Deep Learning-based Classification Research Articles

A Deep Learning-based Classification Model for Arabic News Tweets Using Bidirectional Long Short-Term Memory Networks

This research develops a classification model for Arabic news tweets using Bidirectional Long Short-Term Memory networks (BiLSTM). Tweets about Arabic news were gathered between August 2016 and August 2020 and divided into five categories. Custom Python scripts, Twitter API and the GetOldTweets3 Python library were used to collect the data. BiLSTM was used to train and test the model. The results indicated an average accuracy, precision, recall, and f1-score of 0.88, 0.92, 0.88, and 0.89, respectively. The results could have practical implications for Arabic machine learning and NLP tasks in research and practice.

A proposed secure framework for protecting cloud-based educational systems from hacking

Educational institutions and users involved in the whole learning process frequently have concerns about the storage and processing of sensitive data and essential apps in the cloud. Security and privacy issues have emerged as a major challenge, limiting cloud computing’s implementation in educational environments. Several users have yet to meet this security challenge, which is linked to the system’s multi-tenancy nature and the outsourcing of resources and data. This study proposes a secure framework for protecting cloud-based educational systems from hacking using a unique encryption technique, as well as a deep learning-based classification for cloud attack detection. Initially, we preprocess the data and extract features using a gray-level covariance matrix (GLCM). Next, we propose a classification based on multiple convolutional neural networks (M−CNN) to detect attacks in the cloud environment. Finally, we propose a modified digital signature algorithm (MDSA) for data encryption and decryption. The proposed technique achieved high security rates, with an accuracy of 97.7%, sensitivity of 96%, specificity of 94.3%, precision of 99.6%, and recall of 97%. Comparative evaluations showed that the proposed mechanism outperformed other encryption techniques. This novel model enhances the security of cloud-based educational systems and promotes users’ confidence in such platforms.

Deep learning-based classification and application test of multiple crop leaf diseases using transfer learning and the attention mechanism

Deep learning-based classification and application test of multiple crop leaf diseases using transfer learning and the attention mechanism

Deep Residual Learning-Based Classification with Identification of Incorrect Predictions and Quantification of Cellularity and Nuclear Morphological Features in Digital Pathological Images of Common Astrocytic Tumors.

Interobserver variations in the pathology of common astrocytic tumors impact diagnosis and subsequent treatment decisions. This study leveraged a residual neural network-50 (ResNet-50) in digital pathological images of diffuse astrocytoma, anaplastic astrocytoma, and glioblastoma to recognize characteristic pathological features and perform classification at the patch and case levels with identification of incorrect predictions. In addition, cellularity and nuclear morphological features, including axis ratio, circularity, entropy, area, irregularity, and perimeter, were quantified via a hybrid task cascade (HTC) framework and compared between different characteristic pathological features with importance weighting. A total of 95 cases, including 15 cases of diffuse astrocytoma, 11 cases of anaplastic astrocytoma, and 69 cases of glioblastoma, were collected in Taiwan Hualien Tzu Chi Hospital from January 2000 to December 2021. The results revealed that an optimized ResNet-50 model could recognize characteristic pathological features at the patch level and assist in diagnosis at the case level with accuracies of 0.916 and 0.846, respectively. Incorrect predictions were mainly due to indistinguishable morphologic overlap between anaplastic astrocytoma and glioblastoma tumor cell area, zones of scant vascular lumen with compact endothelial cells in the glioblastoma microvascular proliferation area mimicking the glioblastoma tumor cell area, and certain regions in diffuse astrocytoma with too low cellularity being misrecognized as the glioblastoma necrosis area. Significant differences were observed in cellularity and each nuclear morphological feature among different characteristic pathological features. Furthermore, using the extreme gradient boosting (XGBoost) algorithm, we found that entropy was the most important feature for classification, followed by cellularity, area, circularity, axis ratio, perimeter, and irregularity. Identifying incorrect predictions provided valuable feedback to machine learning design to further enhance accuracy and reduce errors in classification. Moreover, quantifying cellularity and nuclear morphological features with importance weighting provided the basis for developing an innovative scoring system to achieve objective classification and precision diagnosis among common astrocytic tumors.

Improved Identification of Forest Types in the Loess Plateau Using Multi-Source Remote Sensing Data, Transfer Learning, and Neural Residual Networks

This study aims to establish a deep learning-based classification framework to efficiently and rapidly distinguish between coniferous and broadleaf forests across the Loess Plateau. By integrating the deep residual neural network (ResNet) architecture with transfer learning techniques and multispectral data from unmanned aerial vehicles (UAVs) and Landsat remote sensing data, the effectiveness of the framework was validated through well-designed experiments. The study began by selecting optimal spectral band combinations, using the random forest algorithm. Pre-trained models were then constructed, and model performance was optimized with different training strategies, considering factors such as image size, sample quantity, and model depth. The results indicated substantial improvements in the model’s classification accuracy and efficiency for reasonable image dimensions and sample sizes, especially for an image size of 3 × 3 pixels and 2000 samples. In addition, the application of transfer learning and model fine-tuning strategies greatly enhanced the adaptability and universality of the model in different classification scenarios. The fine-tuned model achieved remarkable performance improvements in forest-type classification tasks, increasing classification accuracy from 85% to 93% in Zhengning, from 89% to 96% in Yongshou, and from 86% to 94% in Baishui, as well as exceeding 90% in all counties. These results not only confirm the effectiveness of the proposed framework, but also emphasize the roles of image size, sample quantity, and model depth in improving the generalization ability and classification accuracy of the model. In conclusion, this research has developed a technological framework for effective forest landscape recognition, using a combination of multispectral data from UAVs and Landsat satellites. This combination proved to be more effective in identifying forest types than was using Landsat data alone, demonstrating the enhanced capability and accuracy gained by integrating UAV technology. This research provides valuable scientific guidance and tools for policymakers and practitioners in forest management and sustainable development.

Improved tomato leaf disease classification through adaptive ensemble models with exponential moving average fusion and enhanced weighted gradient optimization.

Tomato is one of the most popular and most important food crops consumed globally. The quality and quantity of yield by tomato plants are affected by the impact made by various kinds of diseases. Therefore, it is essential to identify these diseases early so that it is possible to reduce the occurrences and effect of the diseases on tomato plants to improve the overall crop yield and to support the farmers. In the past, many research works have been carried out by applying the machine learning techniques to segment and classify the tomato leaf images. However, the existing machine learning-based classifiers are not able to detect the new types of diseases more accurately. On the other hand, deep learning-based classifiers with the support of swarm intelligence-based optimization techniques are able to enhance the classification accuracy, leading to the more effective and accurate detection of leaf diseases. This research paper proposes a new method for the accurate classification of tomato leaf diseases by harnessing the power of an ensemble model in a sample dataset of tomato plants, containing images pertaining to nine different types of leaf diseases. This research introduces an ensemble model with an exponential moving average function with temporal constraints and an enhanced weighted gradient optimizer that is integrated into fine-tuned Visual Geometry Group-16 (VGG-16) and Neural Architecture Search Network (NASNet) mobile training methods for providing improved learning and classification accuracy. The dataset used for the research consists of 10,000 tomato leaf images categorized into nine classes for training and validating the model and an additional 1,000 images reserved for testing the model. The results have been analyzed thoroughly and benchmarked with existing performance metrics, thus proving that the proposed approach gives better performance in terms of accuracy, loss, precision, recall, receiver operating characteristic curve, and F1-score with values of 98.7%, 4%, 97.9%, 98.6%, 99.97%, and 98.7%, respectively.

Pine Wilt Disease Segmentation with Deep Metric Learning Species Classification for Early-Stage Disease and Potential False Positive Identification

Pine Wilt Disease poses a significant global threat to forests, necessitating swift detection methods. Conventional approaches are resource-intensive but utilizing deep learning on ortho-mapped images obtained from Unmanned Aerial Vehicles offers cost-effective and scalable solutions. This study presents a novel method for Pine Wilt Disease detection and classification using YOLOv8 for segmenting diseased areas, followed by cropping the diseased regions from the original image and applying Deep Metric Learning for classification. We trained a ResNet50 model using semi-hard triplet loss to obtain embeddings, and subsequently trained a Random Forest classifier tasked with identifying tree species and distinguishing false positives. Segmentation was favored over object detection due to its ability to provide pixel-level information, enabling the flexible extension of subsequent bounding boxes. Deep Metric Learning-based classification after segmentation was chosen for its effectiveness in handling visually similar images. The results indicate a mean Intersection over Union of 83.12% for segmentation, with classification accuracies of 98.7% and 90.7% on the validation and test sets, respectively.

Single-cell classification based on label-free high-resolution optical data of cell adhesion kinetics

Selecting and isolating various cell types is a critical procedure in many applications, including immune therapy, regenerative medicine, and cancer research. Usually, these selection processes involve some labeling or another invasive step potentially affecting cellular functionality or damaging the cell. In the current proof of principle study, we first introduce an optical biosensor-based method capable of classification between healthy and numerous cancerous cell types in a label-free setup. We present high classification accuracy based on the monitored single-cell adhesion kinetic signals. We developed a high-throughput data processing pipeline to build a benchmark database of ~ 4500 single-cell adhesion measurements of a normal preosteoblast (MC3T3-E1) and various cancer (HeLa, LCLC-103H, MDA-MB-231, MCF-7) cell types. Several datasets were used with different cell-type selections to test the performance of deep learning-based classification models, reaching above 70–80% depending on the classification task. Beyond testing these models, we aimed to draw interpretable biological insights from their results; thus, we applied a deep neural network visualization method (grad-CAM) to reveal the basis on which these complex models made their decisions. Our proof-of-concept work demonstrated the success of a deep neural network using merely label-free adhesion kinetic data to classify single mammalian cells into different cell types. We propose our method for label-free single-cell profiling and in vitro cancer research involving adhesion. The employed label-free measurement is noninvasive and does not affect cellular functionality. Therefore, it could also be adapted for applications where the selected cells need further processing, such as immune therapy and regenerative medicine.

Deep learning-based classification of anti-personnel mines and sub-gram metal content in mineralized soil (DL-MMD)

De-mining operations are of critical importance for humanitarian efforts and safety in conflict-affected regions. In this paper, we address the challenge of enhancing the accuracy and efficiency of mine detection systems. We present an innovative Deep Learning architecture tailored for pulse induction-based Metallic Mine Detectors (MMD), so called DL-MMD. Our methodology leverages deep neural networks to distinguish amongst nine distinct materials with an exceptional validation accuracy of 93.5%. This high level of precision enables us not only to differentiate between anti-personnel mines, without metal plates but also to detect minuscule 0.2-g vertical paper pins in both mineralized soil and non-mineralized environments. Moreover, through comparative analysis, we demonstrate a substantial 3% and 7% improvement (approx.) in accuracy performance compared to the traditional K-Nearest Neighbors and Support Vector Machine classifiers, respectively. The fusion of deep neural networks with the pulse induction-based MMD not only presents a cost-effective solution but also significantly expedites decision-making processes in de-mining operations, ultimately contributing to improved safety and effectiveness in these critical endeavors.

Deep learning-based classification of the capillary ultrastructure in human skeletal muscles

Deep learning-based classification of the capillary ultrastructure in human skeletal muscles

Noninvasive Molecular Subtyping of Pediatric Low-Grade Glioma with Self-Supervised Transfer Learning.

Purpose To develop and externally test a scan-to-prediction deep learning pipeline for noninvasive, MRI-based BRAF mutational status classification for pediatric low-grade glioma. Materials and Methods This retrospective study included two pediatric low-grade glioma datasets with linked genomic and diagnostic T2-weighted MRI data of patients: Dana-Farber/Boston Children's Hospital (development dataset, n = 214 [113 (52.8%) male; 104 (48.6%) BRAF wild type, 60 (28.0%) BRAF fusion, and 50 (23.4%) BRAF V600E]) and the Children's Brain Tumor Network (external testing, n = 112 [55 (49.1%) male; 35 (31.2%) BRAF wild type, 60 (53.6%) BRAF fusion, and 17 (15.2%) BRAF V600E]). A deep learning pipeline was developed to classify BRAF mutational status (BRAF wild type vs BRAF fusion vs BRAF V600E) via a two-stage process: (a) three-dimensional tumor segmentation and extraction of axial tumor images and (b) section-wise, deep learning-based classification of mutational status. Knowledge-transfer and self-supervised approaches were investigated to prevent model overfitting, with a primary end point of the area under the receiver operating characteristic curve (AUC). To enhance model interpretability, a novel metric, center of mass distance, was developed to quantify the model attention around the tumor. Results A combination of transfer learning from a pretrained medical imaging-specific network and self-supervised label cross-training (TransferX) coupled with consensus logic yielded the highest classification performance with an AUC of 0.82 (95% CI: 0.72, 0.91), 0.87 (95% CI: 0.61, 0.97), and 0.85 (95% CI: 0.66, 0.95) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively, on internal testing. On external testing, the pipeline yielded an AUC of 0.72 (95% CI: 0.64, 0.86), 0.78 (95% CI: 0.61, 0.89), and 0.72 (95% CI: 0.64, 0.88) for BRAF wild type, BRAF fusion, and BRAF V600E, respectively. Conclusion Transfer learning and self-supervised cross-training improved classification performance and generalizability for noninvasive pediatric low-grade glioma mutational status prediction in a limited data scenario. Keywords: Pediatrics, MRI, CNS, Brain/Brain Stem, Oncology, Feature Detection, Diagnosis, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024.

Deep Learning-Based Classification and Semantic Segmentation of Lung Tuberculosis Lesions in Chest X-ray Images.

We present a deep learning (DL) network-based approach for detecting and semantically segmenting two specific types of tuberculosis (TB) lesions in chest X-ray (CXR) images. In the proposed method, we use a basic U-Net model and its enhanced versions to detect, classify, and segment TB lesions in CXR images. The model architectures used in this study are U-Net, Attention U-Net, U-Net++, Attention U-Net++, and pyramid spatial pooling (PSP) Attention U-Net++, which are optimized and compared based on the test results of each model to find the best parameters. Finally, we use four ensemble approaches which combine the top five models to further improve lesion classification and segmentation results. In the training stage, we use data augmentation and preprocessing methods to increase the number and strength of lesion features in CXR images, respectively. Our dataset consists of 110 training, 14 validation, and 98 test images. The experimental results show that the proposed ensemble model achieves a maximum mean intersection-over-union (MIoU) of 0.70, a mean precision rate of 0.88, a mean recall rate of 0.75, a mean F1-score of 0.81, and an accuracy of 1.0, which are all better than those of only using a single-network model. The proposed method can be used by clinicians as a diagnostic tool assisting in the examination of TB lesions in CXR images.

An efficient Fusion-Purification Network for Cervical pap-smear image classification

Background and Objectives:In cervical cell diagnostics, autonomous screening technology constitutes the foundation of automated diagnostic systems. Currently, numerous deep learning-based classification techniques have been successfully implemented in the analysis of cervical cell images, yielding favorable outcomes. Nevertheless, efficient discrimination of cervical cells continues to be challenging due to large intra-class and small inter-class variations. The key to dealing with this problem is to capture localized informative differences from cervical cell images and to represent discriminative features efficiently. Existing methods neglect the importance of global morphological information, resulting in inadequate feature representation capability. Methods:To address this limitation, we propose a novel cervical cell classification model that focuses on purified fusion information. Specifically, we first integrate the detailed texture information and morphological structure features, named cervical pathology information fusion. Second, in order to enhance the discrimination of cervical cell features and address the data redundancy and bias inherent after fusion, we design a cervical purification bottleneck module. This model strikes a balance between leveraging purified features and facilitating high-efficiency discrimination. Furthermore, we intend to unveil a more intricate cervical cell dataset: Cervical Cytopathology Image Dataset (CCID). Results:Extensive experiments on two real-world datasets show that our proposed model outperforms state-of-the-art cervical cell classification models. Conclusions:The results show that our method can well help pathologists to accurately evaluate cervical smears.

Are deep learning classification results obtained on CT scans fair and interpretable?

Following the great success of various deep learning methods in image and object classification, the biomedical image processing society is also overwhelmed with their applications to various automatic diagnosis cases. Unfortunately, most of the deep learning-based classification attempts in the literature solely focus on the aim of extreme accuracy scores, without considering interpretability, or patient-wise separation of training and test data. For example, most lung nodule classification papers using deep learning randomly shuffle data and split it into training, validation, and test sets, causing certain images from the Computed Tomography (CT) scan of a person to be in the training set, while other images of the same person to be in the validation or testing image sets. This can result in reporting misleading accuracy rates and the learning of irrelevant features, ultimately reducing the real-life usability of these models. When the deep neural networks trained on the traditional, unfair data shuffling method are challenged with new patient images, it is observed that the trained models perform poorly. In contrast, deep neural networks trained with strict patient-level separation maintain their accuracy rates even when new patient images are tested. Heat map visualizations of the activations of the deep neural networks trained with strict patient-level separation indicate a higher degree of focus on the relevant nodules. We argue that the research question posed in the title has a positive answer only if the deep neural networks are trained with images of patients that are strictly isolated from the validation and testing patient sets.

Multiplex Detection of Foodborne Pathogens using 3D Nanostructure Swab and Deep Learning-Based Classification of Raman Spectra.

Proactive management of foodborne illness requires routine surveillance of foodborne pathogens, which requires developing simple, rapid, and sensitive detection methods. Here, a strategy is presented that enables the detection of multiple foodborne bacteria using a 3D nanostructure swab and deep learning-based Raman signal classification. The nanostructure swab efficiently captures foodborne pathogens, and the portable Raman instrument directly collects the Raman signals of captured bacteria. a deep learning algorithm has been demonstrated, 1D convolutional neural network with binary labeling, achieves superior performance in classifying individual bacterial species. This methodology has been extended to mixed bacterial populations, maintaining accuracy close to 100%. In addition, the gradient-weighted class activation mapping method is used to provide an investigation of the Raman bands for foodborne pathogens. For practical application, blind tests are conducted on contaminated kitchen utensils and foods. The proposed technique is validated by the successful detection of bacterial species from the contaminated surfaces. The use of a 3D nanostructure swab, portable Raman device, and deep learning-based classification provides a powerful tool for rapid identification (≈5 min) of foodborne bacterial species. The detection strategy shows significant potential for reliable food safety monitoring, making a meaningful contribution to public health and the food industry.

DeepX-Ray: A Comparative Study of Deep Learning-Based Classification and Segmentation Techniques for Automated Detection and Diagnosis of COVID-19 from Chest X-ray Images

The relentless spread of the SARS-CoV-2 virus, causing COVID-19, has underscored the urgent need for efficient early detection and diagnosis methods to mitigate its impact. While traditional techniques like RT-PCR are valuable, they often suffer from time-consuming processes. In this study, DeepX-Ray is presented, a comprehensive investigation into deep learning-based classification and segmentation approaches for the automated detection of COVID-19 from chest X-ray images. Specifically, the authors focus on constructing a custom convolutional neural network (CNN) model to distinguish between COVID-19 and standard X-ray images and benchmark its performance against established models. For segmentation tasks, the effectiveness of various backbone architectures, including ResNet34, ResNet101, DenseNet201, and ResNet50 within the UNet model framework, is explored, with ResNet50 exhibiting superior performance. Furthermore, a novel dataset comprising 7657 images sourced from three publicly available authentic datasets is introduced, and the labelMe tool is employed by the authors to generate ground truth mask datasets for 4137 images to facilitate segmentation of infected lung areas. The authors' custom CNN model achieves an outstanding classification accuracy of 100%, while the segmentation approach attains a mean Intersection over Union (IoU) score of 96.19%. These results underscore the efficacy of the proposed model in enabling early automatic detection and diagnosis of COVID-19, particularly in resource-constrained and remote settings where establishing traditional laboratories may be impractical. This research significantly advances medical imaging techniques for combating the COVID-19 pandemic.

Bi-level Analysis of Computed Tomography Images of Malignant Pleural Mesothelioma: Deep Learning-Based Classification and Subsequent Three-Dimensional Reconstruction

Abstract A bi-level analysis of computed tomography (CT) images of malignant pleural mesothelioma (MPM) is presented in this paper, starting with a deep learning-based system for classification, followed by a three-dimensional (3D) reconstruction method. MPM is a highly aggressive cancer caused by asbestos exposure, and accurate diagnosis and determination of the tumor’s volume are crucial for effective treatment. The proposed system employs a bi-level approach, utilizing machine learning and deep learning techniques to classify CT lung images and subsequently calculate the tumor’s volume. The study addresses challenges related to deep neural networks, such as the requirement for large and diverse datasets, hyperparameter optimization, and potential data bias. To evaluate performance, two convolutional neural network (CNN) architectures, Inception-v3 and ResNet-50, were compared in terms of their features and performance. Based on CT images, the second stage incorporates 3D volume reconstruction. The process is carried out by cropping, registering, filtering, and segmenting images. This study demonstrated the efficacy of the developed system by combining CNN optimizations with 3D image reconstruction. It is intended to improve the accuracy of MPM diagnosis and to assist in the determination of chemotherapy doses, both of which may result in improved outcomes for patients.

Fish Type and Disease Classification Using Deep Learning Model Based Customized CNN with Resnet 50 Technique

Aquaculture is a critical source of seafood production, addressing the global demand for fish products. Suggesting a Deep learning-based classification technique for fishes specifically Indian Major Carp (IMC) as Mrigala, Catla and Rohu is the major objective of this paper along with detecting the disease among them. This world inside hydrosphere has their own discrete living manner. Yet they are not untouched by diseases; fishes mostly affected when young carry pathogens which cause various infections naturally or due to environmental pollutants including chemical and hazardous waste. This paper proposed the classification and prediction of diseases of fishes in aquaculture using Deep Learning based customized Convolutional Neural Network with ResNet-50 model. The proposed model performance metric compared with recent state-of-art techniques. ResNet-50 classifies accurately the IMC and type of disease the fishes are suffering from.

A self-supervised learning framework based on masked autoencoder for complex wafer bin map classification

Wafer bin map (WBM) automatic classification is one of the critical challenges for semiconductor intelligent manufacturing. Many deep learning-based classification models have performed well in WBM classification, but all require a large amount of labeled data for training. Since real-world WBMs are highly complex and can be labeled correctly only by seasoned engineers, such requirements undermine the practical value of those methods. Several self-supervised learning methods have recently been proposed for WBM to improve classification performance. However, they still require much labeled data for fine-tuning and are only adapted for binary WBM with a single gross failure area. To address these limitations, this study introduces a self-supervised framework based on masked autoencoder (MAE) for complex WBMs with mixed bin signatures and multiple gross failure area patterns. A patchMC encoder is proposed to improve MAE’s representation ability for complex WBMs with mixed bin signatures. Moreover, the pre-trained MAE encoder with a multi-label classifier fine-tuned by labeled WBMs enables a few-shot classification of complex WBMs with multiple gross failure areas. Experimental validation of the proposed method is performed on a real-world complex WBM dataset from Intel Corporation. The results demonstrate that the proposed method can make good use of unlabeled WBMs and reduce the demand for labeled data to a few-shot level and, at the same time, guarantees a classification accuracy of more than 90%. By comparing MAE with other self-supervised learning methods, MAE outperforms other existing self-supervised methods for WBM data.

Data Augmentation Techniques for Accurate Action Classification in Stroke Patients with Hemiparesis.

Stroke survivors with hemiparesis require extensive home-based rehabilitation. Deep learning-based classifiers can detect actions and provide feedback based on patient data; however, this is difficult owing to data sparsity and heterogeneity. In this study, we investigate data augmentation and model training strategies to address this problem. Three transformations are tested with varying data volumes to analyze the changes in the classification performance of individual data. Moreover, the impact of transfer learning relative to a pre-trained one-dimensional convolutional neural network (Conv1D) and training with an advanced InceptionTime model are estimated with data augmentation. In Conv1D, the joint training data of non-disabled (ND) participants and double rotationally augmented data of stroke patients is observed to outperform the baseline in terms of F1-score (60.9% vs. 47.3%). Transfer learning pre-trained with ND data exhibits 60.3% accuracy, whereas joint training with InceptionTime exhibits 67.2% accuracy under the same conditions. Our results indicate that rotational augmentation is more effective for individual data with initially lower performance and subset data with smaller numbers of participants than other techniques, suggesting that joint training on rotationally augmented ND and stroke data enhances classification performance, particularly in cases with sparse data and lower initial performance.