Classification Of Abnormalities Research Articles

Integrating Deep Learning into Genotoxicity Biomarker Detection for Avian Erythrocytes: A Case Study in a Hemispheric Seabird

Recently, nuclear abnormalities in avian erythrocytes have been used as biomarkers of genotoxicity in several species. Anomalous shapes are usually detected in the nuclei by means of microscopy inspection. However, due to inter- and intra-observer variability, the classification of these blood cell abnormalities could be problematic for replicating research. Deep learning, as a powerful image analysis technique, can be used in this context to improve standardization in identifying the biological configurations of medical and veterinary importance. In this study, we present a standardized deep learning model for identifying and classifying abnormal shapes in erythrocyte nuclei in blood smears of the hemispheric and synanthropic kelp gulls (Larus dominicanus). We trained three convolutional backbones (ResNet34, ResNet50, and ResNet101 architectures) to obtain models capable of detecting and classifying these abnormalities in blood cells. The analysis was performed at three discrimination levels of classification, with broad categories subdivided into increasingly specific subcategories (level 1: “normal”, “abnormal”, “other”; level 2: “normal”, “ENAs”, “micronucleus”, “other”; level 3: “normal”, “irregular”, “displaced”, “enucleated”, “micronucleus”, “other”). The results were more than adequate and very similar in levels 1 and 2 (F1-score 84.6% and 83.6%, and accuracy 83.9% and 82.6%). In level 3, performance was lower (F1-score 65.9% and accuracy 80.8%). It can be concluded that the level 2 analysis should be considered the most appropriate as it is more specific than level 1, with similar quality of performance. This method has proven to be a fast, efficient, and standardized approach that reduces the dependence on human supervision in the classification of nuclear abnormalities in avian erythrocytes, and can be adapted to be used in similar contexts with reduced effort.

Prototype Realtime Detection Of Abnormal Heart Beat Using Multiple Back Propagation Neural Network (BPNN)

Real-time heart rate monitoring and early detection of heart abnormalities are vital to determine heart health before it worsens. To achieve this goal, this project uses the backpropagation neural network (BPNN) method including its capability to classify heartbeats into normal or abnormal by inputting heartbeat values in BPM units derived from prototypes utilizing sensors like Sensor Easy Pulse and NodeMCU, along with considerations of age and sports activity. All data from sensors will be stored in Firebase. Then Firebase will connect to Android, and the normal and abnormal heart classification results will be displayed on the Android system. Simulation results successfully examined 40 people as a sample and provided information from real-time heart rate monitoring, age, and sports activity as input. This research seeks to contribute to improving health services at various public health service centers and independently in detecting heart health early.

Computer-aided colorectal cancer diagnosis: AI-driven image segmentation and classification

Colorectal cancer is an enormous health concern since it is among the most lethal types of malignancy. The manual examination has its limitations, including subjectivity and data overload. To overcome these challenges, computer-aided diagnostic systems focusing on image segmentation and abnormality classification have been developed. This study presents a two-stage approach for the automatic detection of five types of colorectal abnormalities in addition to a control group: polyp, low-grade intraepithelial neoplasia, high-grade intraepithelial neoplasia, serrated adenoma, adenocarcinoma. In the first stage, UNet3+ was used for image segmentation to locate the anomalies, while in the second stage, the Cross-Attention Multi-Scale Vision Transformer deep learning model was used to predict the type of anomaly after highlighting the anomaly on the raw images. In anomaly segmentation, UNet3+ achieved values of 0.9872, 0.9422, 0.9832, and 0.9560 for Dice Coefficient, Jaccard Index, Sensitivity, Specificity respectively. In anomaly detection, the Cross-Attention Multi-Scale Vision Transformer model attained a classification performance of 0.9340, 0.9037, 0.9446, 0.8723, 0.9102, 0.9849 for accuracy, F1 score, precision, recall, Matthews correlation coefficient, and specificity, respectively. The proposed approach proves its capacity to alleviate the overwhelm of pathologists and enhance the accuracy of colorectal cancer diagnosis by achieving high performance in both the identification of anomalies and the segmentation of regions.

Postoperative pulmonary function of patients with lung cancer and interstitial lung abnormalities.

We investigated the impact of radiological interstitial lung abnormalities on the postoperative pulmonary functions of patients with non-small cell lung cancer. A total of 1191 patients with clinical stage IA non-small cell lung cancer who underwent lung resections and pulmonary function tests ≥ 6months postoperatively were retrospectively reviewed. Postoperative pulmonary function reduction rates were compared between patients with and without interstitial lung abnormalities and according to the radiological interstitial lung abnormality classifications. Surgical procedures were divided into wedge resection, 1-2 segment resection, and 3-5 segment resection groups. No significant differences in postoperative pulmonary function reduction rates 6months after wedge resection were observed between the interstitial lung abnormality [n = 202] and non-interstitial lung abnormality groups [n = 989] [vital capacity [VC]: 6.82% vs. 5.00%; forced expiratory volume in 1s [FEV1]: 7.05% vs. 7.14%]. After anatomical resection, these values were significantly lower in the interstitial lung abnormality group than in the non-interstitial lung abnormality group [VC: 1-2 segments, 12.50% vs. 9.93%; 3-5 segments, 17.42% vs. 14.23%; FEV1: 1-2 segments: 13.36% vs. 10.27%; 3-5 segments: 17.36% vs. 14.39%]. No significant differences in postoperative pulmonary function reduction rates according to the radiological interstitial lung abnormality classifications were observed. The presence of interstitial lung abnormalities had a minimal effect on postoperative pulmonary functions after wedge resections; however, pulmonary functions significantly worsened after segmentectomy or lobectomy, regardless of the radiological interstitial lung abnormality classification in early-stage non-small cell lung cancer.

Multimodal imaging of optic nerve head abnormalities in high myopia.

Highly myopic optic nerve head (ONH) abnormalities encompass a series of complications resulting from the stretching of papillary and peripapillary structures during significant axial elongation. The morphological changes in the ONH typically initiate with disk tilting or rotation, progressing to PHOMS and PPA. Tissue defects in each layer manifest as focal lamina cribrosa defects (FLDs), peripapillary intrachoroidal cavitations (PICCs), and acquired pits of the optic nerve (APON). Anterior vitreous/vascular traction and posterior scleral protrusion may lead to prelaminar schisis as well as paravascular cysts and holes, which can potentially develop into retinoschisis. Traditional color fundus photography (CFP) is often insufficient for visualizing most of these lesions, yet their description and quantification benefit significantly from the advancements in optical coherence tomography (OCT) and OCT angiography (OCTA), complemented by fundus autofluorescence (FAF), indocyanine green angiography (ICGA), and three-dimensional imaging. The effective diagnosis and classification of ONH abnormalities heavily rely on a comprehensive understanding of their multimodal imaging features, as outlined in this review. These findings provide valuable insights into optic neuropathy in high myopia, establishing a solid foundation for future endeavors in disease monitoring and treatment guidance.

A Novel Approach for Diagnosing Transformer Internal Defects and Inrush Current Based on 1DCNN and LSTM Deep Learning

In power systems, power transformer (Pt) protection plays a vital role in ensuring that customers have a reliable power supply. Correctly recognizing inrush currents from internal defects and preventing differential relay malfunctions are two of biggest challenges facing the differential protection of power transformers. Although previous approaches suggested to overcome these issues have promising outcomes, increasing the accuracy and reducing the execution time and complexity of transformer differential relays are still interesting topics for researchers. Accordingly, a new fault diagnostic method based on wavelet transform (WT) and deep learning is introduced in paper. In the proposed approach, Discrete WT is used to extract the features of differential currents, and combined one-dimensional convolutional neural networks and long short-term memory (1DCNN-LSTM)) is applied for classify internal faults from other abnormal events. High accuracy, no need for any thresholds or transformer parameters and fast fault detection are the main advantages of the proposed approach. The simulation results for a 132/11 kV, 63 MVA power transformer approved the proposed method for its ability to accurately differentiate between inrush currents and internal defects after 5 ms, as well as its accuracy for abnormal event classification of about 99.4%.

Automated ECG Signals Analysis for Cardiac Abnormality Detection and Classification

Automated ECG Signals Analysis for Cardiac Abnormality Detection and Classification

Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteria.

Despite their remarkable performance, deep neural networks remain unadopted in clinical practice, which is considered to be partially due to their lack of explainability. In this work, we apply explainable attribution methods to a pre-trained deep neural network for abnormality classification in 12-lead electrocardiography to open this "black box" and understand the relationship between model prediction and learned features. We classify data from two public databases (CPSC 2018, PTB-XL) and the attribution methods assign a "relevance score" to each sample of the classified signals. This allows analyzing what the network learned during training, for which we propose quantitative methods: average relevance scores over a) classes, b) leads, and c) average beats. The analyses of relevance scores for atrial fibrillation and left bundle branch block compared to healthy controls show that their mean values a) increase with higher classification probability and correspond to false classifications when around zero, and b) correspond to clinical recommendations regarding which lead to consider. Furthermore, c) visible P-waves and concordant T-waves result in clearly negative relevance scores in atrial fibrillation and left bundle branch block classification, respectively. Results are similar across both databases despite differences in study population and hardware. In summary, our analysis suggests that the DNN learned features similar to cardiology textbook knowledge.

A framework for ship abnormal behaviour detection and classification using AIS data

This paper proposes a method for detecting and classifying ship abnormal behaviour in ship trajectories. The method involves generating parameter profiles for the ship's trajectory and applying a Sliding Window algorithm to detect the ship's abnormal behaviour. Then, several features are adopted to effectively describe the characteristics of each ship's abnormal behaviour, such as the standard deviation of speed, detour factor, maximum drift angle, accumulative change of Course Over Ground and maximum lateral distance to the ship route. A density-based clustering algorithm is applied to group similar abnormal behaviour patterns according to the feature similarity, and the Random Forest Classification method is used to train a classification model based on the features extracted from the clusters. The proposed method is then tested on historical ship trajectory data provided by the Automatic Identification System. The results suggest that the method effectively identifies and classifies different abnormal behaviours in the ship trajectories.

Abnormal line loss identification and category classification of distribution networks based on semi-supervised learning and hierarchical classification

Line loss refers to the electrical energy that is dissipated as heat during the transmission and distribution of electricity through power lines. However, unusual causes, such as grid topology mismatch and communication failure, can cause abnormal line loss. Efficient abnormal line loss detection contributes not only to minimizing energy wastage and reducing carbon emissions but also to maintaining the stability and reliability of the entire distribution network. In actual situations, the cause of abnormal line loss is not labeled due to the expensive labor cost. This paper proposes a hierarchical abnormal line loss identification and category classification model, considering the unlabeled and unbalanced sample problem. First, an abnormal line loss identification model-based random forest is established to detect whether the line loss is abnormal. Then, an abnormal line loss category classification model is developed with semi-supervised learning for line loss abnormal category classification, considering the unlabeled samples. The real dataset in China is utilized to validate the performance of the proposed model. Its reliability implies the potential to be applied to real-world scenarios to improve the management level and safety of the power grid.

Ensemble fusion model for improved lung abnormality classification: Leveraging pre-trained models

Lung abnormalities pose significant health concerns, underscoring the need for swift and accurate diagnoses to facilitate timely medical intervention. This study introduces a novel methodology for the sub-classification of lung abnormalities within chest X-rays captured via smartphones. An accurate and timely diagnosis of lung abnormalities is essential for the successful implementation of appropriate therapy. In this paper, we propose a novel approach using a Convolutional neural network (CNN) with three maximum pooling layers and early fusion for sub-classifying lung abnormalities from chest Xrays. Based on the kind of abnormality, the CheXpert dataset is divided into 13 sub-classes, each of which is trained using a different sub-model. An early fusion procedure is then used to integrate the outputs of the sub-model.•3M-CNN (Method 1): We employed a Convolutional Neural Network (CNN) with three max pooling layers and an early fusion strategy to train dedicated sub-models for each of the 13 distinct sub-classes of lung abnormalities using the CheXpert dataset.•Ensemble Model (Method 2): Our ‘Ensemble model’ integrated the outputs of the trained sub-models, providing a powerful approach for the sub-classification of lung abnormalities.•Exceptional Accuracy: Our ‘3M-CNN’ and ‘fused model’ achieved an accuracy of 98.79%, surpassing established methodologies, which is beneficial in resource-constrained environments embracing smartphone-based imaging.

Multi-Feature Decision Fusion Network for Heart Sound Abnormality Detection and Classification.

The heart sound reflects the movement status of the cardiovascular system and contains the early pathological information of cardiovascular diseases. Automatic heart sound diagnosis plays an essential role in the early detection of cardiovascular diseases. In this study, we aim to develop a novel end-to-end heart sound abnormality detection and classification method, which can be adapted to different heart sound diagnosis tasks. Specifically, we developed a Multi-feature Decision Fusion Network (MDFNet) composed of a Multi-dimensional Feature Extraction (MFE) module and a Multi-dimensional Decision Fusion (MDF) module. The MFE module extracted spatial features, multi-level temporal features and spatial-temporal fusion features to learn heart sound characteristics from multiple perspectives. Through deep supervision and decision fusion, the MDF module made the multi-dimensional features extracted by the MFE module more discriminative, and fused the decision results of multi-dimensional features to integrate complementary information. Furthermore, attention modules were embedded in the MDFNet to emphasize the fundamental heart sounds containing effective feature information. Finally, we proposed an efficient data augmentation method to circumvent the diagnosis performance degradation caused by the lack of cardiac cycle segmentation in other end-to-end methods. The developed method achieved an overall accuracy of 94.44% and a F1-score of 86.90% on the binary classification task and a F1-score of 99.30% on the five-classification task. Our method outperformed other state-of-the-art methods and had good clinical application prospects.

Multi-class classification of breast cancer abnormality using transfer learning

Multi-class classification of breast cancer abnormality using transfer learning

Fetal MRI Analysis of Corpus Callosal Abnormalities: Classification, and Associated Anomalies.

Corpus callosal abnormalities (CCA) are midline developmental brain malformations and are usually associated with a wide spectrum of other neurological and non-neurological abnormalities. The study aims to highlight the diagnostic role of fetal MRI to characterize heterogeneous corpus callosal abnormalities using the latest classification system. It also helps to identify associated anomalies, which have prognostic implications for the postnatal outcome. In this study, retrospective data from antenatal women who underwent fetal MRI between January 2014 and July 2023 at Rush University Medical Center were evaluated for CCA and classified based on structural morphology. Patients were further assessed for associated neurological and non-neurological anomalies. The most frequent class of CCA was complete agenesis (79.1%), followed by hypoplasia (12.5%), dysplasia (4.2%), and hypoplasia with dysplasia (4.2%). Among them, 17% had isolated CCA, while the majority (83%) had complex forms of CCA associated with other CNS and non-CNS anomalies. Out of the complex CCA cases, 58% were associated with other CNS anomalies, while 8% were associated with non-CNS anomalies. 17% of cases had both. The use of fetal MRI is valuable in the classification of abnormalities of the corpus callosum after the confirmation of a suspected diagnosis on prenatal ultrasound. This technique is an invaluable method for distinguishing between isolated and complex forms of CCA, especially in cases of apparent isolated CCA. The use of diffusion-weighted imaging or diffusion tensor imaging in fetal neuroimaging is expected to provide further insights into white matter abnormalities in fetuses diagnosed with CCA in the future.

S4D-ECG: A Shallow State-of-the-Art Model for Cardiac Abnormality Classification

Abstract Purpose This study introduces an algorithm specifically designed for processing unprocessed 12-lead electrocardiogram (ECG) data, with the primary aim of detecting cardiac abnormalities. Methods The proposed model integrates Diagonal State Space Sequence (S4D) model into its architecture, leveraging its effectiveness in capturing dynamics within time-series data. The S4D model is designed with stacked S4D layers for processing raw input data and a simplified decoder using a dense layer for predicting abnormality types. Experimental optimization determines the optimal number of S4D layers, striking a balance between computational efficiency and predictive performance. This comprehensive approach ensures the model's suitability for real-time processing on hardware devices with limited capabilities, offering a streamlined yet effective solution for heart monitoring. Results Among the notable features of this algorithm is its strong resilience to noise, enabling the algorithm to achieve an average F1-score of 81.2% and an AUROC of 95.5% in generalization. The model underwent testing specifically on the lead II ECG signal, exhibiting consistent performance with an F1-score of 79.5% and an AUROC of 95.7%. Conclusion It is characterized by the elimination of pre-processing features and the availability of a low-complexity architecture that makes it suitable for implementation on numerous computing devices because it is easily implementable. Consequently, this algorithm exhibits considerable potential for practical applications in analyzing real-world ECG data. This model can be placed on the cloud for diagnosis. The model was also tested on lead II of the ECG alone and has demonstrated promising results, supporting its potential for on-device application.

Enhancing lung abnormalities diagnosis using hybrid DCNN-ViT-GRU model with explainable AI: A deep learning approach

In this study, we propose a novel approach called DCNN-ViT-GRU, which combines deep Convolutional Neural Networks (CNNs) with Gated Recurrent Units (GRUs) and the Vision Transformer (ViT) model for the accurate detection and classification of lung abnormalities. By leveraging the strengths of both CNNs and the ViT model, our architecture automatically extracts meaningful features from lung images, leading to improved diagnostic capabilities. The DCNN-ViT-GRU model utilizes a combination of deep CNN and GRU layers, allowing it to effectively capture local and global patterns. This comprehensive feature representation enhances the model's ability to identify various abnormalities in lung images, including lung cancer, COVID-19, and pneumonia. To further enhance the interpretability and transparency of our model, we integrate Explainable Artificial Intelligence (XAI) techniques, including LIME and SHAP. This integration provides valuable insights into the decision-making process of the DCNN-ViT-GRU model, enabling clinicians to understand and validate the predictions made by the model. We evaluated the performance of our proposed approach on diverse datasets containing cases of lung abnormalities. Through cross-validation, our DCNN-ViT-GRU model achieved impressive weighted mean accuracy of 99% and 99.86% for two distinct datasets, demonstrating its superior performance. Furthermore, in hold-out validation on separate datasets, the model achieved accuracies of 99.09% and 99.87%, respectively. Integrating the XAI techniques enhances the interpretability of the DCNN-ViT-GRU model and provides clinicians with valuable insights regarding the factors contributing to the diagnosis of lung abnormalities. This approach presents a promising solution for accurate and interpretable lung abnormalities detection and classification, with potential implications for improved patient care and treatment planning.

An effective framework of human abnormal behaviour recognition and tracking using multiscale dilated assisted residual attention network

The prevention of certain unwanted crime events and eliminating them even before their execution can be done by automatic identification of abnormal behavior in humans. Hence automatic prediction of abnormal human behavior is a difficult task to perform. Some of the automated model has been implemented and provided the most promising results. The manual intervention is being the greatest approach in earlier time, yet it brings with numerous errors, consumes more time and more cost effective. Henceforth, the automated model is suggested for identifying the activities. As the scholar focus on machine and deep learning, this classifier may extract the hand-crafted features. But it fails to yield the appropriate solution for finding the activities. Since it belongs to the video frames, the object detection is highly Ineffective feature vector and inadequate scale measures of the learning model paves the way for performance degradation. This issue can be resolved by including an attention mechanism in the deep learning model for both monitoring and classification purposes. The recommended Human Abnormal Behavior Recognition and Tracking (HABRT) model performs the following operations, such as the collection of video, categorizing the behavior in the video as normal or abnormal, monitoring, extraction of the object, and classification of the abnormality. The input video with such frames is initially gathered from publically available databases. By using these frames, the abnormal behavior classification is done by Multiscale Dilated assisted Residual Attention Network (MD-RAN), For further enhancement, the hyper-parameters in the MD-RAN are optimally selected by novel Modified Random Parameter-based Chimp Optimization Algorithm (MRP-ChOA). Once the abnormal frames are obtained, the activity tracking is achieved by Adaptively Modified You Only Look Once (YOLO) V3 (AM-YOLO V3). This model encompasses with multiple layers, so that utilized number of layers are determined optimally using MRP-ChOA. Consequently, the objects are extracted from the abnormal frames with the help of AM-YOLO V3. Finally, the abnormalities are classified by using the same MD-RAN. At last, the performance is analyzed and validated with diverse parameters, which are then compared with other algorithms. While implementing the dataset 1, the accuracy value attains maximum in contrast with 3.14% of DTCN, 2.308% of CNN-RNN and 13.7% of ResAttenConvLSTM, correspondingly. Thus, the findings reveal that it has the potential to deliver extensive results for abnormal recognition and tracking.

A twin convolutional neural network with hybrid binary optimizer for multimodal breast cancer digital image classification

There is a wide application of deep learning technique to unimodal medical image analysis with significant classification accuracy performance observed. However, real-world diagnosis of some chronic diseases such as breast cancer often require multimodal data streams with different modalities of visual and textual content. Mammography, magnetic resonance imaging (MRI) and image-guided breast biopsy represent a few of multimodal visual streams considered by physicians in isolating cases of breast cancer. Unfortunately, most studies applying deep learning techniques to solving classification problems in digital breast images have often narrowed their study to unimodal samples. This is understood considering the challenging nature of multimodal image abnormality classification where the fusion of high dimension heterogeneous features learned needs to be projected into a common representation space. This paper presents a novel deep learning approach combining a dual/twin convolutional neural network (TwinCNN) framework to address the challenge of breast cancer image classification from multi-modalities. First, modality-based feature learning was achieved by extracting both low and high levels features using the networks embedded with TwinCNN. Secondly, to address the notorious problem of high dimensionality associated with the extracted features, binary optimization method is adapted to effectively eliminate non-discriminant features in the search space. Furthermore, a novel method for feature fusion is applied to computationally leverage the ground-truth and predicted labels for each sample to enable multimodality classification. To evaluate the proposed method, digital mammography images and digital histopathology breast biopsy samples from benchmark datasets namely MIAS and BreakHis respectively. Experimental results obtained showed that the classification accuracy and area under the curve (AUC) for the single modalities yielded 0.755 and 0.861871 for histology, and 0.791 and 0.638 for mammography. Furthermore, the study investigated classification accuracy resulting from the fused feature method, and the result obtained showed that 0.977, 0.913, and 0.667 for histology, mammography, and multimodality respectively. The findings from the study confirmed that multimodal image classification based on combination of image features and predicted label improves performance. In addition, the contribution of the study shows that feature dimensionality reduction based on binary optimizer supports the elimination of non-discriminant features capable of bottle-necking the classifier.

Learning group-wise spatial attention and label dependencies for multi-task thoracic disease classification

This paper considers the multi-label thoracic abnormality classification with chest X-ray images. In clinical settings, Chest X-ray imaging is a general diagnostic tool applied to visualize numerous thoracic pathological changes. While deep learning techniques have been extensively tested in this field, certain challenges persist. The data in existing thoracic abnormality datasets is insufficient, and some diseases are extremely imbalanced. Meanwhile, the dependencies between different labels are often ignored. To tackle these issues head-on, this paper introduces two crucial modules: the group-wise spatial attention (GWSA) module and the label co-occurrence dependency (LCD) module, integrated with DenseNet121 backbone. Specifically, GWSA enhances the spatial features within distinct groups while keeping the between-group feature discrimination. LCD models the correlations between different thoracic abnormalities to refine the predicted probabilities. In conjunction with the DenseNet121 backbone, these two modules reach an average AUC score of 0.818 on Chest X-ray14 dataset, achieving state-of-the-art. Source code is available at https://github.com/YujiaKCL/Chest-Xray14-GWSA-LCD.

An autonomous and intelligent hybrid CNN-RNN-LSTM based approach for the detection and classification of abnormalities in brain

An autonomous and intelligent hybrid CNN-RNN-LSTM based approach for the detection and classification of abnormalities in brain