Search

Abstract Background MRI is critical for diagnosing lumbar spine disorders but its complexity challenges diagnostic accuracy. This study proposes a BERT-based large language model (LLM) to enhance precision in classifying lumbar spine disorders through the integration of MRI data, textual reports, and numerical measurements. Methods The segmentation quality of MRI data is evaluated using dice coefficients (cut-off: 0.92) and intersection over union (IoU) metrics (cut-off: 0.88) to ensure precise anatomical feature extraction. The CNN extracts key lumbar spine features, such as lumbar lordotic angle (LLA) and disc heights, which are tokenized as direct scalar values representing positional relationships. A data source of 28,065 patients with various disorders, including degenerative disc disease, spinal stenosis, and spondylolisthesis, is used to establish diagnostic standards. These standards are refined through post-CNN processing of MRI texture features. The BERT-based spinal LLM model integrates these CNN-extracted MRI features and numerical values through early fusion layers. Results Segmentation analysis illustrate various lumbar spine disorders and their anatomical changes. The model achieved high performance, with all key metrics nearing 0.9, demonstrating its effectiveness in classifying conditions like spondylolisthesis, herniated disc, and spinal stenosis. External validation further confirmed the model’s generalizability across different populations. External validation on 514 expert-validated MRI cases further confirms the model’s clinical relevance and generalizability. The BERT-based model classifies 61 combinations of lumbar spine disorders. Conclusions The BERT-based spinal LLM significantly improves the precision of lumbar spine disorder classification, supporting accurate diagnosis and treatment planning.

Background: MRI is critical for diagnosing lumbar spine disorders but its complexity challenges diagnostic accuracy. This study proposes a BERT-based large language model (LLM) to enhance precision in classifying lumbar spine disorders through the integration of MRI data, textual reports, and numerical measurements. Methods: The segmentation quality of MRI data is evaluated using dice coefficients (cut-off: 0.92) and intersection over union (IoU) metrics (cut-off: 0.88) to ensure precise anatomical feature extraction. The CNN extracts key lumbar spine features, such as lumbar lordotic angle (LLA) and disc heights, which are tokenized as direct scalar values representing positional relationships. A data source of 28,065 patients with various disorders, including degenerative disc disease, spinal stenosis, and spondylolisthesis, is used to establish diagnostic standards. These standards are refined through post-CNN processing of MRI texture features. The BERT-based spinal LLM model integrates these CNN-extracted MRI features and numerical values through early fusion layers. Results: Segmentation analysis illustrate various lumbar spine disorders and their anatomical changes. The model achieved high performance, with all key metrics nearing 0.9, demonstrating its effectiveness in classifying conditions like spondylolisthesis, herniated disc, and spinal stenosis. External validation further confirmed the model's generalizability across different populations. External validation on 514 expert-validated MRI cases further confirms the model's clinical relevance and generalizability. The BERT-based model classifies 61 combinations of lumbar spine disorders. Conclusions: The BERT-based spinal LLM significantly improves the precision of lumbar spine disorder classification, supporting accurate diagnosis and treatment planning. [ABSTRACT FROM AUTHOR]

This research assessed advancements in brain tumour classification using convolutional neural networks (CNNs) and MRI data. An analysis of 37 studies highlighted the effectiveness of CNN architectures and pre-processing methods in accurately categorising brain tumours. Issues such as class disparities and model interpretability were identified, prompting recommendations for advanced deep learning techniques, ensemble methods, and diverse datasets to enhance diagnostic accuracy. The findings underscored the importance of these methods in achieving high accuracy, with a maximum rate of 98.80% from 154 MRI images. This systematic study also included a meta-analysis from 2018 to 2022, revealing patterns in MRI cases across demographics and providing insights into healthcare trends. [ABSTRACT FROM AUTHOR]

Advanced brain cancer is the deadliest type with just a few months survival rate. Existing technologies hinder the objective of forecasting cancer. This work aims to fulfil the pressing requirement for timely and precise identification of advanced-stage brain tumours, which are notorious for their markedly reduced life expectancy. It presents an innovative hybrid approach for predicting brain tumours and improves diagnostic capabilities. The Multiple Kernel K-Means Cluster Algorithm (MKKCA) is used to segment brain MRI images effectively, differentiating healthy and tumorous tissues. After segmentation, a hybrid approach with 3D-Convolutional Neural Network (CNN) and U-Net has been utilized for classification. The objective is to effectively and accurately distinguish normal and pathological brain images. To enhance the efficiency, we include the Improved Whale Optimization Algorithm (IWOA), which guarantees accurate and dependable performance via location updates. The methodology demonstrates outstanding precision with 98.5% accuracy rate, 98.56% specificity, 91% sensitivity, 87.45% precision and a recall rate of 96% with the F-Measure at 96.02%. These findings, obtained using MATLAB, demonstrate a substantial performance improvement compared to current approaches. This development not only represents a significant addition to diagnostic imaging but also a crucial role in the prediction and treatment of brain cancers. [ABSTRACT FROM AUTHOR]

Magnetoelectric (ME) magnetic field sensors are novel sensing devices of great interest in the field of biomagnetic measurements. We investigate the influence of magnetic crosstalk and the linearity of the response of ME sensors in different array and excitation configurations. To achieve this aim, we introduce a combined multiscale 3D finite-element method (FEM) model consisting of an array of 15 ME sensors and an MRI-based human head model with three approximated compartments of biological tissues for skin, skull, and white matter. A linearized material model at the small-signal working point is assumed. We apply homogeneous magnetic fields and perform inhomogeneous magnetic field excitation for the ME sensors by placing an electric point dipole source inside the head. Our findings indicate significant magnetic crosstalk between adjacent sensors leading down to a 15.6% lower magnetic response at a close distance of 5 mm and an increasing sensor response with diminishing crosstalk effects at increasing distances up to 5 cm. The outermost sensors in the array exhibit significantly less crosstalk than the sensors located in the center of the array, and the vertically adjacent sensors exhibit a stronger crosstalk effect than the horizontally adjacent ones. Furthermore, we calculate the ratio between the electric and magnetic sensor responses as the sensitivity value and find near-constant sensitivities for each sensor, confirming a linear relationship despite magnetic crosstalk and the potential to simulate excitation sources and sensor responses independently. [ABSTRACT FROM AUTHOR]

Cervical malignant growth is the fourth most typical reason for disease demise in women around the world. In developing countries, women don’t approach sufficient screening methods because of the costly procedures to undergo examination regularly, scarce awareness and lack of access to the medical centre. Recently, deep learning-based radiomic methods have been introduced in differentiating vessel invasion from non-vessel invasion in Cervical Cancer (CC) by multi-parametric Magnetic Resonance Imaging (MRI). However, this model doesn’t produce sufficient results. In this work, the MRI images are initially pre-processed using bilateral filtering. After pre-processing, the image is segmented by modified U-Net model in order to identify the cancerous region. Extraction of deep semantic information from images by using residual blocks in the processes of contractions and expansions. The last layer of the contracting route uses tightly coupled convolutions in the second phase to speed up feature recycling and feature propagation. It was inferred from the observations that the proposed model was effective as a predictive tool for detecting vessel invasions in preoperative early stages of CC. Proposed model produces 94.00% detection accuracy which is better than the other existing methods.

Cervical malignant growth is the fourth most typical reason for disease demise in women around the world. In developing countries, women don't approach sufficient screening methods because of the costly procedures to undergo examination regularly, scarce awareness and lack of access to the medical centre. Recently, deep learning-based radiomic methods have been introduced in differentiating vessel invasion from non-vessel invasion in Cervical Cancer (CC) by multi-parametric Magnetic Resonance Imaging (MRI). However, this model doesn't produce sufficient results. In this work, the MRI images are initially pre-processed using bilateral filtering. After pre-processing, the image is segmented by modified U-Net model in order to identify the cancerous region. Extraction of deep semantic information from images by using residual blocks in the processes of contractions and expansions. The last layer of the contracting route uses tightly coupled convolutions in the second phase to speed up feature recycling and feature propagation. It was inferred from the observations that the proposed model was effective as a predictive tool for detecting vessel invasions in preoperative early stages of CC. Proposed model produces 94.00% detection accuracy which is better than the other existing methods. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a neurodegenerative disorder characterized by cognitive impairment and aberrant protein deposition in the brain. Therefore, the early detection of AD is crucial for the development of effective treatments and interventions, as the disease is more responsive to treatment in its early stages. It is worth mentioning that deep learning techniques have been successfully applied in recent years to a wide range of medical imaging tasks, including the detection of AD. These techniques have the ability to automatically learn and extract features from large datasets, making them well suited for the analysis of complex medical images. In this paper, we propose an improved lightweight deep learning model for the accurate detection of AD from magnetic resonance imaging (MRI) images. Our proposed model achieves high detection performance without the need for deeper layers and eliminates the use of traditional methods such as feature extraction and classification by combining them all into one stage. Furthermore, our proposed method consists of only seven layers, making the system less complex than other previous deep models and less time-consuming to process. We evaluate our proposed model using a publicly available Kaggle dataset, which contains a large number of records in a small dataset size of only 36 Megabytes. Our model achieved an overall accuracy of 99.22% for binary classification and 95.93% for multi-classification tasks, which outperformed other previous models. Our study is the first to combine all methods used in the publicly available Kaggle dataset for AD detection, enabling researchers to work on a dataset with new challenges. Our findings show the effectiveness of our lightweight deep learning framework to achieve high accuracy in the classification of AD. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) can be diagnosed by utilizing traditional logistic regression models to fit magnetic resonance imaging (MRI) data of brain, which is regarded as a vector of covariates. But its parameter estimation is inefficient and computationally extensive due to ultrahigh dimensionality and complicated structure of MRI data. To overcome this deficiency, this paper proposes a tensor logistic regression model (TLRM) for AD's MRI data by regarding MRI tensor as covariates. Under this framework, a tensor candecomp/parafac (CP) decomposition tool is employed to reduce ultrahigh dimensional tensor to a high dimensional level, a novel Bayesian adaptive Lasso method is developed to simultaneously select important components of tensor and estimate model parameters by incorporating the P o ´ lya-Gamma method leading a closed-form likelihood and avoiding the usage of the Metropolis-Hastings algorithm, and Gibbs sampler technique in Markov chain Monte Carlo (MCMC). A tensor's product technique is utilized to optimize the calculation program and speed up the calculation of MCMC. Bayes factor together with the path sampling approach is presented to select tensor rank in CP decomposition. Effectiveness of the proposed method is illustrated on simulation studies and an MRI data analysis. [ABSTRACT FROM AUTHOR]

Alzheimer's disease is dementia that impairs one's thinking, behavior, and memory. It starts as a moderate condition affecting areas of the brain that make it challenging to retain recently learned information, causes mood swings, and causes confusion regarding occasions, times, and locations. The most prevalent type of dementia, called Alzheimer's disease (AD), causes memory-related problems in patients. A precise medical diagnosis that correctly classifies AD patients results in better treatment. Currently, the most commonly used classification techniques extract features from longitudinal MRI data before creating a single classifier that performs classification. However, it is difficult to train a reliable classifier to achieve acceptable classification performance due to limited sample size and noise in longitudinal MRI data. Instead of creating a single classifier, we propose an ensemble voting method that generates multiple individual classifier predictions and then combines them to develop a more accurate and reliable classifier. The ensemble voting classifier model performs better in the Open Access Series of Imaging Studies (OASIS) dataset for older adults than existing methods in important assessment criteria such as accuracy, sensitivity, specificity, and AUC. For the binary classification of with dementia and no dementia, an accuracy of 96.4% and an AUC of 97.2% is attained. [ABSTRACT FROM AUTHOR]

This study analyzed the impact of the health condition of elderly drivers on their driving behavior. We obtained drive recorder data and health check data including cognitive function and magnetic resonance imaging data from drivers older than 70 years of age and living in the Chugei area in Kochi Prefecture, Japan, and performed discriminant analysis. The results showed that safe driving skills are more affected by occipital lobe volume than the conventional cognitive tests such as MMSE and FAB. [ABSTRACT FROM AUTHOR]

Alzheimer's disease is the most common neurodegenerative disease. The aim of this study is to infer structural changes in brain connectivity resulting from disease progression using cortical thickness measurements from a cohort of participants who were either healthy control, or with mild cognitive impairment, or Alzheimer's disease patients. For this purpose, we develop a novel approach for inference of multiple networks with related edge values across groups. Specifically, we infer a Gaussian graphical model for each group within a joint framework, where we rely on Bayesian hierarchical priors to link the precision matrix entries across groups. Our proposal differs from existing approaches in that it flexibly learns which groups have the most similar edge values, and accounts for the strength of connection (rather than only edge presence or absence) when sharing information across groups. Our results identify key alterations in structural connectivity that may reflect disruptions to the healthy brain, such as decreased connectivity within the occipital lobe with increasing disease severity. We also illustrate the proposed method through simulations, where we demonstrate its performance in structure learning and precision matrix estimation with respect to alternative approaches. [ABSTRACT FROM AUTHOR]

• The present study proposes multi-objective fuzzy c-means segmentation method and a new cluster validity index, collectively these two enables segmentation of MRI data complete user independent. • The fitness functions of MOALO utilize LMMSE filtered local spatial information, which helps proposed approach to produce effective segmentation of MRI data. • The proposed CNV index formulated by inculcating multiple cluster properties, i.e. cluster compactness, cluster density and inter-cluster distance. It also have tendency to achieve minimum number of compact clusters. These qualities lead CNV index robust to noise and artifact. • The study presents a detailed comparison, where proposed segmentation approach performs better in comparison to related unsupervised FCM based algorithms and supervised deep learning based algorithms. Accurate segmentation of brain tissues in magnetic resonance imaging (MRI) data plays critical role in the clinical diagnostic and treatment planning. The presence of noise and artifacts in MRI data degrades the performance of segmentation algorithms. In this view, the present study proposes a complete unsupervised clustering based multi-objective modified fuzzy c-mean (MOFCM) segmentation algorithm, which inculcates multi-objective antlion optimization (MOALO) to minimize the cluster compactness and fuzzy hyper-volume fitness functions. The output segmented image corresponds to minimum value of partition entropy in the obtained solution set. The present study integrates proposed MOFCM with a new cluster number validity index, which allows user not to provide number of segments in image as an input. The proposed MOFCM algorithm is extensively validated on seventy two synthetic images corrupted with different levels of Gaussian, Speckle and Rician noises, forty simulated BrainWeb MRI images suffered from noise and inhomogeneity, and 10 real IBSR MRI dataset of images. The results are compared with existing popular clustering based algorithms, and supervised deep learning based algorithms, i.e. UNet, SegNet and QuickNAT. The proposed MOFCM algorithm demonstrate the superior segmentation performance in comparison to popular FCM based clustering algorithms, SegNet and UNet, whereas the segmentation results of proposed MOFCM are at par with QuickNAT. [ABSTRACT FROM AUTHOR]

Image clustering is considered amongst the most important tasks in medical image analysis and it is regularly required as a starter and vital stage in the computer‐aided medical image process. In brain magnetic resonance imaging (MRI) analysis, image clustering is regularly used for estimating and visualising the brain anatomical structures, to detect pathological regions and to guide surgical procedures. This study presents a new method for MRI brain images clustering based on the farthest point first algorithm and fuzzy clustering techniques without using any a priori information about the clusters number. The algorithm has been approved against both simulated and clinical magnetic resonance images and it has been compared with the fourth clustered algorithms. Results demonstrate that the proposed algorithm has given reasonable segmentation of white matter, grey matter and cerebrospinal fluid from MRI data, which is superior in preserving image details and segmentation accuracy compared with the other four algorithms giving more than 91% in Jaccard similarity. [ABSTRACT FROM AUTHOR]

Even with increasing data implicating the venous side of the vascular tree of the brain in MS, no diagnostic or treatment protocol has addressed the risk of acute stroke in MS and no systematic study has documented the incidence or prevalence of acute strokein MS patients. Approximately 795,000 strokes occur in the U.S. each year—every 40 s, someone has a stroke and every 4 min, a person dies from a stroke. However, no large, prospective, multi-center study has investigated acute stroke incidence in MS patients either in the U.S. or internationally, leaving a gap in our understanding of the association between stroke and MS. Additionally, data on acute stroke in MS as determined by age, gender or ethnicity are unknown. To compound this further, the diagnosis and definition of acute stroke in MS remains poorly understood. A survey of published literature shows a few anecdotal reports of acute stroke occurring among MS patients, but most studies do not address the fundamental association between acute stroke and MS. Symptoms of acute stroke and MS can overlap and the lack of clear clinical/radiological criteria that alert the patient or clinician to the development of acute stroke in an MS patient compound the dilemma, even leading to the administration of IV alteplase in cases that are later diagnosed as either MS or having an “MS flare.” Clinical trials that use aspirin in multiple sclerosis are urgently needed.

Even with increasing data implicating the venous side of the vascular tree of the brain in MS, no diagnostic or treatment protocol has addressed the risk of acute stroke in MS and no systematic study has documented the incidence or prevalence of acute strokein MS patients. Approximately 795,000 strokes occur in the U.S. each year—every 40 s, someone has a stroke and every 4 min, a person dies from a stroke. However, no large, prospective, multi-center study has investigated acute stroke incidence in MS patients either in the U.S. or internationally, leaving a gap in our understanding of the association between stroke and MS. Additionally, data on acute stroke in MS as determined by age, gender or ethnicity are unknown. To compound this further, the diagnosis and definition of acute stroke in MS remains poorly understood. A survey of published literature shows a few anecdotal reports of acute stroke occurring among MS patients, but most studies do not address the fundamental association between acute stroke and MS. Symptoms of acute stroke and MS can overlap and the lack of clear clinical/radiological criteria that alert the patient or clinician to the development of acute stroke in an MS patient compound the dilemma, even leading to the administration of IV alteplase in cases that are later diagnosed as either MS or having an “MS flare.” Clinical trials that use aspirin in multiple sclerosis are urgently needed. [ABSTRACT FROM AUTHOR]

Automated brain segmentation may leave errors which can be identified by comparing the location of the actual MRI voxels with reference to the reconstructed pial polygonal surface of the brain. Location of the segmentation errors can be marked by displaying color spots on the brain surface followed by its interactive editing, as we previously proposed. In this paper, a new haptic friction-based approach of identifying and correcting errors has been discussed. The user can feel as different friction the discrepancy along the reconstructed surface by moving a haptic proxy along it followed by rubbing the surface as if it is being polished. The proposed approach does not only limit its application in editing of medical data, but can also be successfully used for visually impaired group as this dynamic friction-based editing helps any novice user identify error prone area just by touching the surface. [ABSTRACT FROM AUTHOR]

Abstract: MRI segmentation is a process of deriving semantic information from volume data. For brain MRI data, segmentation is initially performed at a voxel level and then continued at a brain surface level by generating its approximation. While successful most of the time, automated brain segmentation may leave errors which have to be removed interactively by editing individual 2D slices. We propose an approach for correcting these segmentation errors in 3D modeling space. We actively use the brain surface, which is estimated (potentially wrongly) in the automated FreeSurfer segmentation pipeline. It allows us to work with the whole data set at once, utilizing the context information and correcting several slices simultaneously. Proposed heuristic editing support and automatic visual highlighting of potential error locations allow us to substantially reduce the segmentation time. The paper describes the implementation principles of the proposed software tool and illustrates its application. [Copyright &y& Elsevier]

Abstract: Bias-corrected fuzzy c-means (BCFCM) algorithm with spatial information is especially effective in image segmentation. Since it is computationally time taking and lacks enough robustness to noise and outliers, some kernel versions of FCM with spatial constraints, such as KFCM_S1 and KFCM_S2, were proposed to solve those drawbacks of BCFCM. However, KFCM_S1 and KFCM_S2 are heavily affected by their parameters. In this paper, we present a Gaussian kernel-based fuzzy c-means algorithm (GKFCM) with a spatial bias correction. The proposed GKFCM algorithm becomes a generalized type of FCM, BCFCM, KFCM_S1 and KFCM_S2 algorithms and presents with more efficiency and robustness. Some numerical and image experiments are performed to assess the performance of GKFCM in comparison with FCM, BCFCM, KFCM_S1 and KFCM_S2. Experimental results show that the proposed GKFCM has better performance. [Copyright &y& Elsevier]

Pooled data from placebo groups of different trials can serve as historical control for ongoing or future therapeutic studies and as a reference for power calculations. In order to assess their usefulness for this purpose, we investigated the degree of heterogeneity of placebo arm data from 14 controlled studies included in the database of the Sylvia Lawry Centre for Multiple Sclerosis Research. Since different criteria for the inclusion/exclusion of patients were used in these studies, an attempt was made to adjust the distribution of magnetic resonance imaging (MRI) measures for the differences in the study populations. The analyses showed that, even after adjustment, significant differences remained. This heterogeneity does not reduce the usefulness of the database for statistical analysis of inter-relationships between variables, provided that it is explicitly taken into account as a stratification factor. However, care must be taken when trying to compare the results of a newly treated group with the patients of this pool. Heterogeneity in some MRI variables was greatly reduced when only studies from the same image analysis centre were compared. [ABSTRACT FROM AUTHOR]

(1) Background: Recently, it has been shown that the extent of resection (EOR) and molecular classification of low-grade gliomas (LGGs) are endowed with prognostic significance. However, a prognostic stratification of patients able to give specific weight to the single parameters able to predict prognosis is still missing. Here, we adopt classic statistics and an artificial intelligence algorithm to define a multiparametric prognostic stratification of grade II glioma patients. (2) Methods: 241 adults who underwent surgery for a supratentorial LGG were included. Clinical, neuroradiological, surgical, histopathological and molecular data were assessed for their ability to predict overall survival (OS), progression-free survival (PFS), and malignant progression-free survival (MPFS). Finally, a decision-tree algorithm was employed to stratify patients. (3) Results: Classic statistics confirmed EOR, pre-operative- and post-operative tumor volumes, Ki67, and the molecular classification as independent predictors of OS, PFS, and MPFS. The decision tree approach provided an algorithm capable of identifying prognostic factors and defining both the cut-off levels and the hierarchy to be used in order to delineate specific prognostic classes with high positive predictive value. Key results were the superior role of EOR on that of molecular class, the importance of second surgery, and the role of different prognostic factors within the three molecular classes. (4) Conclusions: This study proposes a stratification of LGG patients based on the different combinations of clinical, molecular, and imaging data, adopting a supervised non-parametric learning method. If validated in independent case studies, the clinical utility of this innovative stratification approach might be proved. [ABSTRACT FROM AUTHOR]