Search

Abstract Myocarditis is a significant public health concern because of its potential to cause heart failure and sudden death. The standard invasive diagnostic method, endomyocardial biopsy, is typically reserved for cases with severe complications, limiting its widespread use. Conversely, non‐invasive cardiac magnetic resonance (CMR) imaging presents a promising alternative for detecting and monitoring myocarditis, because of its high signal contrast that reveals myocardial involvement. To assist medical professionals via artificial intelligence, the authors introduce generative adversarial networks ‐ multi discriminator (GAN‐MD), a deep learning model that uses binary classification to diagnose myocarditis from CMR images. Their approach employs a series of convolutional neural networks (CNNs) that extract and combine feature vectors for accurate diagnosis. The authors suggest a novel technique for improving the classification precision of CNNs. Using generative adversarial networks (GANs) to create synthetic images for data augmentation, the authors address challenges such as mode collapse and unstable training. Incorporating a reconstruction loss into the GAN loss function requires the generator to produce images reflecting the discriminator features, thus enhancing the generated images' quality to more accurately replicate authentic data patterns. Moreover, combining this loss function with other regularisation methods, such as gradient penalty, has proven to further improve the performance of diverse GAN models. A significant challenge in myocarditis diagnosis is the imbalance of classification, where one class dominates over the other. To mitigate this, the authors introduce a focal loss‐based training method that effectively trains the model on the minority class samples. The GAN‐MD approach, evaluated on the Z‐Alizadeh Sani myocarditis dataset, achieves superior results (F‐measure 86.2%; geometric mean 91.0%) compared with other deep learning models and traditional machine learning methods.

Abstract Cancer is one of the leading causes of death in the world, with radiotherapy as one of the treatment options. Radiotherapy planning starts with delineating the affected area from healthy organs, called organs at risk (OAR). A new approach to automatic OAR segmentation in the chest cavity in Computed Tomography (CT) images is presented. The proposed approach is based on the modified U‐Net architecture with the ResNet‐34 encoder, which is the baseline adopted in this work. The new two‐branch CS‐SA U‐Net architecture is proposed, which consists of two parallel U‐Net models in which self‐attention blocks with cosine similarity as query‐key similarity function (CS‐SA) blocks are inserted between the encoder and decoder, which enabled the use of consistency regularisation. The proposed solution demonstrates state‐of‐the‐art performance for the problem of OAR segmentation in CT images on the publicly available SegTHOR benchmark dataset in terms of a Dice coefficient (oesophagus—0.8714, heart—0.9516, trachea—0.9286, aorta—0.9510) and Hausdorff distance (oesophagus—0.2541, heart—0.1514, trachea—0.1722, aorta—0.1114) and significantly outperforms the baseline. The current approach is demonstrated to be viable for improving the quality of OAR segmentation for radiotherapy planning.

The integration of positron emission tomography (PET) and single-photon emission computed tomography (SPECT) imaging techniques with machine learning (ML) algorithms, including deep learning (DL) models, is a promising approach. This integration enhances the precision and efficiency of current diagnostic and treatment strategies while offering invaluable insights into disease mechanisms. In this comprehensive review, we delve into the transformative impact of ML and DL in this domain. Firstly, a brief analysis is provided of how these algorithms have evolved and which are the most widely applied in this domain. Their different potential applications in nuclear imaging are then discussed, such as optimization of image adquisition or reconstruction, biomarkers identification, multimodal fusion and the development of diagnostic, prognostic, and disease progression evaluation systems. This is because they are able to analyse complex patterns and relationships within imaging data, as well as extracting quantitative and objective measures. Furthermore, we discuss the challenges in implementation, such as data standardization and limited sample sizes, and explore the clinical opportunities and future horizons, including data augmentation and explainable AI. Together, these factors are propelling the continuous advancement of more robust, transparent, and reliable systems.

Artificial intelligence (AI) refers to the field of computer science theory and technology [...]

The accelerating power of deep learning in diagnosing a disease and analyzing medical data will empower physicians and speed up decision-making in clinical environments. Applications of modern medical instruments and digitalization of medical care have generated large amounts of biomedical information in recent years. These pose challenges, demands, and opportunities for new AI methods and computational models for efficient data processing, analysis, and modeling with the generated data that are important for clinical applications and in understanding the underlying biological process.

Aims: Brain diseases refer to intracranial tissue and organ inflammation, vascular diseases, tumors, degeneration, malformations, genetic diseases, immune diseases, nutritional and metabolic diseases, poisoning, trauma, parasitic diseases, etc. Taking Alzheimer’s disease (AD) as an example, the number of patients dramatically increases in developed countries. By 2025, the number of elderly patients with AD aged 65 and over will reach 7.1 million, an increase of nearly 29% over the 5.5 million patients of the same age in 2018. Unless medical breakthroughs are made, AD patients may increase from 5.5 million to 13.8 million by 2050, almost three times the original. Researchers have focused on developing complex machine learning (ML) algorithms, i.e., convolutional neural networks (CNNs), containing millions of parameters. However, CNN models need many training samples. A small number of training samples in CNN models may lead to overfitting problems. With the continuous research of CNN, other networks have been proposed, such as randomized neural networks (RNNs). Schmidt neural network (SNN), random vector functional link (RVFL), and extreme learning machine (ELM) are three types of RNNs.Methods: We propose three novel models to classify brain diseases to cope with these problems. The proposed models are DenseNet-based SNN (DSNN), DenseNet-based RVFL (DRVFL), and DenseNet-based ELM (DELM). The backbone of the three proposed models is the pre-trained “customize” DenseNet. The modified DenseNet is fine-tuned on the empirical dataset. Finally, the last five layers of the fine-tuned DenseNet are substituted by SNN, ELM, and RVFL, respectively.Results: Overall, the DSNN gets the best performance among the three proposed models in classification performance. We evaluate the proposed DSNN by five-fold cross-validation. The accuracy, sensitivity, specificity, precision, and F1-score of the proposed DSNN on the test set are 98.46% ± 2.05%, 100.00% ± 0.00%, 85.00% ± 20.00%, 98.36% ± 2.17%, and 99.16% ± 1.11%, respectively. The proposed DSNN is compared with restricted DenseNet, spiking neural network, and other state-of-the-art methods. Finally, our model obtains the best results among all models.Conclusions: DSNN is an effective model for classifying brain diseases.

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1D-CNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25%, better than the results of most former studies in this field. It is worth mentioning that to perform all simulations, the k-fold cross-validation method with k = 5 has been used.

Traditional medical sensors/monitors can measure pressure, airflow, force, oxygen, pulse, temperature, etc [...]

In this paper, a novel medical image encryption method based on multi-mode synchronization of hyper-chaotic systems is presented. The synchronization of hyper-chaotic systems is of great significance in secure communication tasks such as encryption of images. Multi-mode synchronization is a novel and highly complex issue, especially if there is uncertainty and disturbance. In this work, an adaptive-robust controller is designed for multimode synchronized chaotic systems with variable and unknown parameters, despite the bounded disturbance and uncertainty with a known function in two modes. In the first case, it is a main system with some response systems, and in the second case, it is a circular synchronization. Using theorems it is proved that the two synchronization methods are equivalent. Our results show that, we are able to obtain the convergence of synchronization error and parameter estimation error to zero using Lyapunov’s method. The new laws to update time-varying parameters, estimating disturbance and uncertainty bounds are proposed such that stability of system is guaranteed. To assess the performance of the proposed synchronization method, various statistical analyzes were carried out on the encrypted medical images and standard benchmark images. The results show effective performance of the proposed synchronization technique in the medical images encryption for telemedicine application.

Over recent years, deep learning (DL) has established itself as a powerful tool across a broad spectrum of domains in imaging—e [...]

(Aim) Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way. (Materials) We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC). (Method) We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM). (Results) The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier. (Conclusions) This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss.

Alzheimer’s Disease (AD) is the most common neurodegenerative disease in elderly people. Itsdevelopment has been shown to be closely related to changes in the brain connectivity networkand in the brain activation patterns along with structural changes caused by the neurodegenerativeprocess.Methods to infer dependence between brain regions are usually derived from the analysis ofcovariance between activation levels in the different areas. However, these covariance-basedmethods are not able to estimate conditional independence between variables to factor out theinfluence of other regions. Conversely, models based on the inverse covariance, or precisionmatrix, such as Sparse Gaussian Graphical Models allow revealing conditional independencebetween regions by estimating the covariance between two variables given the rest as constant.This paper uses Sparse Inverse Covariance Estimation (SICE) methods to learn undirectedgraphs in order to derive functional and structural connectivity patterns from Fludeoxyglucose(18F-FDG) Position Emission Tomography (PET) data and segmented Magnetic Resonanceimages (MRI), drawn from the ADNI database, for Control, MCI (Mild Cognitive ImpairmentSubjects) and AD subjects. Sparse computation fits perfectly here as brain regions usually onlyinteract with a few other areas.The models clearly show different metabolic covariation patters between subject groups, revealingthe loss of strong connections in AD and MCI subjects when compared to Controls. Similarly,the variance between GM (Grey Matter) densities of different regions reveals different structuralcovariation patterns between the different groups. Thus, the different connectivity patterns forcontrols and AD are used in this paper to select regions of interest in PET and GM images withdiscriminative power for early AD diagnosis. Finally, functional an structural models are combinedto leverage the classification accuracy.The results obtained in this work show the usefulness of the Sparse Gaussian Graphical models to reveal functional and structural connectivity patterns. This information provided by the sparseinverse covariance matrices is not only used in an exploratory way but we also propose a methodto use it in a discriminative way. Regression coefficients are used to compute reconstructionerrors for the different classes that are then introduced in a SVM for classification.

Differentiating between Parkinson's disease (PD) and atypical parkinsonian syndromes (APS) is still a challenge, specially at early stages when the patients show similar symptoms. During last years, several computer systems have been proposed in order to improve the diagnosis of PD, but their accuracy is still limited. In this work we demonstrate a full automatic computer system to assist the diagnosis of PD using 18F-DMFP PET data. First, a few regions of interest are selected by means of a two-sample t-test. The accuracy of the selected regions to separate PD from APS patients is then computed using a support vector machine classifier. The accuracy values are finally used to train a Bayesian network that can be used to predict the class of new unseen data. This methodology was evaluated using a database with 87 neuroimages, achieving accuracy rates over 78%. A fair comparison with other similar approaches is also provided.

This work presents a spatial-component (SC) based approach to aid the diagnosis of Alzheimer's disease (AD) using magnetic resonance images. In this approach, the whole brain image is subdivided in regions or spatial components, and a Bayesian network is used to model the dependencies between affected regions of AD. The structure of relations between affected regions allows to detect neurodegeneration with an estimated performance of 88 % on more than 400 subjects and predict neurodegeneration with 80 % accuracy, supporting the conclusion that modelling the dependencies between components increases the recognition of different patterns of brain degeneration in AD.

Abstract Counting high‐density objects quickly and accurately is a popular area of research. Crowd counting has significant social and economic value and is a major focus in artificial intelligence. Despite many advancements in this field, many of them are not widely known, especially in terms of research data. The authors proposed a three‐tier standardised dataset taxonomy (TSDT). The Taxonomy divides datasets into small‐scale, large‐scale and hyper‐scale, according to different application scenarios. This theory can help researchers make more efficient use of datasets and improve the performance of AI algorithms in specific fields. Additionally, the authors proposed a new evaluation index for the clarity of the dataset: average pixel occupied by each object (APO). This new evaluation index is more suitable for evaluating the clarity of the dataset in the object counting task than the image resolution. Moreover, the authors classified the crowd counting methods from a data‐driven perspective: multi‐scale networks, single‐column networks, multi‐column networks, multi‐task networks, attention networks and weak‐supervised networks and introduced the classic crowd counting methods of each class. The authors classified the existing 36 datasets according to the theory of three‐tier standardised dataset taxonomy and discussed and evaluated these datasets. The authors evaluated the performance of more than 100 methods in the past five years on different levels of popular datasets. Recently, progress in research on small‐scale datasets has slowed down. There are few new datasets and algorithms on small‐scale datasets. The studies focused on large or hyper‐scale datasets appear to be reaching a saturation point. The combined use of multiple approaches began to be a major research direction. The authors discussed the theoretical and practical challenges of crowd counting from the perspective of data, algorithms and computing resources. The field of crowd counting is moving towards combining multiple methods and requires fresh, targeted datasets. Despite advancements, the field still faces challenges such as handling real‐world scenarios and processing large crowds in real‐time. Researchers are exploring transfer learning to overcome the limitations of small datasets. The development of effective algorithms for crowd counting remains a challenging and important task in computer vision and AI, with many opportunities for future research.

Aims: Most blood diseases, such as chronic anemia, leukemia (commonly known as blood cancer), and hematopoietic dysfunction, are caused by environmental pollution, substandard decoration materials, radiation exposure, and long-term use certain drugs. Thus, it is imperative to classify the blood cell images. Most cell classification is based on the manual feature, machine learning classifier or the deep convolution network neural model. However, manual feature extraction is a very tedious process, and the results are usually unsatisfactory. On the other hand, the deep convolution neural network is usually composed of massive layers, and each layer has many parameters. Therefore, each deep convolution neural network needs a lot of time to get the results. Another problem is that medical data sets are relatively small, which may lead to overfitting problems.Methods: To address these problems, we propose seven models for the automatic classification of blood cells: BCARENet, BCR5RENet, BCMV2RENet, BCRRNet, BCRENet, BCRSNet, and BCNet. The BCNet model is the best model among the seven proposed models. The backbone model in our method is selected as the ResNet-18, which is pre-trained on the ImageNet set. To improve the performance of the proposed model, we replace the last four layers of the trained transferred ResNet-18 model with the three randomized neural networks (RNNs), which are RVFL, ELM, and SNN. The final outputs of our BCNet are generated by the ensemble of the predictions from the three randomized neural networks by the majority voting. We use four multi-classification indexes for the evaluation of our model.Results: The accuracy, average precision, average F1-score, and average recall are 96.78, 97.07, 96.78, and 96.77%, respectively.Conclusion: We offer the comparison of our model with state-of-the-art methods. The results of the proposed BCNet model are much better than other state-of-the-art methods.

As an important imaging modality, mammography is considered to be the global gold standard for early detection of breast cancer. Computer-Aided (CAD) systems have played a crucial role in facilitating quicker diagnostic procedures, which otherwise could take weeks if only radiologists were involved. In some of these CAD systems, breast pectoral segmentation is required for breast region partition from breast pectoral muscle for specific analysis tasks. Therefore, accurate and efficient breast pectoral muscle segmentation frameworks are in high demand. Here, we proposed a novel deep learning framework, which we code-named PeMNet, for breast pectoral muscle segmentation in mammography images. In the proposed PeMNet, we integrated a novel attention module called the Global Channel Attention Module (GCAM), which can effectively improve the segmentation performance of Deeplabv3+ using minimal parameter overheads. In GCAM, channel attention maps (CAMs) are first extracted by concatenating feature maps after paralleled global average pooling and global maximum pooling operation. CAMs are then refined and scaled up by multi-layer perceptron (MLP) for elementwise multiplication with CAMs in next feature level. By iteratively repeating this procedure, the global CAMs (GCAMs) are then formed and multiplied elementwise with final feature maps to lead to final segmentation. By doing so, CAMs in early stages of a deep convolution network can be effectively passed on to later stages of the network and therefore leads to better information usage. The experiments on a merged dataset derived from two datasets, INbreast and OPTIMAM, showed that PeMNet greatly outperformed state-of-the-art methods by achieving an IoU of 97.46%, global pixel accuracy of 99.48%, Dice similarity coefficient of 96.30%, and Jaccard of 93.33%, respectively.

Ellipsoid fitting algorithms are widely used to calibrate Magnetic Angular Rate and Gravity (MARG) sensors. These algorithms are based on the minimization of an error function that optimizes the parameters of a mathematical sensor model that is subsequently applied to calibrate the raw data. The convergence of this kind of algorithms to a correct solution is very sensitive to input data. Input calibration datasets must be properly distributed in space so data can be accurately fitted to the theoretical ellipsoid model. Gathering a well distributed set is not an easy task as it is difficult for the operator carrying out the maneuvers to keep a visual record of all the positions that have already been covered, as well as the remaining ones. It would be then desirable to have a system that gives feedback to the operator when the dataset is ready, or to enable the calibration process in auto-calibrated systems. In this work, we propose two different algorithms that analyze the goodness of the distributions by computing four different indicators. The first approach is based on a thresholding algorithm that uses only one indicator as its input and the second one is based on a Fuzzy Logic System (FLS) that estimates the calibration error for a given calibration set using a weighted combination of two indicators. Very accurate classification between valid and invalid datasets is achieved with average Area Under Curve (AUC) of up to 0.98.

The existence of an endophenotype of autism spectrum condition (ASC) has been recently suggested by several commentators. It can be estimated by finding differences between controls and people with ASC that are also present when comparing controls and the unaffected siblings of ASC individuals. In this work, we used a multivariate methodology applied on magnetic resonance images to look for such differences. The proposed procedure consists of combining a searchlight approach and a support vector machine classifier to identify the differences between three groups of participants in pairwise comparisons: controls, people with ASC and their unaffected siblings. Then we compared those differences selecting spatially collocated as candidate endophenotypes of ASC.

This paper shows an adaptive statistical test for QRS detection of electrocardiography (ECG) signals. The method is based on a M-ary generalized likelihood ratio test (LRT) defined over a multiple observation window in the Fourier domain. The motivations for proposing another detection algorithm based on maximum a posteriori (MAP) estimation are found in the high complexity of the signal model proposed in previous approaches which i) makes them computationally unfeasible or not intended for real time applications such as intensive care monitoring and (ii) in which the parameter selection conditions the overall performance. In this sense, we propose an alternative model based on the independent Gaussian properties of the Discrete Fourier Transform (DFT) coefficients, which allows to define a simplified MAP probability function. In addition, the proposed approach defines an adaptive MAP statistical test in which a global hypothesis is defined on particular hypotheses of the multiple observation window. In this sense, the observation interval is modeled as a discontinuous transmission discrete-time stochastic process avoiding the inclusion of parameters that constraint the morphology of the QRS complexes.

In recent years, several approaches to develop computer aided diagnosis (CAD) systems for dementia have been proposed. Some of these systems analyze neurological brain images by means of machine learning algorithms in order to find the patterns that characterize the disorder, and a few combine several imaging modalities to improve the diagnostic accuracy. However, they usually do not use neuropsychological testing data in that analysis. The purpose of this work is to measure the advantages of using not only neuroimages as data source in CAD systems for dementia but also neuropsychological scores. To this aim, we compared the accuracy rates achieved by systems that use neuropsychological scores beside the imaging data in the classification step and systems that use only one of these data sources. In order to address the small sample size problem and facilitate the data combination, a dimensionality reduction step (implemented using three different algorithms) was also applied on the imaging data. After each image is summarized in a reduced set of image features, the data sources were combined and classified using three different data combination approaches and a Support Vector Machine classifier. That way, by testing different dimensionality reduction methods and several data combination approaches, we aim not only highlighting the advantages of using neuropsychological scores in the classification, but also implementing the most accurate computer system for early dementia detention. The accuracy of the CAD systems were estimated using a database with records from 46 subjects, diagnosed with MCI or AD. A peak accuracy rate of 89% was obtained. In all cases the accuracy achieved using both, neuropsychological scores and imaging data, was substantially higher than the one obtained using only the imaging data.