Multi-class Classification Accuracy Research Articles

Scoring of swine lung images: a comparison between a computer vision system and human evaluators

Cranioventral pulmonary consolidation (CVPC) is a common lesion observed in the lungs of slaughtered pigs, often associated with Mycoplasma (M.) hyopneumoniae infection. There is a need to implement simple, fast, and valid CVPC scoring methods. Therefore, this study aimed to compare CVPC scores provided by a computer vision system (CVS; AI DIAGNOS) from lung images obtained at slaughter, with scores assigned by human evaluators. In addition, intra- and inter-evaluator variability were assessed and compared to intra-CVS variability. A total of 1050 dorsal view images of swine lungs were analyzed. Total lung lesion score, lesion score per lung lobe, and percentage of affected lung area were employed as outcomes for the evaluation. The CVS showed moderate accuracy (62–71%) in discriminating between non-lesioned and lesioned lung lobes in all but the diaphragmatic lobes. A low multiclass classification accuracy at the lung lobe level (24–36%) was observed. A moderate to high inter-evaluator variability was noticed depending on the lung lobe, as shown by the intraclass correlation coefficient (ICC: 0.29–0.6). The intra-evaluator variability was low and similar among the different outcomes and lung lobes, although the observed ICC slightly differed among evaluators. In contrast, the CVS scoring was identical per lobe per image. The results of this study suggest that the CVS AI DIAGNOS could be used as an alternative to the manual scoring of CVPC during slaughter inspections due to its accuracy in binary classification and its perfect consistency in the scoring.

Deep Learning Models for Automatic Classification of Anatomic Location in Abdominopelvic Digital Subtraction Angiography.

To explore the information in routine digital subtraction angiography (DSA) and evaluate deep learning algorithms for automated identification of anatomic location in DSA sequences. DSA of the abdominal aorta, celiac, superior mesenteric, inferior mesenteric, and bilateral external iliac arteries was labeled with the anatomic location from retrospectively collected endovascular procedures performed between 2010 and 2020 at a tertiary care medical center. "Key" images within each sequence demonstrating the parent vessel and the first bifurcation were additionally labeled. Mode models aggregating single image predictions, trained with the full or "key" datasets, and a multiple instance learning (MIL) model were developed for location classification of the DSA sequences. Model performance was evaluated with a primary endpoint of multiclass classification accuracy and compared by McNemar's test. A total of 819 unique angiographic sequences from 205 patients and 276 procedures were included in the training, validation, and testing data and split into partitions at the patient level to preclude data leakage. The data demonstrate substantial information sparsity as a minority of the images were designated as "key" with sufficient information for localization by a domain expert. A Mode model, trained and tested with "key" images, demonstrated an overall multiclass classification accuracy of 0.975 (95% CI 0.941-1). A MIL model, trained and tested with all data, demonstrated an overall multiclass classification accuracy of 0.966 (95% CI 0.932-0.992). Both the Mode model with "key" images (p < 0.001) and MIL model (p < 0.001) significantly outperformed a Mode model trained and tested with the full dataset. The MIL model additionally automatically identified a set of top-5 images with an average overlap of 92.5% to manually labelled "key" images. Deep learning algorithms can identify anatomic locations in abdominopelvic DSA with high fidelity using manual or automatic methods to manage information sparsity.

Utilizing a Wireless Radar Framework in Combination With Deep Learning Approaches to Evaluate Obstructive Sleep Apnea Severity in Home-Setting Environments.

Common examinations for diagnosing obstructive sleep apnea (OSA) are polysomnography (PSG) and home sleep apnea testing (HSAT). However, both PSG and HSAT require that sensors be attached to a subject, which may disturb their sleep and affect the results. Hence, in this study, we aimed to verify a wireless radar framework combined with deep learning techniques to screen for the risk of OSA in home-based environments. This study prospectively collected home-based sleep parameters from 80 participants over 147 nights using both HSAT and a 24-GHz wireless radar framework. The proposed framework, using hybrid models (ie, deep neural decision trees), identified respiratory events by analyzing continuous-wave signals indicative of breathing patterns. Analyses were performed to examine correlations and agreement of the apnea-hypopnea index (AHI) with results obtained through HSAT and the radar-based respiratory disturbance index based on the time in bed from HSAT (bRDITIB). Additionally, Youden's index was used to establish cutoff thresholds for the bRDITIB, followed by multiclass classification and outcome comparisons. A strong correlation (ρ = 0.87) and high agreement (93.88% within the 95% confidence interval; 138/147) between the AHI and bRDITIB were identified. The moderate-to-severe OSA model achieved 83.67% accuracy (with a bRDITIB cutoff of 21.19 events/h), and the severe OSA model demonstrated 93.21% accuracy (with a bRDITIB cutoff of 28.14 events/h). The average accuracy of multiclass classification using these thresholds was 78.23%. The proposed framework, with its cutoff thresholds, has the potential to be applied in home settings as a surrogate for HSAT, offering acceptable accuracy in screening for OSA without the interference of attached sensors. However, further optimization and verification of the radar-based total sleep time function are necessary for independent application.

Innovative Telecom Fraud Detection: A New Dataset and an Advanced Model with RoBERTa and Dual Loss Functions

Telecom fraud has emerged as one of the most pressing challenges in the criminal field. With advancements in artificial intelligence, telecom fraud texts have become increasingly covert and deceptive. Existing prevention methods, such as mobile number tracking, detection, and traditional machine-learning-based text recognition, struggle in terms of their real-time performance in identifying telecom fraud. Additionally, the scarcity of Chinese telecom fraud text data has limited research in this area. In this paper, we propose a telecom fraud text detection model, RoBERTa-MHARC, which combines RoBERTa with a multi-head attention mechanism and residual connections. First, the model selects data categories from the CCL2023 telecom fraud dataset as basic samples and merges them with collected telecom fraud text data, creating a five-category dataset covering impersonation of customer service, impersonation of leadership acquaintances, loans, public security fraud, and normal text. During training, the model integrates a multi-head attention mechanism and enhances its training efficiency through residual connections. Finally, the model improves its multi-class classification accuracy by incorporating an inconsistency loss function alongside the cross-entropy loss. The experimental results demonstrate that our model performs well on multiple benchmark datasets, achieving an F1 score of 97.65 on the FBS dataset, 98.10 on our own dataset, and 93.69 on the news dataset.

Logistic Regression Model to Personality Type Prediction Based on the Myers–Briggs Type Indicator

The Myers-Briggs Type Indicator (MBTI) is a widely-used tool in psychology for determining personality types, playing a crucial role in fields like team building, communication, and personalized marketing. Despite its popularity, accurately classifying MBTI types using machine learning remains a significant challenge. This study focuses on addressing this challenge by exploring the effectiveness of logistic regression in MBTI classification tasks. Two approaches are used: four-times binary classification and multi-class classification. The findings show that while logistic regression performs exceptionally well in binary classification tasks but the accuracy is not good in multi-class classification. Additionally, combining binary classification results yields an overall accuracy that is lower than the direct multi-class classification. These results highlight the limitations of logistic regression in multi-class tasks and suggest the necessity for more advanced models. Future research should focus on improving multi-class classification accuracy, potentially through more complex architectures or hybrid models combining binary and multi-class approaches.

Predicting invasion in early-stage ground-glass opacity pulmonary adenocarcinoma: a radiomics-based machine learning approach

BackgroundTo design a pulmonary ground-glass nodules (GGN) classification method based on computed tomography (CT) radiomics and machine learning for prediction of invasion in early-stage ground-glass opacity (GGO) pulmonary adenocarcinoma.MethodsThis retrospective study included pulmonary GGN patients who were histologically confirmed to have adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma cancer (IAC) from 2020 to 2023. CT images of all patients were automatically segmented and 107 radiomic features were obtained for each patient. Classification models were developed using random forest (RF) and cross-validation, including three one-versus-others models and one three-class model. For each model, features were ranked by normalized Gini importance, and a minimal subset was selected with a cumulative importance exceeding 0.9. These selected features were then used to train the final models. The models’ performance metrics, including area under the curve (AUC), accuracy, sensitivity, and specificity, were computed. AUC and accuracy were compared to determine the final optimal method.ResultsThe study comprised 193 patients (mean age 54 ± 11 years, 65 men), including 65 AIS, 54 MIA, and 74 IAC, divided into one training cohort (N = 154) and one test cohort (N = 39). The final three-class RF model outperformed three individual one-versus-others models in distinguishing each class from the other two. For the multiclass classification model, the AUC, accuracy, sensitivity, and specificity were 0.87, 0.79, 0.62, and 0.88 for AIS; 0.90, 0.79, 0.54, and 0.89 for MIA; and 0.87, 0.69, 0.73, and 0.67 for IAC, respectively.ConclusionsA radiomics-based multiclass RF model could effectively differentiate three types of pulmonary GGN, which enabled early diagnosis of GGO pulmonary adenocarcinoma.

Estimating the Workability of Concrete with a Stereovision Camera during Mixing.

The correct workability of concrete is an essential parameter for its placement and compaction. However, an absence of automatic and transparent measurement methods to estimate the workability of concrete hinders the adaptation from laborious traditional methods such as the slump test. In this paper, we developed a machine-learning framework for estimating the slump class of concrete in the mixer using a stereovision camera. Depth data from five different slump classes was transformed into Haralick texture features to train several machine-learning classifiers. The best-performing classifier achieved a multiclass classification accuracy of 0.8179 with the XGBoost algorithm. Furthermore, we found through statistical analysis that while the denoising of depth data has little effect on the accuracy, the feature extraction of mixer blades and the choice of region of interest significantly increase the accuracy and the efficiency of the classifiers. The proposed framework shows robust results, indicating that stereovision is a competitive solution to estimate the workability of concrete during concrete production.

Improving platelet-RNA-based diagnostics: a comparative analysis of machine learning models for cancer detection and multiclass classification.

Liquid biopsy demonstrates excellent potential in patient management by providing a minimally invasive and cost-effective approach to detecting and monitoring cancer, even at its early stages. Due to the complexity of liquid biopsy data, machine-learning techniques are increasingly gaining attention in sample analysis, especially for multidimensional data such as RNA expression profiles. Yet, there is no agreement in the community on which methods are the most effective or how to process the data. To circumvent this, we performed a large-scale study using various machine-learning techniques. First, we took a closer look at existing datasets and filtered out some patients to assert data collection quality. The final data collection included platelet RNA samples acquired from 1397 cancer patients (17 types of cancer) and 354 asymptomatic, presumed healthy, donors. Then, we assessed an array of different machine-learning models and techniques (e.g., feature selection of RNA transcripts) in pan-cancer detection and multiclass classification. Our results show that simple logistic regression performs the best, reaching a 68% cancer detection rate at a 99% specificity level, and multiclass classification accuracy of 79.38% when distinguishing between five cancer types. In summary, by revisiting classical machine-learning models, we have exceeded the previously used method by 5% and 9.65% in cancer detection and multiclass classification, respectively. To ease further research, we open-source our code and data processing pipelines (https://gitlab.com/jopekmaksym/improving-platelet-rna-based-diagnostics), which we hope will serve the community as a strong baseline.

A hybrid feature weighted attention based deep learning approach for an intrusion detection system using the random forest algorithm.

Due to the recent advances in the Internet and communication technologies, network systems and data have evolved rapidly. The emergence of new attacks jeopardizes network security and make it really challenging to detect intrusions. Multiple network attacks by an intruder are unavoidable. Our research targets the critical issue of class imbalance in intrusion detection, a reflection of the real-world scenario where legitimate network activities significantly out number malicious ones. This imbalance can adversely affect the learning process of predictive models, often resulting in high false-negative rates, a major concern in Intrusion Detection Systems (IDS). By focusing on datasets with this imbalance, we aim to develop and refine advanced algorithms and techniques, such as anomaly detection, cost-sensitive learning, and oversampling methods, to effectively handle such disparities. The primary goal is to create models that are highly sensitive to intrusions while minimizing false alarms, an essential aspect of effective IDS. This approach is not only practical for real-world applications but also enhances the theoretical understanding of managing class imbalance in machine learning. Our research, by addressing these significant challenges, is positioned to make substantial contributions to cybersecurity, providing valuable insights and applicable solutions in the fight against digital threats and ensuring robustness and relevance in IDS development. An intrusion detection system (IDS) checks network traffic for security, availability, and being non-shared. Despite the efforts of many researchers, contemporary IDSs still need to further improve detection accuracy, reduce false alarms, and detect new intrusions. The mean convolutional layer (MCL), feature-weighted attention (FWA) learning, a bidirectional long short-term memory (BILSTM) network, and the random forest algorithm are all parts of our unique hybrid model called MCL-FWA-BILSTM. The CNN-MCL layer for feature extraction receives data after preprocessing. After convolution, pooling, and flattening phases, feature vectors are obtained. The BI-LSTM and self-attention feature weights are used in the suggested method to mitigate the effects of class imbalance. The attention layer and the BI-LSTM features are concatenated to create mapped features before feeding them to the random forest algorithm for classification. Our methodology and model performance were validated using NSL-KDD and UNSW-NB-15, two widely available IDS datasets. The suggested model's accuracies on binary and multi-class classification tasks using the NSL-KDD dataset are 99.67% and 99.88%, respectively. The model's binary and multi-class classification accuracies on the UNSW-NB15 dataset are 99.56% and 99.45%, respectively. Further, we compared the suggested approach with other previous machine learning and deep learning models and found it to outperform them in detection rate, FPR, and F-score. For both binary and multiclass classifications, the proposed method reduces false positives while increasing the number of true positives. The model proficiently identifies diverse network intrusions on computer networks and accomplishes its intended purpose. The suggested model will be helpful in a variety of network security research fields and applications.

Optimal Channel Selection of Multiclass Motor Imagery Classification Based on Fusion Convolutional Neural Network with Attention Blocks.

The widely adopted paradigm in brain-computer interfaces (BCIs) involves motor imagery (MI), enabling improved communication between humans and machines. EEG signals derived from MI present several challenges due to their inherent characteristics, which lead to a complex process of classifying and finding the potential tasks of a specific participant. Another issue is that BCI systems can result in noisy data and redundant channels, which in turn can lead to increased equipment and computational costs. To address these problems, the optimal channel selection of a multiclass MI classification based on a Fusion convolutional neural network with Attention blocks (FCNNA) is proposed. In this study, we developed a CNN model consisting of layers of convolutional blocks with multiple spatial and temporal filters. These filters are designed specifically to capture the distribution and relationships of signal features across different electrode locations, as well as to analyze the evolution of these features over time. Following these layers, a Convolutional Block Attention Module (CBAM) is used to, further, enhance EEG signal feature extraction. In the process of channel selection, the genetic algorithm is used to select the optimal set of channels using a new technique to deliver fixed as well as variable channels for all participants. The proposed methodology is validated showing 6.41% improvement in multiclass classification compared to most baseline models. Notably, we achieved the highest results of 93.09% for binary classes involving left-hand and right-hand movements. In addition, the cross-subject strategy for multiclass classification yielded an impressive accuracy of 68.87%. Following channel selection, multiclass classification accuracy was enhanced, reaching 84.53%. Overall, our experiments illustrated the efficiency of the proposed EEG MI model in both channel selection and classification, showing superior results with either a full channel set or a reduced number of channels.

Comparison of three machine learning algorithms for classification of B-cell neoplasms using clinical flow cytometry data.

Multiparameter flow cytometry data is visually inspected by expert personnel as part of standard clinical disease diagnosis practice. This is a demanding and costly process, and recent research has demonstrated that it is possible to utilize artificial intelligence (AI) algorithms to assist in the interpretive process. Here we report our examination of three previously published machine learning methods for classification of flow cytometry data and apply these to a B-cell neoplasm dataset to obtain predicted disease subtypes. Each of the examined methods classifies samples according to specific disease categories using ungated flow cytometry data. We compare and contrast the three algorithms with respect to their architectures, and we report the multiclass classification accuracies and relative required computation times. Despite different architectures, two of the methods, flowCat and EnsembleCNN, had similarly good accuracies with relatively fast computational times. We note a speed advantage for EnsembleCNN, particularly in the case of addition of training data and retraining of the classifier.

Cognitive Impairment Detection Based on Frontal Camera Scene While Performing Handwriting Tasks

Diagnosing cognitive impairment is an ongoing field of research especially in the elderly. Assessing the health status of the elderly can be a complex process that requires both subjective and objective measures. Subjective measures, such as self-reported responses to questions, can provide valuable information about a person’s experiences, feelings, and beliefs. However, from a scientific point of view, objective measures, based on quantifiable data that can be used to assess a person’s physical and cognitive functioning, are more appropriate and rigorous. The proposed system is based on the use of non-invasive instrumentation, which includes video images acquired with a frontal camera while the user performs different handwriting tasks on a Wacom tablet. We have acquired a new multimodal database of 191 elder subjects, which has been classified by human experts into healthy and cognitive impairment users by means of the standard pentagon copying test. The automatic classification was carried out using a video segmentation algorithm through the technique of shot boundary detection, in conjunction with a Transformer neural network. We obtain a multiclass classification accuracy of 77% and two-class accuracy of 83% based on frontal camera images, which basically detects head movements during handwriting tasks. Our automatic system can replicate human classification of handwritten pentagon copying test, opening a new method for cognitive impairment detection based on head movements. We also demonstrate the possibility to identifying the handwritten task performed by the user, based on frontal camera images and a Transformer neural network.

The BONSAI (Brain and Optic Nerve Study with Artificial Intelligence) deep learning system can accurately identify pediatric papilledema on standard ocular fundus photographs

Pediatric papilledema often reflects an underlying severe neurologic disorder and may be difficult to appreciate, especially in young children. Ocular fundus photographs are easy to obtain even in young children and in nonophthalmology settings. The aim of our study was to ascertain whether an improved deep-learning system (DLS), previously validated in adults, can accurately identify papilledema and other optic disk abnormalities in children. The DLS was tested on mydriatic fundus photographs obtained in a multiethnic pediatric population (<17 years) from three centers (Atlanta-USA; Bucharest-Romania; Singapore). The DLS's multiclass classification accuracy (ie, normal optic disk, papilledema, disks with other abnormality) was calculated, and the DLS's performance to specifically detect papilledema and normal disks was evaluated in a one-vs-rest strategy using the AUC, sensitivity and specificity, with reference to expert neuro-ophthalmologists. External testing was performed on 898 fundus photographs: 447 patients; mean age, 10.33 (231 patients ≤10 years of age; 216, 11-16 years); 558 normal disks, 254 papilledema, 86 other disk abnormalities. Overall multiclass accuracy of the DLS was 89.6% (range, 87.8%-91.6%). The DLS successfully distinguished "normal" from "abnormal" optic disks (AUC 0.99 [0.98-0.99]; sensitivity, 87.3% [84.9%-89.8%]; specificity, 98.5% [97.6%-99.6%]), and "papilledema" from "normal and other" (AUC 0.99 [0.98-1.0]; sensitivity, 98.0% [96.8%-99.4%]; specificity, 94.1% (92.4%-95.9%)]. Our DLS reliably distinguished papilledema from normal optic disks and other disk abnormalities in children, suggesting it could be utilized as a diagnostic aid for the assessment of optic nerve head appearance in the pediatric age group.

Machine Learning Approaches: Detecting the Disease Variants in Human-Exhaled Breath Biomarkers.

In recent days, the development of sensor-based medical devices has been found to be very effective for the prediction and analysis of the onset of diseases. The instigation of an electronic nose (eNose) device is profound and very useful in diverse applications. The analysis of exhaled breath biomarkers using eNose sensors has attained wider attention among researchers, and the prediction of multiple disease variants using the same is still an open research problem. In this work, an enhanced XGBooster classifier-based prediction mechanism was introduced to identify the disease variants based on the responses of commercially available metal oxide-based Figaro (Japan) sensors including TGS826, TGS822, TGS2600, and TGS2602. The implemented model secured 98.36% prediction accuracy in multiclass disease prediction and classification. The homemade one-dimensional metal oxide sensing elements such as ZnO, Cr-doped ZnO, and ZnO/NiO were integrated with the aforementioned sensor array for the specific detection of the three biomarkers of interest. This model has attained a classification accuracy of 99.77, 94.91, and 96.56% toward ammonia, ethanol, and acetone, respectively. And the multiclass disease biomarker classification accuracy of the readymade and homemade eNose prototype models was compared, and the results are summarized.

Convolutional neural network-assisted diagnosis of midpalatal suture maturation stage in cone-beam computed tomography

The selection of treatment for maxillary expansion is closely related to the calcification degree of the midpalatal suture. A classification method for individual assessment of the morphology of midpalatal suture in cone-beam computed tomography (CBCT) is useful for evaluating the calcification degree. Currently, convolutional neural networks (CNNs) have been introduced into the field of oral and maxillofacial imaging diagnosis. This study validated the ability of CNN models in assessing the maturation stage of the midpalatal suture. The existing CNN model ResNet50 was trained to locate the CBCT transverse plane which contained a complete midpalatal suture. ResNet18, ResNet50, RessNet101, Inception-v3, and Efficientnetv2-s models were trained to evaluate the midpalatal suture maturation stage. Multi-class classification metrics, accuracy, recall, precision, F1-score, and area under the curve values from the receiver operating characteristic curve were used to evaluate the performance of the models, and gradient-weighted class activation map technology was utilised to visualise five midpalatal suture maturation stages for each model. Resnet50 demonstrated an accuracy of 99.74% in identifying the transverse plane that contained the complete midpalatal suture. The highest accuracies achieved on the two-stage, three-stage, and five-stage maturation classification tests were 95.15, 88.06, and 75.37%, all of which exceeded the average accuracy of three experienced orthodontists. The CNN model can locate the plane of the midpalatal suture in CBCT images and can assist clinicians in assessing the maturation stage of the midpalatal suture to select the means of maxillary expansion. The application of artificial intelligence on CBCT midpalatal suture plane localisation and maturation stage evaluation enhances diagnostic and treatment efficiency and accuracy of individual assessment of midpalatal suture calcification degree. Additionally, it assists the clinical palatal expansion technique in achieving ideal results.

Novel Ensemble Domain Adaptation Methodology for Enhanced Multi-class Fault Diagnosis of Highly-Connected Fleet of Assets

This paper proposes a novel methodology for enhancing multi-class classification accuracy in fault diagnosis problems among domains with highly-connected fleets of assets using time series data. The approach involves appending specially tailored models to an initial model and incorporating domain adaptation techniques to account for domain variations. The methodology is demonstrated through a case study on fault diagnosis of a fleet of hydraulic rock drills, which presents challenges due to variations in sensor data between different fault classes and individual machines. Results show significant improvements in classification accuracy, both in validation and testing, upon employing ensemble models and applying domain adaptation. While the study is limited to one case study, it lays the groundwork for exploring the applicability of the proposed methodology in other contexts.

Patch-Based Siamese 3D Convolutional Neural Network for Early Alzheimer's Disease Using Multi-Modal Approach

Alzheimer's Disease (AD), the most common type of dementia, is characterized by memory issues that worsen with time. When evaluating single modalities, there are specific efficient learning techniques that produce a poor identification rate. The clinical significance of Mild Cognitive Impairment (MCI) has clinical importance, which is crucial for identifying and categorizing AD patients. This study includes the utilization of 3D T1 weighted /Magnetic Resonance Imaging (3D T1WI MRI) images where the structural changes in the brain are identified for predicting early AD. The classification accuracy for AD, MCI, and Normal Control (NC) has also increased due to cognitive evaluations when comparing three one vs one classifications, i.e. AD vs. NC, MCI vs. NC, AD vs. MCI, and multi-class classification. The proposed approach’s novelty is a binary and multi-class classification of structural MRI images using a Siamese 3D Convolutional Neural Network (Siamese 3D-CNN). The Stochastic Gradient Descent (SGD) has been employed to modify the proposed network's weights, and 5-Fold Cross-Validation (CV) has been used for each binary classification task. Our study used the neuropsychological data of 417 people from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to validate the suggested methodology. Experimental results demonstrate that accuracy, sensitivity, and specificity for three binary classifications produce the maximum percentage, in contrast to other relevant approaches found in the literature. In addition, the multi-class classification accuracy of 99.8% was attained.

Implementation of data fusion to increase the efficiency of classification of precancerous skin states using in vivo bimodal spectroscopic technique.

This study presents the results of the classification of diffuse reflectance (DR) spectra and multiexcitation autofluorescence (AF) spectra that were collected in vivo from precancerous and benign skin lesions at three different source detector separation (SDS) values. Spectra processing pipeline consisted of dimensionality reduction, which was performed using principal component analysis (PCA), followed by classification step using such methods as support vector machine (SVM), multilayered perceptron (MLP), linear discriminant analysis (LDA), and random forest (RF). In order to increase the efficiency of lesion classification, several data fusion methods were applied to the classification results: majority voting, stacking, and manual optimization of weights. The results of the study showed that in most of cases the use of data fusion methods increased the average multiclass classification accuracy from 2% up to 4%. The highest accuracy of multiclass classification was obtained using the manual optimization of weights and reached 94.41%.

Data Diversity in Convolutional Neural Network Based Ensemble Model for Diabetic Retinopathy.

The medical and healthcare domains require automatic diagnosis systems (ADS) for the identification of health problems with technological advancements. Biomedical imaging is one of the techniques used in computer-aided diagnosis systems. Ophthalmologists examine fundus images (FI) to detect and classify stages of diabetic retinopathy (DR). DR is a chronic disease that appears in patients with long-term diabetes. Unattained patients can lead to severe conditions of DR, such as retinal eye detachments. Therefore, early detection and classification of DR are crucial to ward off advanced stages of DR and preserve the vision. Data diversity in an ensemble model refers to the use of multiple models trained on different subsets of data to improve the ensemble's overall performance. In the context of an ensemble model based on a convolutional neural network (CNN) for diabetic retinopathy, this could involve training multiple CNNs on various subsets of retinal images, including images from different patients or those captured using distinct imaging techniques. By combining the predictions of these multiple models, the ensemble model can potentially make more accurate predictions than a single prediction. In this paper, an ensemble model (EM) of three CNN models is proposed for limited and imbalanced DR data using data diversity. Detecting the Class 1 stage of DR is important to control this fatal disease in time. CNN-based EM is incorporated to classify the five classes of DR while giving attention to the early stage, i.e., Class 1. Furthermore, data diversity is created by applying various augmentation and generation techniques with affine transformation. Compared to the single model and other existing work, the proposed EM has achieved better multi-class classification accuracy, precision, sensitivity, and specificity of 91.06%, 91.00%, 95.01%, and 98.38%, respectively.

Utilizing Deep Learning Models and Transfer Learning for COVID-19 Detection from X-Ray Images.

COVID-19 has been a global pandemic. Flattening the curve requires intensive testing, and the world has been facing a shortage of testing equipment and medical personnel with expertise. There is a need to automate and aid the detection process. Several diagnostic tools are currently being used for COVID-19, including X-Rays and CT-scans. This study focuses on detecting COVID-19 from X-Rays. We pursue two types of problems: binary classification (COVID-19 and No COVID-19) and multi-class classification (COVID-19, No COVID-19 and Pneumonia). We examine and evaluate several classic models, namely VGG19, ResNet50, MobileNetV2, InceptionV3, Xception, DenseNet121, and specialized models such as DarkCOVIDNet and COVID-Net and prove that ResNet50 models perform best. We also propose a simple modification to the ResNet50 model, which gives a binary classification accuracy of 99.20% and a multi-class classification accuracy of 86.13%, hence cementing the ResNet50's abilities for COVID-19 detection and ability to differentiate pneumonia and COVID-19. The proposed model's explanations were interpreted via LIME which provides contours, and Grad-CAM, which provides heat-maps over the area(s) of interest of the classifier, i.e., COVID-19 concentrated regions in the lungs, and realize that LIME explains the results better. These explanations support our model's ability to generalize. The proposed model is intended to be deployed for free use.