Displaying publications 1 - 20 of 133 in total

Abstract:
Sort:
  1. Shahab M, Iqbal MW, Ahmad A, Alshabrmi FM, Wei DQ, Khan A, et al.
    Comput Biol Med, 2024 Mar;170:108056.
    PMID: 38301512 DOI: 10.1016/j.compbiomed.2024.108056
    The Nipah virus (NPV) is a highly lethal virus, known for its significant fatality rate. The virus initially originated in Malaysia in 1998 and later led to outbreaks in nearby countries such as Bangladesh, Singapore, and India. Currently, there are no specific vaccines available for this virus. The current work employed the reverse vaccinology method to conduct a comprehensive analysis of the entire proteome of the NPV virus. The aim was to identify and choose the most promising antigenic proteins that could serve as potential candidates for vaccine development. We have also designed B and T cell epitopes-based vaccine candidate using immunoinformatics approach. We have identified a total of 5 novel Cytotoxic T Lymphocytes (CTL), 5 Helper T Lymphocytes (HTL), and 6 linear B-cell potential antigenic epitopes which are novel and can be used for further vaccine development against Nipah virus. Then we performed the physicochemical properties, antigenic, immunogenic and allergenicity prediction of the designed vaccine candidate against NPV. Further, Computational analysis indicated that these epitopes possessed highly antigenic properties and were capable of interacting with immune receptors. The designed vaccine were then docked with the human immune receptors, namely TLR-2 and TLR-4 showed robust interaction with the immune receptor. Molecular dynamics simulations demonstrated robust binding and good dynamics. After numerous dosages at varied intervals, computational immune response modeling showed that the immunogenic construct might elicit a significant immune response. In conclusion, the immunogenic construct shows promise in providing protection against NPV, However, further experimental validation is required before moving to clinical trials.
  2. Cheng J, Wang H, Wei S, Mei J, Liu F, Zhang G
    Comput Biol Med, 2024 Mar;170:108000.
    PMID: 38232453 DOI: 10.1016/j.compbiomed.2024.108000
    Alzheimer's disease (AD) is a neurodegenerative disease characterized by various pathological changes. Utilizing multimodal data from Fluorodeoxyglucose positron emission tomography(FDG-PET) and Magnetic Resonance Imaging(MRI) of the brain can offer comprehensive information about the lesions from different perspectives and improve the accuracy of prediction. However, there are significant differences in the feature space of multimodal data. Commonly, the simple concatenation of multimodal features can cause the model to struggle in distinguishing and utilizing the complementary information between different modalities, thus affecting the accuracy of predictions. Therefore, we propose an AD prediction model based on de-correlation constraint and multi-modal feature interaction. This model consists of the following three parts: (1) The feature extractor employs residual connections and attention mechanisms to capture distinctive lesion features from FDG-PET and MRI data within their respective modalities. (2) The de-correlation constraint function enhances the model's capacity to extract complementary information from different modalities by reducing the feature similarity between them. (3) The mutual attention feature fusion module interacts with the features within and between modalities to enhance the modal-specific features and adaptively adjust the weights of these features based on information from other modalities. The experimental results on ADNI database demonstrate that the proposed model achieves a prediction accuracy of 86.79% for AD, MCI and NC, which is higher than the existing multi-modal AD prediction models.
  3. Chai LE, Loh SK, Low ST, Mohamad MS, Deris S, Zakaria Z
    Comput Biol Med, 2014 May;48:55-65.
    PMID: 24637147 DOI: 10.1016/j.compbiomed.2014.02.011
    Many biological research areas such as drug design require gene regulatory networks to provide clear insight and understanding of the cellular process in living cells. This is because interactions among the genes and their products play an important role in many molecular processes. A gene regulatory network can act as a blueprint for the researchers to observe the relationships among genes. Due to its importance, several computational approaches have been proposed to infer gene regulatory networks from gene expression data. In this review, six inference approaches are discussed: Boolean network, probabilistic Boolean network, ordinary differential equation, neural network, Bayesian network, and dynamic Bayesian network. These approaches are discussed in terms of introduction, methodology and recent applications of these approaches in gene regulatory network construction. These approaches are also compared in the discussion section. Furthermore, the strengths and weaknesses of these computational approaches are described.
  4. Roslan R, Othman RM, Shah ZA, Kasim S, Asmuni H, Taliba J, et al.
    Comput Biol Med, 2010 Jun;40(6):555-64.
    PMID: 20417930 DOI: 10.1016/j.compbiomed.2010.03.009
    Protein-protein interactions (PPIs) play a significant role in many crucial cellular operations such as metabolism, signaling and regulations. The computational methods for predicting PPIs have shown tremendous growth in recent years, but problem such as huge false positive rates has contributed to the lack of solid PPI information. We aimed at enhancing the overlap between computational predictions and experimental results in an effort to partially remove PPIs falsely predicted. The use of protein function predictor named PFP() that are based on shared interacting domain patterns is introduced in this study with the purpose of aiding the Gene Ontology Annotations (GOA). We used GOA and PFP() as agents in a filtering process to reduce false positive pairs in the computationally predicted PPI datasets. The functions predicted by PFP() were extracted from cross-species PPI data in order to assign novel functional annotations for the uncharacterized proteins and also as additional functions for those that are already characterized by the GO (Gene Ontology). The implementation of PFP() managed to increase the chances of finding matching function annotation for the first rule in the filtration process as much as 20%. To assess the capability of the proposed framework in filtering false PPIs, we applied it on the available S. cerevisiae PPIs and measured the performance in two aspects, the improvement made indicated as Signal-to-Noise Ratio (SNR) and the strength of improvement, respectively. The proposed filtering framework significantly achieved better performance than without it in both metrics.
  5. Kalsum HU, Shah ZA, Othman RM, Hassan R, Rahim SM, Asmuni H, et al.
    Comput Biol Med, 2009 Nov;39(11):1013-9.
    PMID: 19720371 DOI: 10.1016/j.compbiomed.2009.08.002
    Protein domains contain information about the prediction of protein structure, function, evolution and design since the protein sequence may contain several domains with different or the same copies of the protein domain. In this study, we proposed an algorithm named SplitSSI-SVM that works with the following steps. First, the training and testing datasets are generated to test the SplitSSI-SVM. Second, the protein sequence is split into subsequence based on order and disorder regions. The protein sequence that is more than 600 residues is split into subsequences to investigate the effectiveness of the protein domain prediction based on subsequence. Third, multiple sequence alignment is performed to predict the secondary structure using bidirectional recurrent neural networks (BRNN) where BRNN considers the interaction between amino acids. The information of about protein secondary structure is used to increase the protein domain boundaries signal. Lastly, support vector machines (SVM) are used to classify the protein domain into single-domain, two-domain and multiple-domain. The SplitSSI-SVM is developed to reduce misleading signal, lower protein domain signal caused by primary structure of protein sequence and to provide accurate classification of the protein domain. The performance of SplitSSI-SVM is evaluated using sensitivity and specificity on single-domain, two-domain and multiple-domain. The evaluation shows that the SplitSSI-SVM achieved better results compared with other protein domain predictors such as DOMpro, GlobPlot, Dompred-DPS, Mateo, Biozon, Armadillo, KemaDom, SBASE, HMMPfam and HMMSMART especially in two-domain and multiple-domain.
  6. Rajendra Acharya U, Faust O, Adib Kadri N, Suri JS, Yu W
    Comput Biol Med, 2013 Oct;43(10):1523-9.
    PMID: 24034744 DOI: 10.1016/j.compbiomed.2013.05.024
    Diabetes mellitus (DM) affects considerable number of people in the world and the number of cases is increasing every year. Due to a strong link to the genetic basis of the disease, it is extremely difficult to cure. However, it can be controlled to prevent severe consequences, such as organ damage. Therefore, diabetes diagnosis and monitoring of its treatment is very important. In this paper, we have proposed a non-invasive diagnosis support system for DM. The system determines whether or not diabetes is present by determining the cardiac health of a patient using heart rate variability (HRV) analysis. This analysis was based on nine nonlinear features namely: Approximate Entropy (ApEn), largest Lyapunov exponet (LLE), detrended fluctuation analysis (DFA) and recurrence quantification analysis (RQA). Clinically significant measures were used as input to classification algorithms, namely AdaBoost, decision tree (DT), fuzzy Sugeno classifier (FSC), k-nearest neighbor algorithm (k-NN), probabilistic neural network (PNN) and support vector machine (SVM). Ten-fold stratified cross-validation was used to select the best classifier. AdaBoost, with least squares (LS) as weak learner, performed better than the other classifiers, yielding an average accuracy of 90%, sensitivity of 92.5% and specificity of 88.7%.
  7. Acharya UR, Koh JEW, Hagiwara Y, Tan JH, Gertych A, Vijayananthan A, et al.
    Comput Biol Med, 2018 03 01;94:11-18.
    PMID: 29353161 DOI: 10.1016/j.compbiomed.2017.12.024
    Liver is the heaviest internal organ of the human body and performs many vital functions. Prolonged cirrhosis and fatty liver disease may lead to the formation of benign or malignant lesions in this organ, and an early and reliable evaluation of these conditions can improve treatment outcomes. Ultrasound imaging is a safe, non-invasive, and cost-effective way of diagnosing liver lesions. However, this technique has limited performance in determining the nature of the lesions. This study initiates a computer-aided diagnosis (CAD) system to aid radiologists in an objective and more reliable interpretation of ultrasound images of liver lesions. In this work, we have employed radon transform and bi-directional empirical mode decomposition (BEMD) to extract features from the focal liver lesions. After which, the extracted features were subjected to particle swarm optimization (PSO) technique for the selection of a set of optimized features for classification. Our automated CAD system can differentiate normal, malignant, and benign liver lesions using machine learning algorithms. It was trained using 78 normal, 26 benign and 36 malignant focal lesions of the liver. The accuracy, sensitivity, and specificity of lesion classification were 92.95%, 90.80%, and 97.44%, respectively. The proposed CAD system is fully automatic as no segmentation of region-of-interest (ROI) is required.
  8. Jain S, Seal A, Ojha A, Krejcar O, Bureš J, Tachecí I, et al.
    Comput Biol Med, 2020 12;127:104094.
    PMID: 33152668 DOI: 10.1016/j.compbiomed.2020.104094
    One of the most recent non-invasive technologies to examine the gastrointestinal tract is wireless capsule endoscopy (WCE). As there are thousands of endoscopic images in an 8-15 h long video, an evaluator has to pay constant attention for a relatively long time (60-120 min). Therefore the possibility of the presence of pathological findings in a few images (displayed for evaluation for a few seconds only) brings a significant risk of missing the pathology with all negative consequences for the patient. Hence, manually reviewing a video to identify abnormal images is not only a tedious and time consuming task that overwhelms human attention but also is error prone. In this paper, a method is proposed for the automatic detection of abnormal WCE images. The differential box counting method is used for the extraction of fractal dimension (FD) of WCE images and the random forest based ensemble classifier is used for the identification of abnormal frames. The FD is a well-known technique for extraction of features related to texture, smoothness, and roughness. In this paper, FDs are extracted from pixel-blocks of WCE images and are fed to the classifier for identification of images with abnormalities. To determine a suitable pixel block size for FD feature extraction, various sizes of blocks are considered and are fed into six frequently used classifiers separately, and the block size of 7×7 giving the best performance is empirically determined. Further, the selection of the random forest ensemble classifier is also done using the same empirical study. Performance of the proposed method is evaluated on two datasets containing WCE frames. Results demonstrate that the proposed method outperforms some of the state-of-the-art methods with AUC of 85% and 99% on Dataset-I and Dataset-II respectively.
  9. Zeb A, Ali SS, Azad AK, Safdar M, Anwar Z, Suleman M, et al.
    Comput Biol Med, 2021 06;133:104412.
    PMID: 33934066 DOI: 10.1016/j.compbiomed.2021.104412
    Campylobacter jejuni, gram-negative bacteria, is an infectious agent of foodborne disease-causing bloody diarrhea, abdominal pain, fever, Guillain-Barré syndrome (GBS) and Miller Fisher syndrome in humans. Campylobacter spp. with multidrug resistance to fluoroquinolones, tetracycline, and erythromycin are reported. Hence, an effective vaccine candidate would provide long-term immunity against C. jejuni infections. Thus, we used a subtractive proteomics pipeline to prioritize essential proteins, which impart a critical role in virulence, replication and survival. Five proteins, i.e. Single-stranded DNA-binding protein, UPF0324 membrane protein Cj0999c, DNA translocase FtsK, 50S ribosomal protein L22, and 50S ribosomal protein L1 were identified as virulent proteins and selected for vaccine designing. We reported that the multi-epitopes subunit vaccine based on CTL, HTL and B-cell epitopes combination possess strong antigenic properties and associates no allergenic reaction. Further investigation revealed that the vaccine interacts with the immune receptor (TLR-4) and triggered the release of primary and secondary immune factors. Moreover, the CAI and GC contents obtained through codon optimization were reported to be 0.93 and 53% that confirmed a high expression in the selected vector. The vaccine designed in this study needs further scientific consensus and will aid in managing C. jejuni infections.
  10. Tahir Ul Qamar M, Ahmad S, Khan A, Mirza MU, Ahmad S, Abro A, et al.
    Comput Biol Med, 2021 11;138:104929.
    PMID: 34655900 DOI: 10.1016/j.compbiomed.2021.104929
    Cholera is a severe small intestine bacterial disease caused by consumption of water and food contaminated with Vibrio cholera. The disease causes watery diarrhea leading to severe dehydration and even death if left untreated. In the past few decades, V. cholerae has emerged as multidrug-resistant enteric pathogen due to its rapid ability to adapt in detrimental environmental conditions. This research study aimed to design inhibitors of a master virulence gene expression regulator, HapR. HapR is critical in regulating the expression of several set of V. cholera virulence genes, quorum-sensing circuits and biofilm formation. A blind docking strategy was employed to infer the natural binding tendency of diverse phytochemicals extracted from medicinal plants by exposing the whole HapR structure to the screening library. Scoring function criteria was applied to prioritize molecules with strong binding affinity (binding energy 
  11. Khan A, Hussain S, Ahmad S, Suleman M, Bukhari I, Khan T, et al.
    Comput Biol Med, 2022 02;141:105163.
    PMID: 34979405 DOI: 10.1016/j.compbiomed.2021.105163
    The spike protein of SARS-CoV-2 and the host ACE2 receptor plays a vital role in the entry to the cell. Among which the hotspot residue 501 is continuously subjected to positive selection pressure and induces unusual virulence. Keeping in view the importance of the hot spot residue 501, we predicted the potentially emerging structural variants of 501 residue. We analyzed the binding pattern of wild type and mutants (Spike RBD) to the ACE2 receptor by deciphering variations in the amino acids' interaction networks by graph kernels along with evolutionary, network metrics, and energetic information. Our analysis revealed that N501I, N501T, and N501V increase the binding affinity and alter the intra and inter-residue bonding networks. The N501T has shown strong positive selection and fitness in other animals. Docking results and repeated simulations (three times) confirmed the structural stability and tighter binding of these three variants, correlated with the previous results following the global stability trend. Consequently, we reported three variants N501I, N501T, and N501V could worsen the situation further if they emerged. The relations between the viral fitness and binding affinity is a complicated game thus the emergence of high affinity mutations in the SARS-CoV-2 RBD brings up the question of whether or not positive selection favours these mutations or not?
  12. Mookiah MR, Acharya UR, Fujita H, Tan JH, Chua CK, Bhandary SV, et al.
    Comput Biol Med, 2015 Nov 1;66:295-315.
    PMID: 26453760 DOI: 10.1016/j.compbiomed.2015.09.012
    Diabetic Macular Edema (DME) is caused by accumulation of extracellular fluid from hyperpermeable capillaries within the macula. DME is one of the leading causes of blindness among Diabetes Mellitus (DM) patients. Early detection followed by laser photocoagulation can save the visual loss. This review discusses various imaging modalities viz. biomicroscopy, Fluorescein Angiography (FA), Optical Coherence Tomography (OCT) and colour fundus photographs used for diagnosis of DME. Various automated DME grading systems using retinal fundus images, associated retinal image processing techniques for fovea, exudate detection and segmentation are presented. We have also compared various imaging modalities and automated screening methods used for DME grading. The reviewed literature indicates that FA and OCT identify DME related changes accurately. FA is an invasive method, which uses fluorescein dye, and OCT is an expensive imaging method compared to fundus photographs. Moreover, using fundus images DME can be identified and automated. DME grading algorithms can be implemented for telescreening. Hence, fundus imaging based DME grading is more suitable and affordable method compared to biomicroscopy, FA, and OCT modalities.
  13. Mookiah MR, Acharya UR, Fujita H, Koh JE, Tan JH, Noronha K, et al.
    Comput Biol Med, 2015 Aug;63:208-18.
    PMID: 26093788 DOI: 10.1016/j.compbiomed.2015.05.019
    Age-related Macular Degeneration (AMD) is an irreversible and chronic medical condition characterized by drusen, Choroidal Neovascularization (CNV) and Geographic Atrophy (GA). AMD is one of the major causes of visual loss among elderly people. It is caused by the degeneration of cells in the macula which is responsible for central vision. AMD can be dry or wet type, however dry AMD is most common. It is classified into early, intermediate and late AMD. The early detection and treatment may help one to stop the progression of the disease. Automated AMD diagnosis may reduce the screening time of the clinicians. In this work, we have introduced LCP to characterize normal and AMD classes using fundus images. Linear Configuration Coefficients (CC) and Pattern Occurrence (PO) features are extracted from fundus images. These extracted features are ranked using p-value of the t-test and fed to various supervised classifiers viz. Decision Tree (DT), Nearest Neighbour (k-NN), Naive Bayes (NB), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM) to classify normal and AMD classes. The performance of the system is evaluated using both private (Kasturba Medical Hospital, Manipal, India) and public domain datasets viz. Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) using ten-fold cross validation. The proposed approach yielded best performance with a highest average accuracy of 97.78%, sensitivity of 98.00% and specificity of 97.50% for STARE dataset using 22 significant features. Hence, this system can be used as an aiding tool to the clinicians during mass eye screening programs to diagnose AMD.
  14. Koh JEW, Acharya UR, Hagiwara Y, Raghavendra U, Tan JH, Sree SV, et al.
    Comput Biol Med, 2017 05 01;84:89-97.
    PMID: 28351716 DOI: 10.1016/j.compbiomed.2017.03.008
    Vision is paramount to humans to lead an active personal and professional life. The prevalence of ocular diseases is rising, and diseases such as glaucoma, Diabetic Retinopathy (DR) and Age-related Macular Degeneration (AMD) are the leading causes of blindness in developed countries. Identifying these diseases in mass screening programmes is time-consuming, labor-intensive and the diagnosis can be subjective. The use of an automated computer aided diagnosis system will reduce the time taken for analysis and will also reduce the inter-observer subjective variabilities in image interpretation. In this work, we propose one such system for the automatic classification of normal from abnormal (DR, AMD, glaucoma) images. We had a total of 404 normal and 1082 abnormal fundus images in our database. As the first step, 2D-Continuous Wavelet Transform (CWT) decomposition on the fundus images of two classes was performed. Subsequently, energy features and various entropies namely Yager, Renyi, Kapoor, Shannon, and Fuzzy were extracted from the decomposed images. Then, adaptive synthetic sampling approach was applied to balance the normal and abnormal datasets. Next, the extracted features were ranked according to the significances using Particle Swarm Optimization (PSO). Thereupon, the ranked and selected features were used to train the random forest classifier using stratified 10-fold cross validation. Overall, the proposed system presented a performance rate of 92.48%, and a sensitivity and specificity of 89.37% and 95.58% respectively using 15 features. This novel system shows promise in detecting abnormal fundus images, and hence, could be a valuable adjunct eye health screening tool that could be employed in polyclinics, and thereby reduce the workload of specialists at hospitals.
  15. Rasheed W, Neoh YY, Bin Hamid NH, Reza F, Idris Z, Tang TB
    Comput Biol Med, 2017 10 01;89:573-583.
    PMID: 28551109 DOI: 10.1016/j.compbiomed.2017.05.005
    Functional neuroimaging modalities play an important role in deciding the diagnosis and course of treatment of neuronal dysfunction and degeneration. This article presents an analytical tool with visualization by exploiting the strengths of the MEG (magnetoencephalographic) neuroimaging technique. The tool automates MEG data import (in tSSS format), channel information extraction, time/frequency decomposition, and circular graph visualization (connectogram) for simple result inspection. For advanced users, the tool also provides magnitude squared coherence (MSC) values allowing personalized threshold levels, and the computation of default model from MEG data of control population. Default model obtained from healthy population data serves as a useful benchmark to diagnose and monitor neuronal recovery during treatment. The proposed tool further provides optional labels with international 10-10 system nomenclature in order to facilitate comparison studies with EEG (electroencephalography) sensor space. Potential applications in epilepsy and traumatic brain injury studies are also discussed.
  16. Masni-Azian, Tanaka M
    Comput Biol Med, 2018 07 01;98:26-38.
    PMID: 29758454 DOI: 10.1016/j.compbiomed.2018.05.010
    Intervertebral disc degeneration involves changes in its material properties that affect the mechanical functions of the spinal system. However, the alteration of the biomechanics of a spinal segment through specific material degradation in a specific region is poorly understood. In this study, the influence of the constitutive material degeneration of disc tissues on the mechanics of a lower lumbar spinal unit was examined using a three-dimensional nonlinear finite element model of the L4-L5 functional spinal unit. Different grades of disc degeneration were simulated by introducing a degeneration factor to the corresponding material properties to represent fibrous nucleus, increased fibre and ground substance laxity, increased fibre stiffness and total annular fracture along posterior and posterolateral regions. The model was loaded with an axial compression of 500 N and pure moments of up to 10 Nm to simulate extension, flexion, lateral bending and axial rotation. To validate the model, the spinal motion and intradiscal pressure of healthy and degenerated discs with existing in vitro data were compared. The disc with a fibrous nucleus and the presence of intradiscal pressure increase the spinal instability during flexion and axial rotation, and the absence of intradiscal pressure increases the spinal instability in all directions. Bulging displacement and shear strains in the disc with total fracture and ground substance laxity are high in all of the loading cases. Our study could provide useful information to enhance our understanding of the influence of each constitutive component of the intervertebral disc on the mechanics of the spinal segment.
  17. Sudarshan VK, Acharya UR, Oh SL, Adam M, Tan JH, Chua CK, et al.
    Comput Biol Med, 2017 04 01;83:48-58.
    PMID: 28231511 DOI: 10.1016/j.compbiomed.2017.01.019
    Identification of alarming features in the electrocardiogram (ECG) signal is extremely significant for the prediction of congestive heart failure (CHF). ECG signal analysis carried out using computer-aided techniques can speed up the diagnosis process and aid in the proper management of CHF patients. Therefore, in this work, dual tree complex wavelets transform (DTCWT)-based methodology is proposed for an automated identification of ECG signals exhibiting CHF from normal. In the experiment, we have performed a DTCWT on ECG segments of 2s duration up to six levels to obtain the coefficients. From these DTCWT coefficients, statistical features are extracted and ranked using Bhattacharyya, entropy, minimum redundancy maximum relevance (mRMR), receiver-operating characteristics (ROC), Wilcoxon, t-test and reliefF methods. Ranked features are subjected to k-nearest neighbor (KNN) and decision tree (DT) classifiers for automated differentiation of CHF and normal ECG signals. We have achieved 99.86% accuracy, 99.78% sensitivity and 99.94% specificity in the identification of CHF affected ECG signals using 45 features. The proposed method is able to detect CHF patients accurately using only 2s of ECG signal length and hence providing sufficient time for the clinicians to further investigate on the severity of CHF and treatments.
  18. Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A, et al.
    Comput Biol Med, 2017 10 01;89:389-396.
    PMID: 28869899 DOI: 10.1016/j.compbiomed.2017.08.022
    The electrocardiogram (ECG) is a standard test used to monitor the activity of the heart. Many cardiac abnormalities will be manifested in the ECG including arrhythmia which is a general term that refers to an abnormal heart rhythm. The basis of arrhythmia diagnosis is the identification of normal versus abnormal individual heart beats, and their correct classification into different diagnoses, based on ECG morphology. Heartbeats can be sub-divided into five categories namely non-ectopic, supraventricular ectopic, ventricular ectopic, fusion, and unknown beats. It is challenging and time-consuming to distinguish these heartbeats on ECG as these signals are typically corrupted by noise. We developed a 9-layer deep convolutional neural network (CNN) to automatically identify 5 different categories of heartbeats in ECG signals. Our experiment was conducted in original and noise attenuated sets of ECG signals derived from a publicly available database. This set was artificially augmented to even out the number of instances the 5 classes of heartbeats and filtered to remove high-frequency noise. The CNN was trained using the augmented data and achieved an accuracy of 94.03% and 93.47% in the diagnostic classification of heartbeats in original and noise free ECGs, respectively. When the CNN was trained with highly imbalanced data (original dataset), the accuracy of the CNN reduced to 89.07%% and 89.3% in noisy and noise-free ECGs. When properly trained, the proposed CNN model can serve as a tool for screening of ECG to quickly identify different types and frequency of arrhythmic heartbeats.
  19. Liew A, Lee CC, Lan BL, Tan M
    Comput Biol Med, 2021 09;136:104690.
    PMID: 34352452 DOI: 10.1016/j.compbiomed.2021.104690
    Convolutional neural networks (CNNs) have been used quite successfully for semantic segmentation of brain tumors. However, current CNNs and attention mechanisms are stochastic in nature and neglect the morphological indicators used by radiologists to manually annotate regions of interest. In this paper, we introduce a channel and spatial wise asymmetric attention (CASPIAN) by leveraging the inherent structure of tumors to detect regions of saliency. To demonstrate the efficacy of our proposed layer, we integrate this into a well-established convolutional neural network (CNN) architecture to achieve higher Dice scores, with less GPU resources. Also, we investigate the inclusion of auxiliary multiscale and multiplanar attention branches to increase the spatial context crucial in semantic segmentation tasks. The resulting architecture is the new CASPIANET++, which achieves Dice Scores of 91.19%, 87.6% and 81.03% for whole tumor, tumor core and enhancing tumor respectively. Furthermore, driven by the scarcity of brain tumor data, we investigate the Noisy Student method for segmentation tasks. Our new Noisy Student Curriculum Learning paradigm, which infuses noise incrementally to increase the complexity of the training images exposed to the network, further boosts the enhancing tumor region to 81.53%. Additional validation performed on the BraTS2020 data shows that the Noisy Student Curriculum Learning method works well without any additional training or finetuning.
  20. Than JCM, Saba L, Noor NM, Rijal OM, Kassim RM, Yunus A, et al.
    Comput Biol Med, 2017 10 01;89:197-211.
    PMID: 28825994 DOI: 10.1016/j.compbiomed.2017.08.014
    Lung disease risk stratification is important for both diagnosis and treatment planning, particularly in biopsies and radiation therapy. Manual lung disease risk stratification is challenging because of: (a) large lung data sizes, (b) inter- and intra-observer variability of the lung delineation and (c) lack of feature amalgamation during machine learning paradigm. This paper presents a two stage CADx cascaded system consisting of: (a) semi-automated lung delineation subsystem (LDS) for lung region extraction in CT slices followed by (b) morphology-based lung tissue characterization, thereby addressing the above shortcomings. LDS primarily uses entropy-based region extraction while ML-based lung characterization is mainly based on an amalgamation of directional transforms such as Riesz and Gabor along with texture-based features comprising of 100 greyscale features using the K-fold cross-validation protocol (K = 2, 3, 5 and 10). The lung database consisted of 96 patients: 15 normal and 81 diseased. We use five high resolution Computed Tomography (HRCT) levels representing different anatomy landmarks where disease is commonly seen. We demonstrate the amalgamated ML stratification accuracy of 99.53%, an increase of 2% against the conventional non-amalgamation ML system that uses alone Riesz-based feature embedded with feature selection based on feature strength. The robustness of the system was determined based on the reliability and stability that showed a reliability index of 0.99 and the deviation in risk stratification accuracies less than 5%. Our CADx system shows 10% better performance when compared against the mean of five other prominent studies available in the current literature covering over one decade.
Filters
Contact Us

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links