Search

The Internet of Medical Things (IoMT) is poised to play a pivotal role in future medical support systems, enabling pervasive health monitoring in smart cities. Alzheimer's disease (AD) afflicts millions globally, and this paper explores the potential of electroencephalogram (EEG) data in addressing this challenge. We propose the Convolutional Learning Attention-Bidirectional Time-Aware Long-Short-Term Memory (CL-ATBiLSTM) model, a deep learning approach designed to classify different AD phases through EEG data analysis. The model utilizes Discrete Wavelet Transform (DWT) to decompose EEG data into distinct frequency bands, allowing for targeted analysis of AD-related brain activity patterns. Additionally, the data is segmented into smaller windows to handle the dynamic nature of EEG signals, and these segments are transformed into spectrogram images, visually depicting brain activity distribution over time and frequency. The CL-ATBiLSTM model incorporates convolutional layers to capture spatial features, attention mechanisms to emphasize crucial data, and BiLSTM networks to explore temporal relationships within the sequences. To optimize the model's performance, Bayesian optimization is employed to fine-tune the hyperparameters of the ATBiLSTM network, enhancing its ability to generalize and accurately classify AD stages. Incorporating Bayesian learning ensures the most effective model configuration, improving sensitivity and specificity for identifying AD-related patterns. Our model extracts discriminative features from EEG data to differentiate between AD, Mild Cognitive Impairment (MCI), and healthy controls (CO), offering a more comprehensive approach than existing two-class detection algorithms. By including the MCI category, our method facilitates earlier identification and potentially more impactful therapy interventions. Achieving a 96.52% accuracy on Figshare datasets containing AD, MCI, and CO groups, our approach demonstrates strong potential for practical use, accelerating AD identification, enhancing patient care, and contributing to the development of targeted treatments for this debilitating condition., (© 2024. The Author(s).)

Attention Deficit Hyperactivity Disorder (ADHD) is characterized by deficits in attention, hyperactivity, and/or impulsivity. Resting-state functional connectivity analysis has emerged as a promising approach for ADHD classification using resting-state functional magnetic resonance imaging (rs-fMRI), although with limited accuracy. Recent studies have highlighted dynamic changes in functional connectivity patterns among ADHD children. In this study, we introduce Skip-Vote-Net, a novel deep learning-based network designed for classifying ADHD from typically developing children (TDC) by leveraging dynamic connectivity analysis on rs-fMRI data collected from 222 participants included in the NYU dataset within the ADHD-200 database. Initially, for each subject, functional connectivity matrices were constructed from overlapping segments using Pearson's correlation between mean time series of 116 regions of interest defined by the Automated Anatomical Labeling (AAL) 116 atlas. Skip-Vote-Net was then developed, employing a majority voting mechanism to classify ADHD/TDC children, as well as distinguishing between the two main subtypes: the inattentive subtype (ADHD I ) and the predominantly combined subtype (ADHD C ). The proposed method was evaluated across four classification scenarios: (1) two-class classification of ADHD from TD children using balanced data, (2) two-class classification between ADHD and TD children using unbalanced data, (3) two-class classification between ADHD I and ADHD C , and (4) three-class classification among ADHD I , ADHD C , and TD children. Using Skip-Vote-Net, we achieved mean classification accuracies of 97% ± 1.87 and 97.7% ± 2.2 for the balanced and unbalanced classification cases, respectively. Furthermore, the mean classification accuracy for discriminating between ADHD I and ADHD C reached 99.4% ± 1.21. Finally, the proposed method demonstrated an average accuracy of 98.86% ± 1.03 in classifying ADHD I , ADHD C , and TD children collectively. Our findings highlight the superior performance of Skip-Vote-Net over existing methods in the classification of ADHD, showcasing its potential as an effective diagnostic tool for identifying ADHD subtypes and distinguishing ADHD from typically developing children., (© 2024. The Author(s).)

Background: Wireless capsule endoscopy (WCE) is a patient-friendly and non-invasive technology that scans the whole of the gastrointestinal tract, including difficult-to-access regions like the small bowel. Major drawback of this technology is that the visual inspection of a large number of video frames produced during each examination makes the physician diagnosis process tedious and prone to error. Several computer-aided diagnosis (CAD) systems, such as deep network models, have been developed for the automatic recognition of abnormalities in WCE frames. Nevertheless, most of these studies have only focused on spatial information within individual WCE frames, missing the crucial temporal data within consecutive frames., Methods: In this article, an automatic multiclass classification system based on a three-dimensional deep convolutional neural network (3D-CNN) is proposed, which utilizes the spatiotemporal information to facilitate the WCE diagnosis process. The 3D-CNN model fed with a series of sequential WCE frames in contrast to the two-dimensional (2D) model, which exploits frames as independent ones. Moreover, the proposed 3D deep model is compared with some pre-trained networks. The proposed models are trained and evaluated with 29 subject WCE videos (14,691 frames before augmentation). The performance advantages of 3D-CNN over 2D-CNN and pre-trained networks are verified in terms of sensitivity, specificity, and accuracy., Results: 3D-CNN outperforms the 2D technique in all evaluation metrics (sensitivity: 98.92 vs. 98.05, specificity: 99.50 vs. 86.94, accuracy: 99.20 vs. 92.60). In conclusion, a novel 3D-CNN model for lesion detection in WCE frames is proposed in this study., Conclusion: The results indicate the performance of 3D-CNN over 2D-CNN and some well-known pre-trained classifier networks. The proposed 3D-CNN model uses the rich temporal information in adjacent frames as well as spatial data to develop an accurate and efficient model., (© 2023. The Author(s).)

Cannabis is one of the most used and commodified illicit substances worldwide, especially among young adults. The neurobiology mechanism of cannabis is yet to be identified particularly in youth. The purpose of this study was to concurrently measure alterations in brain structural and functional connectivity in cannabis users using resting-state functional magnetic resonance images (rs-fMRI) and diffusion-weighted images (DWI) from a group of 73 cannabis users (age 22-36, 19 female) in comparison with 73 healthy controls (age 22-36, 14 female) from Human Connectome Project (HCP). Several significant differences were observed in local structural/functional network measures (e.g. degree and clustering coefficient), being prominent in the insular and frontal opercular cortex and lateral/medial temporal cortex. The rich-club organization of structural networks revealed a normal trend, distributed within bilateral frontal, temporal and occipital regions. However, minor differences were found between the two groups in the superior and inferior temporal gyri. Functional rich-club nodes were mostly located within parietal and posterior areas, with minor differences between the groups found mainly in the centro-temporal and parietal regions. Regional network measures of structural/functional networks were associated with times used cannabis (TUC) in several regions. Although the structural/functional network in both groups showed small-world property, no differences between cannabis users and healthy controls were found regarding the global network measures, showing no association with cannabis use. After FDR correction, all of the significant associations between network measures and TUC were found to be insignificant, except for the association between degree and TUC within the presubiculum region. To recap, our findings revealed alterations in local topological properties of structural and functional networks in cannabis users, although their global brain network organization remained intact., (© 2023. The Author(s).)

The detection of multi-scale pedestrians is one of the challenging tasks in pedestrian detection applications. Moreover, the task of small-scale pedestrian detection, i.e., accurate localization of pedestrians as low-scale target objects, can help solve the issue of occluded pedestrian detection as well. In this paper, we present a fully convolutional neural network with a new architecture and an innovative, fully detailed supervision for semantic segmentation of pedestrians. The proposed network has been named butterfly network (BF-Net) because of its architecture analogous to a butterfly. The proposed BF-Net preserves the ability of simplicity so that it can process static images with a real-time image processing rate. The sub-path blocks embedded in the architecture of the proposed BF-Net provides a higher accuracy for detecting multi-scale objective targets including the small ones. The other advantage of the proposed architecture is replacing common batch normalization with conditional one. In conclusion, the experimental results of the proposed method demonstrate that the proposed network outperform the other state-of-the-art networks such as U-Net +  + , U-Net3 + , Mask-RCNN, and Deeplabv3 + for the semantic segmentation of the pedestrians., Competing Interests: Conflict of interestAll authors declare that they have no conflicts of interest., (© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023, Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.)

Cue-induced drug craving and disinhibition are two essential components of continued drug use and relapse in substance use disorders. While these phenomena develop and interact across time, the temporal dynamics of their underlying neural activity remain under-investigated. To explore these dynamics, an analysis of time-varying activation was applied to fMRI data from 62 men with methamphetamine use disorder in their first weeks of recovery in an abstinence-based treatment program. Using a mixed block-event, factorial cue-reactivity/Go-NoGo task and a sliding window across the task duration, dynamically-activated regions were identified in three linear mixed effects models (LMEs). Habituation to drug cues across time was observed in the superior temporal gyri, amygdalae, left hippocampus, and right precuneus, while response inhibition was associated with the sensitization of temporally-dynamic activations across many regions of the inhibitory frontoparietal network. Methamphetamine-related response inhibition was associated with temporally-dynamic activity in the parahippocampal gyri and right precuneus (corrected p-value < 0.001), which show a declining cue-reactivity contrast and an increasing response inhibition contrast. Overall, the declining craving-related activations (habituation) and increasing inhibition-associated activations (sensitization) during the task duration suggest the gradual recruitment of response inhibitory processes and a concurrent habituation to drug cues in areas with temporally-dynamic methamphetamine-related response inhibition. Furthermore, temporally dynamic cue-reactivity and response inhibition were correlated with behavioral and clinical measures such as the severity of methamphetamine use and craving, impulsivity and inhibitory task performance. This exploratory study demonstrates the time-variance of the neural activations undergirding cue-reactivity, response inhibition, and response inhibition during exposure to drug cues, and suggests a method to assess this dynamic interplay. Analyses that can capture temporal fluctuations in the neural substrates of drug cue-reactivity and response inhibition may prove useful for biomarker development by revealing the rate and pattern of sensitization and habituation processes, and may inform mixed cue-exposure intervention paradigms which could promote habituation to drug cues and sensitization in inhibitory control regions., (© 2022. The Author(s).)

Background: Brain tumor extraction from magnetic resonance (MR) images is challenging due to variations in the location, shape, size and intensity of tumors. Manual delineation of brain tumors from MR images is time-consuming and prone to human errors., Method: In this paper, we present a method for automatic tumor extraction from multimodal MR images. Brain tumors are first detected using k-means clustering. A morphological region-based active contour model is then used for tumor extraction using an initial contour defined based on the boundary of the detected brain tumor regions. The contour evolution for tumor extraction was performed using successive application of morphological operators. In our model, a Gaussian distribution was used to model local image intensities. The spatial correlation between neighboring voxels was also modeled using Markov random field., Results: The proposed method was evaluated on BraTS 2013 dataset including patients with high-grade and low-grade tumors. In comparison with other active contour based methods, the proposed method yielded better performance on tumor segmentation with mean Dice similarity coefficients of 0.9179 ( ± 0.025) and 0.8910 ( ± 0.042) obtained on high-grade and low-grade tumors, respectively., Conclusion: The proposed method achieved higher accuracies for brain tumor extraction in comparison to other contour-based methods., (Copyright © 2021 Elsevier B.V. All rights reserved.)

Melanoma is one of the deadliest types of skin cancer with increasing incidence. The most definitive diagnosis method is the histopathological examination of the tissue sample. In this paper, a melanoma detection algorithm is proposed based on decision-level fusion and a Hidden Markov Model (HMM), whose parameters are optimized using Expectation Maximization (EM) and asymmetric analysis. The texture heterogeneity of the samples is determined using asymmetric analysis. A fusion-based HMM classifier trained using EM is introduced. For this purpose, a novel texture feature is extracted based on two local binary patterns, namely local difference pattern (LDP) and statistical histogram features of the microscopic image. Extensive experiments demonstrate that the proposed melanoma detection algorithm yields a total error of less than 0.04%.

Attention deficit/hyperactivity disorder (ADHD) is characterized by inattention, hyperactivity and impulsivity. In this study, we investigated group differences in dynamic functional connectivity (dFC) between 113 children with inattentive (46 ADHD I ) and combined (67 ADHD C ) ADHD and 76 typically developing (TD) children using resting-state functional MRI data. For dynamic connectivity analysis, the data were first decomposed into 100 independent components, among which 88 were classified into eight well-known resting-state networks (RSNs). Three discrete FC states were then identified using k-means clustering and used to estimate transition probabilities between states in both patient and control groups using a hidden Markov model. Our results showed state-dependent alterations in intra and inter-network connectivity in both ADHD subtypes in comparison with TD. Spending less time than healthy controls in state 1, both ADHD I and ADHD C were characterized with weaker intra-hemispheric connectivity with functional asymmetries. In this state, ADHD I further showed weaker inter-hemispheric connectivity. The patients spent more time in state 2, exhibiting characteristic abnormalities in corticosubcortical and corticocerebellar connectivity. In state 3, a less frequently state observed across the ADHD and TD children, ADHD C was differentiated from ADHD I by significant alterations in FC between bilateral temporal regions and other brain areas in comparison with TD. Across all three states, several strategic brain regions, mostly bilateral, exhibited significant alterations in both static functional connectivity (sFC) and dFC in the ADHD groups compared to TD, including inferior, middle and superior temporal gyri, middle frontal gyri, insula, anterior cingulum cortex, precuneus, calcarine, fusiform, superior motor area, and cerebellum. Our results show distributed abnormalities in sFC and dFC between different large-scale RSNs including cortical and subcortical regions in both ADHD subtypes compared to TD. Our findings show that the dynamic changes in brain FC can better explain the underlying pathophysiology of ADHD such as deficits in visual cognition, attention, memory and emotion processing, and cognitive and motor control., (© 2021 IOP Publishing Ltd.)

Growing evidence indicates that disruptions in the brain's functional connectivity play an important role in the pathophysiology of ADHD. The present study investigates alterations in resting-state EEG source connectivity and rich-club organization in children with inattentive (ADHD I ) and combined (ADHD C ) ADHD compared with typically developing children (TD) under the eyes-closed condition. EEG source analysis was performed by eLORETA in different frequency bands. The lagged phase synchronization (LPS) and graph theoretical metrics were then used to examine group differences in the topological properties and rich-club organization of functional networks. Compared with the TD children, the ADHD I children were characterized by a widespread significant decrease in delta and beta LPS, as well as increased theta and alpha LPS in the left frontal and right occipital regions. The ADHD C children displayed significant increases in LPS in the central, temporal and posterior areas. Both ADHD groups showed small-worldness properties with significant increases and decreases in the network degree in the θ and β bands, respectively. Both subtypes also displayed reduced levels of network segregation. Group differences in rich-club distribution were found in the central and posterior areas. Our findings suggest that resting-state EEG source connectivity analysis can better characterize alterations in the rich-club organization of functional brain networks in ADHD patients.

The majority of network studies of human brain structural connectivity are based on single-shell diffusion-weighted imaging (DWI) data. Recent advances in imaging hardware and software capabilities have made it possible to acquire multishell (b-values) high-quality data required for better characterization of white-matter crossing-fiber microstructures. The purpose of this study was to investigate the extent to which brain structural organization and network topology are affected by the choice of diffusion magnetic resonance imaging (MRI) acquisition strategy and parcellation scale. We performed graph-theoretical network analysis using DWI data from 35 Human Connectome Project subjects. Our study compared four single-shell (b = 1000, 3000, 5000, 10,000 s/mm 2 ) and multishell sampling schemes and six parcellation scales (68, 200, 400, 600, 800, 1000 nodes) using five graph metrics, including small-worldness, clustering coefficient, characteristic path length, modularity and global efficiency. Rich-club analysis was also performed to explore the rich-club organization of brain structural networks. Our results showed that the parcellation scale and imaging protocol have significant effects on the network attributes, with the parcellation scale having a substantially larger effect. Regardless of the parcellation scale, the brain structural networks exhibited a rich-club organization with similar cortical distributions across the parcellation scales involving at least 400 nodes. Compared to single b-value diffusion acquisitions, the deterministic tractography using multishell diffusion imaging data consisting of shells with b-values higher than 5000 s/mm 2 resulted in significantly improved fiber-tracking results at the locations where fiber bundles cross each other. Brain structural networks constructed using the multishell acquisition scheme including high b-values also exhibited significantly shorter characteristic path lengths, higher global efficiency and lower modularity. Our results showed that both parcellation scale and sampling protocol can significantly impact the rich-club organization of brain structural networks. Therefore, caution should be taken concerning the reproducibility of connectivity results with regard to the parcellation scale and sampling scheme.

The tumor proliferation, which is correlated with tumor grade, is a crucial biomarker indicative of breast cancer patients' prognosis. The most commonly used method in predicting tumor proliferation speed is the counting of mitotic figures in Hematoxylin and Eosin (H&E) histological slides. Manual mitosis counting is known to suffer from reproducibility problems. This paper presents a fully automated system for tumor proliferation prediction from whole slide images via mitosis counting. First, by considering the epithelial tissue as mitosis activity regions, we build a deep-learning-based region of interest detection method to select the high mitosis activity regions from whole slide images. Second, we learned a set of deep neural networks to detect mitosis detection from selected areas. The proposed mitosis detection system is designed to effectively overcome the mitosis detection challenges by two novel deep preprocessing and two-step hard negative mining approaches. Third, we trained a Support Vector Machine (SVM) classifier to predict the final tumor proliferation score. The proposed method was evaluated on the dataset of the Tumor Proliferation Assessment Challenge (TUPAC16) and achieved a 73.81 % F-measure and 0.612 weighted kappa score, respectively, outperforming all previous approaches significantly. Experimental results demonstrate that the proposed system considerably improves the tumor proliferation prediction accuracy and provides a reliable automated tool to support health care make-decisions., (Copyright © 2021 Elsevier B.V. All rights reserved.)

Purpose: Multi-echo spin-echo sequence is commonly used for T 2 mapping. The estimated values using conventional exponential fit, however, are hampered by stimulated and indirect echoes leading to overestimation of T 2 . Here, we present fast analysis of multi-echo spin-echo (FAMESE) as a novel approach to decrease the complexity of the search space, which leads to accelerated measurement of T 2 ., Methods: We developed FAMESE based on mathematical analysis of the Bloch equations in which the search space dimension decreased to only one. Then, we tested it in both phantom and human brain. Bland-Altman plot was used to assess the agreement between the estimated T 2 values from FAMESE and the ones estimated from single-echo spin-echo sequence. The reliability of FAMESE was assessed by intraclass correlation coefficients. In addition, we investigated the noise stability of the method in synthetic and experimental data., Results: In both phantom and healthy participants, FAMESE provided accelerated and SNR-resistant T 2 maps. The FAMESE had a very good agreement with the single-echo spin echo for the whole range of T 2 values. The intraclass correlation coefficient values for FAMESE were excellent (ie, 0.9998 and 0.9860 < intraclass correlation coefficient < 0.9942 for the phantom and humans, respectively)., Conclusion: Our developed method FAMESE could be considered as a candidate for rapid T 2 mapping with a clinically feasible scan time., (© 2020 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.)

Objective: This study investigated age-dependent and subtype-related alterations in electroencephalography (EEG) power spectra and current source densities (CSD) in children with attention deficit and hyperactivity disorder (ADHD)., Methods: We performed spectral and cortical source (exact low-resolution electromagnetic tomography, eLORETA) analyses using resting state EEG recordings from 40 children (8-16 years) with combined and inattentive subtypes of ADHD and 41 age-matched healthy controls (HC). Group differences in EEG spectra and CSD were investigated at each scalp location, voxel and cortical region in delta, theta, alpha and beta bands. We also explored associations between topographic changes in EEG power and CSD and age., Results: Compared to healthy controls, combined ADHD subtype was characterized with significantly increased diffuse theta/beta power ratios (TBR) with a widespread decrease in beta CSD. Inattentive ADHD subtype presented increased TBR in all brain regions except in posterior areas with a global increase in theta source power. In both ADHD and HC, older age groups showed significantly lower delta source power and TBR and higher alpha and beta source power than younger age groups. Compared to HC, ADHD was characterized with increases in theta fronto-central and temporal source power with increasing age., Conclusions: Our results confirm that TBR can be used as a neurophysiological biomarker to differentiate ADHD from healthy children at both the source and sensor levels., Significance: Our findings emphasize the importance of performing the source imaging analysis in order to better characterize age-related changes in resting-state EEG activity in ADHD and controls., Competing Interests: Disclosures None of the authors have potential conflicts of interest to be disclosed., (Copyright © 2020 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.)

Objective: Automatic sleep stage scoring is of great importance for investigating sleep architecture during infancy. In this work, we introduce a novel multichannel approach based on deep learning networks and hidden Markov models (HMM) to improve the accuracy of sleep stage classification in term neonates., Approach: The classification performance was evaluated on quiet sleep (QS) and active sleep (AS) stages, each with two sub-states, using multichannel EEG data recorded from sixteen neonates with postmenstrual age of 38-40 weeks. A comprehensive set of linear and nonlinear features were extracted from thirty-second EEG segments. The feature space dimensionality was then reduced by using an evolutionary feature selection method called MGCACO (Modified Graph Clustering Ant Colony Optimization) based on the relevance and redundancy analysis. A bi-directional long-short time memory (BiLSTM) network was trained for sleep stage classification. The number of channels was optimized using the sequential forward selection method to reduce the spatial space. Finally, an HMM-based postprocessing stage was used to reduce false positives by incorporating the knowledge of transition probabilities between stages into the classification process. The method performance was evaluated using the K-fold (KFCV) and leave-one-out cross-validation (LOOCV) strategies., Main Results: Using six-bipolar channels, our method achieved a mean kappa and an overall accuracy of 0.71-0.76 and 78.9%-82.4% using the KFCV and LOOCV strategies, respectively., Significance: The presented automatic sleep stage scoring method can be used to study the neurodevelopmental process and to diagnose brain abnormalities in term neonates.

Objective: Sleep stage scoring is essential for diagnosing sleep disorders. Visual scoring of sleep stages is very time-consuming and prone to human errors. In this work, we introduce an efficient approach to improve the accuracy of sleep stage scoring and classification for sleep analysis., Method: In this approach, a set of optimal features was first selected from a pool of features extracted from sleep EEG epochs by using a feature selection method based on the relevance and redundancy analysis. EEG segments were then classified using a random forest classifier. Finally, a Hidden Markov Model (HMM) was used to reduce false positives by incorporating knowledge of the temporal structure of transitions between sleep stages. We evaluated the proposed method using single-channel EEG signals from four public sleep EEG datasets scored according to R&K and AASM guidelines. We compared the performance of our method with existing methods using different cross validation strategies., Results: Using a leave-one-out validation strategy, our method achieved overall accuracies in the range of (79.4-87.4%) and (77.6-80.4%) with Kappa values in the range of 0.7-0.85 for six-stage (R&K) and five-stage (AASM) classification, respectively. Our method showed a reduction in overall accuracy up to 8% using the cross-dataset validation strategy in comparison with the subject cross-validation method., Comparison With Existing Method(s): Our method outperformed the existing methods for all multi-stage classification., Conclusions: The proposed single-channel method can be used for robust and reliable sleep stage scoring with high accuracy and relatively low complexity required for real time applications., (Copyright © 2019 Elsevier B.V. All rights reserved.)

Background: Spinal cord (SC) segmentation from magnetic resonance (MR) images can be used to study neurological disorders and facilitates group analysis. Variation of intensity inhomogeneity and small cross section of SC are difficulties that restrict automizing SC segmentation., New Methods: In this paper we present a method for accurate SC segmentation from MR images. The proposed morphological local global intensity fitting model (MLGIF) is based on region based morphological active contour model that utilizes local and global information. The local information is obtained using local morphology fitting and has been embedded into region based active contour to deal with images intensity inhomogeneity and variable contrast levels between SC and the cerebrospinal fluid. The contour evolution has been performed using successive application of a set of morphological operators., Results: The proposed method has been validated on 28 T1-weighted and 29 T2-weighted MR images and simulated MR images with different noise levels. Assessment of the results shows the accuracy of the proposed method for SC segmentation., Comparison to Existing Method(s): The proposed MLGIF method was comparable with existing SC segmentation methods. Between segmented images and corresponding ground truth images, the mean DICE similarity coefficient, mean conformity coefficient and mean Hausdorff distance were 0.90 (092), 0.8 (0.83) and 0.85 mm (0.70 mm), respectively, for T1(T2)-weighted images., Conclusion: The MLGIF model was proposed to achieve a robust method to deal with intensity inhomogeneity and lack of contrast between SC and surrounding tissues. Moreover, accuracy and less sensitivity to initial curve were seen., (Copyright © 2018 Elsevier B.V. All rights reserved.)

This paper proposes an automatic and robust decision support system for accurate acute leukemia diagnosis from blood microscopic images. It is a challenging issue to segment leukocytes under uneven imaging conditions since features of microscopic leukocyte images change in different laboratories. Therefore, this paper introduces an automatic robust method to segment leukocyte from blood microscopic images. The proposed robust segmentation technique was designed based on the fact that if background and erythrocytes could be removed from the blood microscopic image, the remainder area will indicate leukocyte candidate regions. A new set of features based on hematologist visual criteria for the recognition of malignant leukocytes in blood samples comprising shape, color, and LBP-based texture features are extracted. Two new ensemble classifiers are proposed for healthy and malignant leukocytes classification which each of them is highly effective in different levels of analysis. Experimental results demonstrate that the proposed approach effectively segments leukocytes from various types of blood microscopic images. The proposed method performs better than other available methods in terms of robustness and accuracy. The final accuracy rate achieved by the proposed method is 98.10% in cell level. To the best of our knowledge, the image level test for acute lymphoblastic leukemia (ALL) recognition was performed on the proposed system for the first time that achieves the best accuracy rate of 89.81%.

Here, a two-phase search strategy is proposed to identify the biomarkers in gene expression data set for the prostate cancer diagnosis. A statistical filtering method is initially employed to remove the noisiest data. In the first phase of the search strategy, a multi-objective optimisation based on the binary particle swarm optimisation algorithm tuned by a chaotic method is proposed to select the optimal subset of genes with the minimum number of genes and the maximum classification accuracy. Finally, in the second phase of the search strategy, the cache-based modification of the sequential forward floating selection algorithm is used to find the most discriminant genes from the optimal subset of genes selected in the first phase. The results of applying the proposed algorithm on the available challenging prostate cancer data set demonstrate that the proposed algorithm can perfectly identify the informative genes such that the classification accuracy, sensitivity, and specificity of 100% are achieved with only nine biomarkers., (© 2020 The Institution of Engineering and Technology.)

Background: With advances in medical imaging systems, digital dermoscopy has become one of the major imaging modalities in the analysis of skin lesions. Thus, automated segmentation or border detection has a great impact on the subsequent steps of skin cancer computer-aided diagnosis using demoscopy images. Since dermoscopy images suffer from artifacts such as shading and hair, there is a need for automated and robust artifact attenuation removal and lesion border detection., Methods: method for segmentation of dermoscopy images is proposed based on active contour. To this end, at first, a simple method for hair pixels is restored and a new scheme for shading detection is proposed. Then, particle swarm optimization (PSO) algorithm is applied to select the best coefficients for converting RGB to gray level. The obtained gray level image is then used as input for multi Otsu method which provides initial contour for border detection using active contour. Finally, Chan and Vese active contour is used for final lesion border detection., Results: The method is tested on a total of 145 dermoscopic images: 79 cases with benign lesion and 75 cases with melanoma lesion. Mean accuracy, sensitivity and specificity were obtained 94%, 78.5% and 99%, respectively., Conclusion: Results reveal that the proposed method segments the lesion from dermoscopy images accurately., Competing Interests: Conflict of interests: None.

Based on the Nottingham criteria, the number of mitosis cells in histopathological slides is an important factor in diagnosis and grading of breast cancer. For manual grading of mitosis cells, histopathology slides of the tissue are examined by pathologists at 40× magnification for each patient. This task is very difficult and time-consuming even for experts. In this paper, a fully automated method is presented for accurate detection of mitosis cells in histopathology slide images. First a method based on maximum-likelihood is employed for segmentation and extraction of mitosis cell. Then a novel Maximized Inter-class Weighted Mean (MIWM) method is proposed that aims at reducing the number of extracted non-mitosis candidates that results in reducing the false positive mitosis detection rate. Finally, segmented candidates are classified into mitosis and non-mitosis classes by using a support vector machine (SVM) classifier. Experimental results demonstrate a significant improvement in accuracy of mitosis cells detection in different grades of breast cancer histopathological images.

Fatty liver disease is progressive and may not cause any symptoms at early stages. This disease is potentially fatal and can cause liver cancer in severe stages. Therefore, diagnosing and staging fatty liver disease in early stages is necessary. In this paper, a novel method is presented to classify normal and fatty liver, as well as discriminate three stages of fatty liver in ultrasound images. This study is performed with 129 subjects including 28 normal, 47 steatosis, 42 fibrosis, and 12 cirrhosis images. The proposed approach uses back-scan conversion of ultrasound sector images and is based on a hierarchical classification. The proposed algorithm is performed in two parts. The first part selects the optimum regions of interest from the focal zone of the back-scan-converted ultrasound images. In the second part, discrimination between normal and fatty liver is performed and then steatosis, fibrosis, and cirrhosis are classified in a hierarchical basis. The wavelet packet transform and gray-level co-occurrence matrix are used to obtain a number of statistical features. A support vector machine classifier is used to discriminate between normal and fatty liver, and stage fatty cases. The results of the proposed scheme clearly illustrate the efficiency of this system with overall accuracy of 94.91% and also specificity of more than 90%.

Ultrasound imaging is a popular and noninvasive tool frequently used in the diagnoses of liver diseases. A system to characterize normal, fatty and heterogeneous liver, using textural analysis of liver Ultrasound images, is proposed in this paper. The proposed approach is able to select the optimum regions of interest of the liver images. These optimum regions of interests are analyzed by two level wavelet packet transform to extract some statistical features, namely, median, standard deviation, and interquartile range. Discrimination between heterogeneous, fatty and normal livers is performed in a hierarchical approach in the classification stage. This stage, first, classifies focal and diffused livers and then distinguishes between fatty and normal ones. Support vector machine and k-nearest neighbor classifiers have been used to classify the images into three groups, and their performance is compared. The Support vector machine classifier outperformed the compared classifier, attaining an overall accuracy of 97.9%, with a sensitivity of 100%, 100% and 95.1% for the heterogeneous, fatty and normal class, respectively. The Acc obtained by the proposed computer-aided diagnostic system is quite promising and suggests that the proposed system can be used in a clinical environment to support radiologists and experts in liver diseases interpretation.

Histopathology slides are one of the most applicable resources for pathology studies. As observation of these kinds of slides even by skillful pathologists is a tedious and time-consuming activity, computerizing this procedure aids the experts to have faster analysis with more case studies per day. In this paper, an automatic mitosis detection system (AMDS) for breast cancer histopathological slide images is proposed. In the proposed AMDS, the general phases of an automatic image based analyzer are considered and in each phase, some special innovations are employed. In the pre-processing step to segment the input digital histopathology images more precisely, 2D anisotropic diffusion filters are applied to them. In the training segmentation phase, the histopathological slide images are segmented based on RGB contents of their pixels using maximum likelihood estimation. Then, the mitosis and non-mitosis candidates are processed and hence that their completed local binary patterns are extracted object-wise. For the classification phase, two subsequently non-linear support vector machine classifiers are trained pixel-wise and object-wise, respectively. For the evaluation of the proposed AMDS, some object and region based measures are employed. Having computed the evaluation criteria, our proposed method performs more efficient according to f-measure metric (70.94% for Aperio XT scanner images and 70.11% for Hamamatsu images) than the methods proposed by other participants at Mitos-ICPR2012 contest in breast cancer histopathological images. The experimental results show the higher performance of the proposed AMDS compared with other competitive systems proposed in Mitos-ICPR2012 contest.

In this paper, we present a new semi-automatic brain tissue segmentation method based on a hybrid hierarchical approach that combines a brain atlas as a priori information and a least-square support vector machine (LS-SVM). The method consists of three steps. In the first two steps, the skull is removed and the cerebrospinal fluid (CSF) is extracted. These two steps are performed using the toolbox FMRIB's automated segmentation tool integrated in the FSL software (FSL-FAST) developed in Oxford Centre for functional MRI of the brain (FMRIB). Then, in the third step, the LS-SVM is used to segment grey matter (GM) and white matter (WM). The training samples for LS-SVM are selected from the registered brain atlas. The voxel intensities and spatial positions are selected as the two feature groups for training and test. SVM as a powerful discriminator is able to handle nonlinear classification problems; however, it cannot provide posterior probability. Thus, we use a sigmoid function to map the SVM output into probabilities. The proposed method is used to segment CSF, GM and WM from the simulated magnetic resonance imaging (MRI) using Brainweb MRI simulator and real data provided by Internet Brain Segmentation Repository. The semi-automatically segmented brain tissues were evaluated by comparing to the corresponding ground truth. The Dice and Jaccard similarity coefficients, sensitivity and specificity were calculated for the quantitative validation of the results. The quantitative results show that the proposed method segments brain tissues accurately with respect to corresponding ground truth.

It is well established that the two hemispheres of the human brain exhibit a certain degree of asymmetry. Postmortem studies of developing brains of pre- and postpartum infants have shown that already in this early stage of development Heschl gyrus, planum temporale and superior temporal sulcus (STS) exhibit pronounced asymmetry. Advances in acquisition and computational evaluation of high-resolution magnetic resonance images provide enhanced tools for noninvasive studies of brain asymmetry in newborns. Until now most atlases used for image processing contain themselves asymmetry and may thus introduce and/or increase asymmetry already contained in the original data of brain structural or functional images. So, it is preferable to avoid the application of these asymmetric atlases. Thus, in this paper we present our framework to create a symmetric brain atlas from a group of newborns aged between 39 and 42 weeks after gestation. The resulting atlas demonstrates no difference between its original and its flipped version as should be the case for an asymmetric atlas. Consequently, the resulting symmetric atlas can be used for applications such as analysis of development of brain asymmetry in the context of language development.

Noise and intensity non-uniformity are causing major difficulties in magnetic resonance (MR) image segmentation. This paper introduces a variational level set approach for simultaneous MR image segmentation and intensity non-uniformity correction. The proposed energy functional is based on local Gaussian intensity fitting with local means and variances. Furthermore, the proposed model utilizes Markov random fields to model the spatial correlation between neighboring pixels/voxels. The improvements achieved with our method are demonstrated by brain segmentation experiments with simulated and real magnetic resonance images with different noise and bias level. In particular, it is superior in term of accuracy as compared to LGDF and FSL-FAST methods., (Copyright © 2012 Elsevier B.V. All rights reserved.)

In this paper, a novel fuzzy scheme for medical X-ray image classification is presented. In this method, each image is partitioned into 25 overlapping subimages and then, we extracted the shape-texture features from shape and directional information of each subimage. In the classification step, we apply a fuzzy membership to each subimage considering the Euclidean distance between feature vector of each subimage and average of feature vectors of training subimages. At last, a hard classification of the test image can be obtained by performing a max operation on the summation of fuzzy memberships. The proposed method is evaluated for image classification on 2655 radiographic images from IRMA dataset with 300 training samples and 2355 test samples. Classification accuracy rates obtained by fuzzy classifier are higher than that of obtained by multilayer perceptron or even SVM classifier.

This paper represents a new region-based active contour model that can be used to segment images with intensity non-uniformity and high-level noise. The main idea of our proposed method is to use Gaussian distributions with different means and variances with incorporation of intensity non-uniformity model for image segmentation. In order to integrate the spatial information between neighboring pixels in our proposed method, we use Markov Random Field. Our experiments on synthetic images and cerebral magnetic resonance images show the advantages of the proposed method over state-of-art methods, i.e. local Gaussian distribution fitting.