One of the most promising research areas in the healthcare industry and the scientific community is focusing on the AI-based applications for real medical challenges such as the building of computer-aided diagnosis (CAD) systems for breast cancer. Transfer learning is one of the recent emerging AI-based techniques that allow rapid learning progress and improve medical imaging diagnosis performance. Although deep learning classification for breast cancer has been widely covered, certain obstacles still remain to investigate the independency among the extracted high-level deep features. This work tackles two challenges that still exist when designing effective CAD systems for breast lesion classification from mammograms. The first challenge is to enrich the input information of the deep learning models by generating pseudo-colored images instead of only using the input original grayscale images. To achieve this goal two different image preprocessing techniques are parallel used: contrast-limited adaptive histogram equalization (CLAHE) and Pixel-wise intensity adjustment. The original image is preserved in the first channel, while the other two channels receive the processed images, respectively. The generated three-channel pseudo-colored images are fed directly into the input layer of the backbone CNNs to generate more powerful high-level deep features. The second challenge is to overcome the multicollinearity problem that occurs among the high correlated deep features generated from deep learning models. A new hybrid processing technique based on Logistic Regression (LR) as well as Principal Components Analysis (PCA) is presented and called LR-PCA. Such a process helps to select the significant principal components (PCs) to further use them for the classification purpose. The proposed CAD system has been examined using two different public benchmark datasets which are INbreast and mini-MAIS. The proposed CAD system could achieve the highest performance accuracies of 98.60% and 98.80% using INbreast and mini-MAIS datasets, respectively. Such a CAD system seems to be useful and reliable for breast cancer diagnosis.
Novel Coronavirus Disease 2019 (COVID-19) is a new pandemic that appeared at the end of March 2019 in Wuhan city, China, which affected millions worldwide. COVID-19 is caused by the novel severe acute respiratory syndrome coronavirus 2 (SARSCoV-2) epidemic. Also, several viral epidemics have been listed in the last two decades, like the middle east respiratory syndrome coronavirus (MERSCoV) and the severe acute respiratory syndrome coronavirus 1 (SARSCoV-1), which cause MERS, and SARS diseases, respectively. Detection of these viral epidemics is a difficult issue because of their genetic similarity. In this paper, an effective automated system was developed to classify these viral epidemics using their complete genomic sequences via the genomic image processing techniques to facilitate the diagnosis and increase the detection accuracy in a short time. Results achieved an overall accuracy of 100% using two classifiers: SVM and KNN. However, the KNN classifier shows a privilege over the SVM in the execution time performance.
Many attempts have been carried out to deal with missing values (MV) in microarrays data representing gene expressions. This is a problematic issue as many data analysis techniques are not robust to missing data. Most of the MV imputation methods currently being used have been evaluated only in terms of the similarity between the original and imputed data. While imputed expression values themselves are not interesting, rather whether or not the imputed expression values are reliable to use in subsequent analysis is the major concern. This paper focuses on studying the impact of different MV imputation methods on the classification accuracy. The experimental work was first subjected to implementing three popular imputation methods, namely Singular Value Decomposition (SVD), weighted K-nearest neighbors (KNNimpute), and Zero replacement. The robustness of the three methods to the amount of missing data was then studied. The experiments were repeated for datasets with different missing rates (MR) over the range of 0-20% MR.In applying supervised two class classification we adopted a twofold approach, introducing all genes expressions to the classifiers as well as a subset of selected genes. The feature selection method used for gene selection is Fisher Discriminate Analysis (FDA), which improved noticeably the performance of the classifiers. The retained classifiers accuracies using imputed data after applying the three proposed imputation methods show slight variations over the specified range of MR. Thus, assessing that the three imputation methods in concern are robust.
The coronavirus disease 2019 (COVID-19) pandemic has been spreading quickly, threatening the public health system. Consequently, positive COVID-19 cases must be rapidly detected and treated. Automatic detection systems are essential for controlling the COVID-19 pandemic. Molecular techniques and medical imaging scans are among the most effective approaches for detecting COVID-19. Although these approaches are crucial for controlling the COVID-19 pandemic, they have certain limitations. This study proposes an effective hybrid approach based on genomic image processing (GIP) techniques to rapidly detect COVID-19 while avoiding the limitations of traditional detection techniques, using whole and partial genome sequences of human coronavirus (HCoV) diseases. In this work, the GIP techniques convert the genome sequences of HCoVs into genomic grayscale images using a genomic image mapping technique known as the frequency chaos game representation. Then, the pre-trained convolution neural network, AlexNet, is used to extract deep features from these images using the last convolution (conv5) and second fully-connected (fc7) layers. The most significant features were obtained by removing the redundant ones using the ReliefF and least absolute shrinkage and selection operator (LASSO) algorithms. These features are then passed to two classifiers: decision trees and k-nearest neighbors (KNN). Results showed that extracting deep features from the fc7 layer, selecting the most significant features using the LASSO algorithm, and executing the classification process using the KNN classifier is the best hybrid approach. The proposed hybrid deep learning approach detected COVID-19, among other HCoV diseases, with 99.71% accuracy, 99.78% specificity, and 99.62% sensitivity.
High-throughput microarrays contain a huge number of genes. Determining the relationships between all these genes is a time-consuming computation. In this paper, the authors provide a parallel algorithm for finding the Pearson’s correlation coefficient between genes measured in the Affymetrix microarrays. The main idea in the proposed algorithm, ForkJoinPcc, mimics the well-known parallel programming model: the fork–join model. The parallel MATLAB APIs have been employed and evaluated on shared or distributed multiprocessing systems. Two performance metrics—the processing and communication times—have been used to assess the performance of the ForkJoinPcc. The experimental results reveal that the ForkJoinPcc algorithm achieves a substantial speedup on the cluster platform of 62× compared with a 3.8× speedup on the multicore platform.
More than hundred algorithms were developed to infer Gene Regulatory Networks (GRN) describing relations between genes. GRN construction has been a field of interest to researchers since the beginning of the current century. Many competitions were held to encourage the development of GRN inference algorithms, such competitions offer synthetic data to enable the validation of proposed algorithms. A GRN is constructed from an adjacency matrix which contains relations between genes. The developers of many of the GRN inference algorithms set a threshold on the adjacency matrix to construct GRN based on high gene-gene relation weights. This threshold strategy was followed in previous studies to increase the accuracy of any algorithm but yet based on no well-known rule. A different perspective here is to compare different GRN inference algorithms without setting any threshold. Comparison in this work is among different GRN inference algorithms by implementing all algorithms with no threshold on values of adjacency matrices: Differential Equation methods (TSNI), Granger Causality, GP4GRN, GENIE3, NIMEFI (SVR), and PLSNET. Another comparison between different distance metric equations to create adjacency matrix is also studied in an attempt to construct GRN. GP4GRN and GENIE3 participate in producing best results for dream4 InSilico_Size10 while GENIE3 produce best results for all networks of dream4 InSilico_Size100. 654 I2M. Volume 17-n° 4/2018 Mé thodes d'é quation diffé rentielle (TSNI), causalité de Granger, GP4GRN, GENIE3, NIMEFI (SVR) et PLSNET. Une autre comparaison entre diffé rentes é quations mé triques de distance pour cré er une matrice d'adjacence est é galement é tudié e dans le but de construire un GRN. GP4GRN et GENIE3 contribuent à produire les meilleurs ré sultats pour dream4 InSilico_Size10, tandis que GENIE3 fournit les meilleurs ré sultats pour tous les ré seaux de dream4 InSilico_Size100.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.