D image registration systems had been widely practiced across various clinical applications. However, these frameworks are limited to specific clinical conditions such as anatomy, dimension of image correspondence, and imaging modalities. Moreover, there are certain prerequisites for these frameworks to function in clinical application, such as dataset requirement, speed of computation, requirement of high-end system configuration, limited capture range, and multiple local maxima. A simple and effective registration framework was designed with a study objective of vertebral level identification and its pose estimation from intraoperative fluoroscopic images by combining intensity-based and iterative control point (ICP)-based 3D-2D registration. A hierarchical multi-stage registration framework was designed that comprises coarse and finer registration. The coarse registration was performed in two stages, i.e., intensity similarity-based spatial localization and source-to-detector localization based on the intervertebral distance correspondence between vertebral centroids in projected and intraoperative X-ray images. Finally, to speed up target localization in the intraoperative application, based on 3D-2D vertebral centroid correspondence, a rigid ICP-based finer registration was performed. The mean projection distance error (mPDE) measurement and visual similarity between projection image at finer registration point and intraoperative X-ray image and surgeons' feedback were held accountable for the quality assurance of the designed registration framework. The average mPDE after peak signal to noise ratio (PSNR)-based coarse registration was 20.41mm. After the coarse registration in spatial region and source to detector direction, the average mPDE reduced to 12.18mm. On finer ICP-based registration, the mean mPDE was finally reduced to 0.36 mm. The approximate mean time required for the coarse registration, finer registration, and DRR image generation at the final registration point were 10 s, 15 s, and 1.5 min, respectively. The designed registration framework can act as a supporting tool for vertebral level localization and its pose estimation in an intraoperative environment. The framework was designed with the future perspective of intraoperative target localization and its pose estimation irrespective of the target anatomy.

Pedicle screw insertion is considered a complex surgery among Orthopaedics surgeons. Exclusively to prevent postoperative complications associated with pedicle screw insertion, various types of image intensity registration-based navigation systems have been developed. These systems are computation-intensive, have a small capture range and have local maxima issues. On the other hand, deep learning-based techniques lack registration generalizability and have data dependency. To overcome these limitations, a patient-specific hybrid 3D-2D registration principled framework was designed to map a pedicle screw trajectory between intraoperative X-ray image and preoperative CT image. An anatomical landmark-based 3D-2D Iterative Control Point (ICP) registration was performed to register a pedicular marker pose between the X-ray images and axial preoperative CT images. The registration framework was clinically validated by generating projection images possessing an optimal match with intraoperative X-ray images at the corresponding control point registration. The effectiveness of the registered trajectory was evaluated in terms of displacement and directional errors after reprojecting its position on 2D radiographic planes. The mean Euclidean distances for the Head and Tail end of the reprojected trajectory from the actual trajectory in the AP and lateral planes were shown to be 0.6–0.8 mm and 0.5–1.6 mm, respectively. Similarly, the corresponding mean directional errors were found to be 4.90 and 20. The mean trajectory length difference between the actual and registered trajectory was shown to be 2.67 mm. The approximate time required in the intraoperative environment to axially map the marker position for a single vertebra was found to be 3 min. Utilizing the markerless registration techniques, the designed framework functions like a screw navigation tool, and assures the quality of surgery being performed by limiting the need of postoperative CT.

Speech recognition system extract the textual data from the speech signal. The research in speech recognition domain is challenging due to the large variabilities involved with the speech signal. Variety of signal processing and machine learning techniques have been explored to achieve better recognition accuracy. Speech is highly non-stationary in nature and therefore analysis is carried out by considering short time-domain window or frame. In the speech recognition task, cepstral (Mel frequency cepstral coefficients (MFCC)) features are commonly used and are extracted for short time-frame. The effectiveness of features depend upon duration of the time-window chosen. The present study is aimed at investigation of optimal time-window duration for extraction of cepstral features in the context of speech recognition task. A speaker independent speech recognition system for the Kannada language has been considered for the analysis. In the current work, speech utterances of Kannada news corpus recorded from different speakers have been used to create speech database. The hidden Markov tool kit (HTK) has been used to implement the speech recognition system. The MFCC along with their first and second derivative coefficients are considered as feature vectors. Pronunciation dictionary required for the study has been built manually for mono-phone system. Experiments have been carried out and results have been analyzed for different time-window lengths. The overlapping Hamming window has been considered in this study. The best average word recognition accuracy of 61.58% has been obtained for a window length of 110 msec duration. This recognition accuracy is comparable with the similar work found in literature. The experiments have shown that best word recognition performance can be achieved by tuning the window length to its optimum value.

Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI

One of the most complex joints in the human body is the temporomandibular joint (TMJ), which connects the mandible and the skull's temporal bone. The two main structures of TMJ are mandibular condyles and the articular disc. Around 28% of the population is affected by TMJ dysfunction. The leading cause of TMJ dysfunction is due to internal derangement of the condyle and disc. In current scenarios, magnetic resonance imaging (MRI) is an imaging technique used in diagnosing TMJ dysfunction. The clinician must visually investigate the derangement of condyle with a disc which can lead to subjective error. This study focuses on segmenting the TMJ condyle using two image processing techniques like marker-controlled watershed segmentation and Random walks. These techniques segment the TMJ from MR images in sagittal orientation, even when the MR images are corrupted due to noise.