Pneumonia Detection using Deep Learning

Leaf disease detection is a crucial task in modern agriculture, aiding in early diagnosis and prevention of crop infections. In this research paper, authors present a comprehensive study comparing nine widely used pre-trained models, namely DenseNet201, EfficientNetB3, EfficientNetB4, InceptionResNetV2, MobileNetV2, ResNet50, ResNet152, VGG16, and Xception, with our newly developed custom CNN (Convolutional Neural Network) for leaf disease detection. The objective is to determine if our custom CNN can match the performance of these established pre-trained models while maintaining superior efficiency. The authors trained and fine-tuned each pre-trained model and our custom CNN on a large dataset of labeled leaf images, covering various diseases and healthy states. Subsequently, the authors evaluated the models using standard metrics, including accuracy, precision, recall, and F1-score, to gauge their overall performance. Additionally, the authors analyzed computational efficiency regarding training time and memory consumption. Surprisingly, our results indicate that the custom CNN performs comparable to the pre-trained models, despite their sophisticated architectures and extensive pre-training on massive datasets. Moreover, our custom CNN demonstrates superior efficiency, outperforming the pre-trained models regarding training speed and memory requirements. These findings highlight the potential of custom CNN architectures for leaf disease detection tasks, offering a compelling alternative to the commonly used pre-trained models. The efficiency gains achieved by our custom CNN can be beneficial in resource-constrained environments, enabling faster inference and deployment of leaf disease detection systems. Overall, our research contributes to the advancement of agricultural technology by presenting a robust and efficient solution for the early detection of leaf diseases, thereby aiding in crop protection and yield enhancement.

Rapid and accurate assessment of endotracheal tube (ETT) location is essential in the intensive care unit (ICU) setting, where timely identification of a mispositioned support device may prevent significant patient morbidity and mortality. This study proposes a series of deep learning-based algorithms which together iteratively identify and localize the position of an ETT relative to the carina on chest radiographs. Using the open-source MIMIC Chest X-Ray (MIMIC-CXR) dataset, a total of 16,000 patients were identified (8000 patients with an ETT and 8000 patients without an ETT). Three different convolutional neural network (CNN) algorithms were created. First, a regression loss function CNN was trained to estimate the coordinate location of the carina, which was then used to crop the original radiograph to the distal trachea and proximal bronchi. Second, a classifier CNN was trained using the cropped inputs to determine the presence or absence of an ETT. Finally, for radiographs containing an ETT, a third regression CNN was trained to both refine the coordinate location of the carina and identify the location of the distal ETT tip. Model accuracy was assessed by comparing the absolute distance of prediction and ground-truth coordinates as well as CNN predictions relative to measurements documented in original radiologic reports. Upon five-fold cross validation, binary classification for the presence or absence of ETT demonstrated an accuracy, sensitivity, specificity, PPV, NPV, and AUC of 97.14%, 97.37%, 96.89%, 97.12%, 97.15%, and 99.58% respectively. CNN predicted coordinate location of the carina, and distal ETT tip was estimated within a median error of 0.46 cm and 0.60 cm from ground-truth annotations respectively. Overall final CNN assessment of distance between the carina and distal ETT tip was predicted within a median error of 0.60 cm from manual ground-truth annotations, and a median error of 0.66 cm from measurements documented in the original radiology reports. A serial cascaded CNN approach demonstrates high accuracy for both identification and localization of ETT tip and carina on chest radiographs. High performance of the proposed multi-step strategy is in part related to iterative refinement of coordinate localization as well as explicit image cropping which focuses algorithm attention to key anatomic regions of interest.

Particulate matter with a diameter less than 10 micrometers (PM10) is today an important subject of study, mainly because of its increasing concentration and its impact on environment and public health. This article summarizes the usage of convolutional neural networks (CNNs) to forecast PM10 concentrations based on atmospheric variables. In this particular case-study, the use of deep convolutional neural networks (both 1D and 2D) was explored to probe the feasibility of these techniques in prediction tasks. Furthermore, in this contribution, an ensemble method called Bagging (BEM) is used to improve the accuracy of the prediction model. Lastly, a well-known technique for PM10 forecasting, called multilayer perceptron (MLP) is used as a comparison to show the feasibility, accuracy, and robustness of the proposed model. In this contribution, it was found that the CNNs outperforms MLP, especially when they are executed using ensemble models.

Content filtering is gaining popularity due to easy exposure of explicit visual contents to the public. Excessive exposure of inappropriate visual contents can cause devastating effects such as the growth of improper mindset and rise of societal issues such as free sex, child abandonment and rape cases. At present, most of the broadcasting media sites are hiring censorship editors to label graphic contents manually. Nevertheless, the efficiency is limited by factors such as the attention span of humans and the training required for the editors. This paper proposes to study the effect of usage of Convolutional Neural Network (CNN) as feature extractor coupled with Support Vector Machine (SVM) as classifier in an automated pornographic detection system. Three CNN architectures: Mobile Net, Visual Geometry Group-19 (VGG-19) and Residual Network-50 Version 2 (ResNet50_V2), and two classifiers: CNN and SVM were utilized to explore the combination that produce the best result. Frames of films fed as input into the CNN were classified into two groups: porn or non-porn. The best accuracy was 92.80% obtained using fine-tuned ResNet50_V2 as feature extractor and SVM as classifier. Transfer learning and SVM have improved the CNN model by approximately 10%.

Tauopathies are characterised by a progressive accumulation of hyperphosphorylated tau. However, early and intermediate stages remain challenging to quantify due to subtle and heterogeneous morphological characteristics. This study evaluates a deep learning framework for classifying multiple temporal stages of tauopathy progression using AT8 (anti-phospho-tau antibody)-stained cortical micrographs in a controlled traumatic brain injury mouse model - an underexplored application. Three convolutional neural network (CNN) architectures were examined: a custom CNN and two transfer-learning models (InceptionV3 and DenseNet). Images were grouped into four post-injury stages: 1day, 1week, 1month and 3months. Preprocessing included normalisation, augmentation and oversampling to address imbalance. Performance was assessed using stratified k-fold cross-validation with accuracy, macro-F1, per-class F1, and one-vs-rest area under the receiver operating characteristic curve (AUC). DenseNet achieved the best overall performance (accuracy = 70.9%, macro-F1 = 0.68) with strong discrimination for the 1-week stage (F1 = 0.95). All models showed limited separability in the earliest post-injury stage (1day), while intermediate to late stages (1-3months) exhibited partial overlap, consistent with the progressive nature of tau accumulation. These results indicate that deep learning, particularly transfer learning, offers a scalable approach for automated temporal staging of tauopathy in preclinical histology. Although the results are based on internal cross-validation without independent animal-level identifiers or external cohorts, the proposed framework provides a reliable foundation for incorporating CNN-based analysis into digital neuropathology workflows. Larger multi-centre datasets and slide-level modelling will be required to assess generalisation and support applications in early detection, longitudinal tracking, and treatment evaluation of tau-related neurodegeneration.

目的 基于计算机的胸腔X线影像疾病检测和分类目前存在误诊率高，准确率低的问题。本文在视觉Transformer（vision Transformer，ViT）预训练模型的基础上，通过迁移学习方法，实现胸腔X线影像辅助诊断，提高诊断准确率和效率。方法 选用带有卷积神经网络（convolutional neural network，CNN）的ViT模型，其在超大规模自然图像数据集中进行了预训练；通过微调模型结构，使用预训练的ViT模型参数初始化主干网络，并迁移至胸腔X线影像数据集中再次训练，实现疾病多标签分类。结果 在IU X-Ray数据集中对ViT迁移学习前、后模型平均AUC（area under ROC curve）得分进行对比分析实验。结果表明，预训练ViT模型平均AUC得分为0.774，与不使用迁移学习相比提升了0.208。并针对模型结构和数据预处理进行了消融实验，对ViT中的注意力机制进行可视化，进一步验证了模型有效性。最后使用Chest X-Ray14和CheXpert数据集训练微调后的ViT模型，平均AUC得分为0.839和0.806，与对比方法相比分别有0.014～0.031的提升。结论 与其他方法相比，ViT模型胸腔X线影像的多标签分类精确度更高，且迁移学习可以在降低训练成本的同时提升ViT模型的分类性能和泛化性。消融实验与模型可视化表明，包含CNN结构的ViT模型能重点关注有意义的区域，高效获取胸腔X线影像的视觉特征。;Objective The chest X-ray-relevant screening and diagnostic method is essential for radiology nowadays. Most of chest X-ray images interpretation is still restricted by clinical experience and challenged for misdiagnose and missed diagnoses. To detect and identify one or more potential diseases in images automatically，it is beneficial for improving diagnostic efficiency and accuracy using computer-based technique. Compared to natural images，multiple lesions are challenged to be detected and distinguished accurately in a single image because abnormal areas have a small proportion and complex representations in chest X-ray images. Current convolutional neural network（CNN）based deep learning models have been widely used in the context of medical imaging. The structure of the CNN convolution kernel has sensitive to local detail information，and it is possible to extract richer image features. However，the convolution kernel cannot be used to get global information，and the features-extracted are restricted of redundant information like its relevance of background， muscles，and bones. The model’s performance in multi-label classification tasks are affected to a certain extent. At present，the vision Transformer（ViT）model has achieved its priorities in computer vision-related tasks. The ViT can be used to capture information simultaneously and effectively for multiple regions of the entire image. However，it is required to use large-scale dataset training to achieve good performance. Due to some factors like patient privacy and manual annotate costs，the size of the chest X-ray image data set has been limited. To reduce the model's dependence on data scale and improve the performance of multi-label classification，we develop the CNN-based ViT pre-training model in terms of the transfer learning method for diagnosis-assisted of chest X-ray image and multi-label classification. Method The CNN-based ViT model is pre-trained on a huge scale ground truth dataset，and it is used to obtain the initial parameters of the model. The model structure is fine-tuned according to the features of chest X-ray dataset. A 1×1 convolution layer is used to convert the chest X-ray images channels between 1 to 3. The number of output nodes of the linear layer in the classifier is balanced from 1 000 to the number of chest X-ray classification labels，and the Sigmoid is used as an activation function. The parameters of the backbone network are initialized in terms of the pre-trained ViT model parameters，and it is trained in the chest X-ray dataset after that to complete multi-label classification. The experiment is configured of Python3. 7 and PyTorch1. 8 to construct the model and RTX3090 GPU for training. Stochastic gradient descent（SGD）optimizer，binary cross-entropy（BCE）loss function，an initial learning rate of 1E-3，the cosine annealing learning rate decay are used. For training，each image is scaled to a size of 512×512 pixels，and a 224×224 pixels area and it is then cropped in random as the model input，and data augmentation is performed randomly by some of the flipping，perspective transformation， shearing，translation，zooming，and changing brightness. For testing，the chest X-ray image is scaled to 256×256 pixels and center crop a 224×224 area to input the trained model. Result The experiment is performed on the IU X-Ray，which is a small-scale chest X-ray dataset. This model is evaluated in quantitative using the average of area under ROC curve （AUC）scores across all classification labels. The results show that the average AUC score of the pre-trained ViT model is 0. 774. The accuracy and training efficiency of the non-pre-trained ViT model is dropped significantly. The average AUC score is reached to 0. 566 only，which is 0. 208 lower. In addition，the attention mechanism heat map is generated based on the ViT model，which can strengthen the interpretability of the model. A series of ablation experiments are carried out for data augmentation，model structure，and batch size design. The fine-tuned ViT model is trained on the Chest-Ray14 and CheXpert dataset as well. The average AUC score is reached to 0. 839 and 0. 806，which is optimized by 0. 014 and 0. 031. Conclusion A pre-trained ViT model is used for the multi-label classification of chest X-ray images via transfer learning. The experimental results illustrate that the ViT has its stronger multi-label classification performance in chest Xray images，and its attention mechanism is beneficial for lesions precision-focused like the interior of the chest cavity and the heart. Transfer learning is potential to improve the classification performance and model generalization of the ViT in small-scale datasets，and the training cost is reduced greatly. Ablation experiments demonstrate that the incorporated model of CNN and Transformer has its priority beyond single-structure model. Data enhancement and the batch size cutting can improve the performance of the model，but smaller scale of batch is still interlinked to longer training span. To improve the model's ability，we predict that future research direction can be focused on the extraction for complex disease and highlevel semantic information，such as their small lesions，disease location，and severity.

This study investigates the use of convolutional neural networks to automatically detect malaria-infected cells in blood smear images, offering an alternative to manual diagnosis, which depends on specialized professionals and adequate infrastructure. Manual diagnosis is time-consuming and prone to human errors, especially in malaria-endemic regions with limited resources. Automated approaches based on convolutional neural networks provide a promising solution to optimize the diagnostic process and improve access to rapid treatment in remote areas. The research evaluates the performance of different convolutional neural network architectures for malaria diagnosis, following the Cross Industry Standard Process for Data Mining methodology to structure preprocessing, modeling, and model evaluation. Preprocessing involved normalization and data augmentation techniques to enhance sample quality and diversity. Two architectures were compared: a customized convolutional neural network designed to balance computational efficiency and accuracy, and an adapted VGG16, recognized for its advanced image feature extraction capabilities. Both models were trained and evaluated using a robust dataset of blood cell images. The customized network achieved 95.6% accuracy, outperforming similar models in the literature and demonstrating its practicality for low-resource settings. It also exhibited high precision, recall, and F1-score, ensuring reliable and balanced classification of infected and healthy cells. This approach reduces reliance on specialists and advanced equipment, making malaria diagnosis more accessible and efficient. The findings position the customized convolutional neural network as a viable solution for automated malaria diagnosis, combining simplicity with high performance and offering significant potential for improving healthcare in endemic regions.

The use of Convolutional Neural Networks (CNNs) for image classification is wellestablished in defect detection within manufacturing environments. However, their application in assembly processes remains underexplored. This study investigates the effectiveness of using relatively smaller CNNs for detecting assembly defects by testing multiple existing pre-trained CNNs and a custom CNN on a dataset of model train seat assembly images. The dataset includes common assembly defects such as missing, rotated, and swapped parts. Despite implementing various data augmentation and image processing techniques, such as cropping, normalization, and image transforms, and making several modifications to the models, the existing techniques struggled to accurately predict defects while providing the correct rationale for their predictions. The Grad-CAM analysis revealed that the models often focused on irrelevant features, highlighting the challenges of defect detection in complex assembly environments. These findings indicate the need for more robust machine learning approaches capable of handling high levels of noise and variations typical of realworld assembly conditions. This study underscores the limitations of current CNN-based defect detection methods in uncontrolled assembly settings and the necessity for further research to develop more reliable solutions.

With the rise of crimes associated with Automated Teller Machines (ATMs), security reinforcement by surveillance techniques has been a hot topic on the security agenda. As a result, cameras are frequently installed with ATMs, so as to capture the facial images of users. The main objective is to support follow-up criminal investigations in the event of an incident. However, in the case of miss-use, the user’s face is often occluded. Therefore, face occlusion detection has become very important to prevent crimes connected with ATM usage. Traditional approaches to solving the problem typically comprise a succession of steps: localization, segmentation, feature extraction and recognition. This paper proposes an end-to-end facial occlusion detection framework, which is robust and effective by combining region proposal algorithm and Convolutional Neural Networks (CNN). The framework utilizes a coarse-to-fine strategy, which consists of two CNNs. The first CNN detects the head element within an upper body image while the second distinguishes which facial part is occluded from the head image. In comparison with previous approaches, the usage of CNN is optimal from a system point of view as the design is based on the end-to-end principle and the model operates directly on image pixels. For evaluation purposes, a face occlusion database consisting of over 50[Formula: see text]000 images, with annotated facial parts, was used. Experimental results revealed that the proposed framework is very effective. Using the bespoke face occlusion dataset, Aleix and Robert (AR) face dataset and the Labeled Face in the Wild (LFW) database, we achieved over 85.61%, 97.58% and 100% accuracies for head detection when the Intersection over Union-section (IoU) is larger than 0.5, and 94.55%, 98.58% and 95.41% accuracies for occlusion discrimination, respectively.

As more and more aircraft are used, using an efficient and accurate tool to identify aircraft types will help manage air safety. As a basic framework for machine learning, a Convolutional neural network is widely used to make image recognition. This paper presents a method to classify different types of military and civilian aircraft using neural networks and explore the performance differences by changing batch size and learning rate. Five models are selected to achieve classification for ten types of aircraft images from the Fine-Grained Visual Classification of Aircraft (FGVC)-Aircraft dataset. Except for the existing models like Visual Geometry Group 16-layer Network (VGG16), Residual Network with 152 Layers (Resnet152), Densely Connected Convolutional Networks (DenseNet), and Efficient Neural Network (EfficientNet), a customized Convolutional Neural Network (CNN) is also designed to complete the image classification task. The parameters used to demonstrate performance are latency, throughput, model convergence speed, accuracy, f1-score, and confusion matrix. By analyzing the results, the customized CNN performs best among these five models, having both good accuracy and latency. VGG16 and DenseNet perform well although each has certain deficiencies in terms of latency and accuracy respectively. The performance of EfficientNet and Resnet152 is not good, and their accuracy is relatively lower compared to other models. Therefore, the best model can be obtained for solving this task and make predictions on the performance of each model when classifying pictures of more types of aircraft.

Pneumonia is an infection in one or both the lungs because of virus or bacteria through breathing air. It inflames air sacs in lungs which fill with fluid which further leads to problems in respiration. Pneumonia is interpreted by radiologists by observing abnormality in lungs in case of fluid in Chest X-Rays. Computer Aided Detection Diagnosis (CAD) tools can assist radiologists by improving their diagnostic accuracy. Such CAD tools use neural networks which are trained on Chest X-Ray dataset to classify a Chest X-Ray into normal or infected with Pneumonia. Convolution neural networks have shown remarkable performance in object detection in an image. Quaternion Convolution neural network (QCNN) is a generalization of conventional convolution neural networks. QCNN treats all three channels (R, G, B) of color image as a single unit and it extracts better representative features and which further improves classification. In this paper, we have trained Quaternion residual network on a publicly available large Chest X-Ray dataset on Kaggle repository and obtained classification accuracy of 93.75% and F-score of .94. We have also compared our performance with other CNN architectures. We found that classification accuracy was higher with Quaternion Residual network when we compared it with a real valued Residual network.

Pest infestation is a significant challenge in agriculture, causing substantial economic losses and impacting crop yields. Manual pest identification is time-consuming and error-prone, especially in large-scale farming. This study presents a hybrid deep learning approach to automate pest detection and classification using image data. It employs a pre-trained VGG16 model for robust feature extraction, followed by a custom Convolutional Neural Network (CNN) for classification. The VGG16 model leverages transfer learning to capture high-level visual patterns from pest images, while the custom CNN is trained on these features to distinguish between multiple pest classes. The proposed pipeline is optimized using data augmentation, early stopping, and adaptive learning techniques. Performance is evaluated using metrics such as accuracy, precision, recall, and F1-score. The model demonstrates high accuracy and robustness on agricultural image datasets, making it a scalable solution for smart farming systems. Index Terms: Pest Detection, Deep Learning, VGG16, Convolutional Neural Network, Transfer Learning, Image Classification, Precision Agriculture, Feature Extraction.

Satellite image classification plays a crucial role in applications such as land cover mapping, urban planning, and environmental monitoring. This project focuses on the development of SpectrumNet, a custom Convolutional Neural Network (CNN) designed to classify satellite images from the EuroSAT dataset into ten distinct land-use categories. The primary goal is to improve the accuracy and efficiency of satellite image classification through the implementation of advanced preprocessing techniques, optimized training strategies, and multiple network configurations. By utilizing deep learning methodologies, SpectrumNet aims to provide reliable insights for real-world applications in remote sensing, geospatial analysis, and environmental studies. The project strives to enhance the ability to analyze and interpret large-scale satellite image data, offering valuable information for decision-making in various fields. Key Words: Deep Learning, Convolutional Neural Networks, EuroSAT, SpectrumNet, Geospatial Analysis, Land Cover Mapping, Environmental Monitoring, Urban Planning.

Deep convolutional neural networks (DCNNs) for diagnosis of disease on chest radiographs (CXR) have been shown to be biased against males or females if the datasets used to train them have unbalanced sex representation. Prior work has suggested that DCNNs can predict sex on CXR, which could aid forensic evaluations, but also be a source of bias. To (1) evaluate the performance of DCNNs for predicting sex across different datasets and architectures and (2) evaluate visual biomarkers used by DCNNs to predict sex on CXRs. Chest radiographs were obtained from the Stanford CheXPert and NIH Chest XRay14 datasets which comprised of 224,316 and 112,120 CXRs, respectively. To control for dataset size and class imbalance, random undersampling was used to reduce each dataset to 97,560 images that were balanced for sex. Each dataset was randomly split into training (70%), validation (10%), and test (20%) sets. Four DCNN architectures pre-trained on ImageNet were used for transfer learning. DCNNs were externally validated using a test set from the opposing dataset. Performance was evaluated using area under the receiver operating characteristic curve (AUC). Class activation mapping (CAM) was used to generate heatmaps visualizing the regions contributing to the DCNN's prediction. On the internal test set, DCNNs achieved AUROCs ranging from 0.98 to 0.99. On external validation, the models reached peak cross-dataset performance of 0.94 for the VGG19-Stanford model and 0.95 for the InceptionV3-NIH model. Heatmaps highlighted similar regions of attention between model architectures and datasets, localizing to the mediastinal and upper rib regions, as well as to the lower chest/diaphragmatic regions. DCNNs trained on two large CXR datasets accurately predicted sex on internal and external test data with similar heatmap localizations across DCNN architectures and datasets. These findings support the notion that DCNNs can leverage imaging biomarkers to predict sex and potentially confound the accurate prediction of disease on CXRs and contribute to biased models. On the other hand, these DCNNs can be beneficial to emergency radiologists for forensic evaluations and identifying patient sex for patients whose identities are unknown, such as in acute trauma.

Optical inspection using unmanned aerial vehicles is a popular trend for detection of surface defects on industrial infrastructure, and full automation is the next step in order to improve potential and reduce costs. Binary classification of the obtained visual image data into defect and defect-free sets is one sub-task of these systems and is still often carried out either completely manually by an expert or by using pre-defined features as classifiers for automatic image post-processing. In contrast, deep convolutional neural networks (CNN) are able to perform both the feature extraction and classification tasks simultaneously by internal hierarchical learning. In this work, custom CNNs and a transfer-learned AlexNet are applied to an experimental data set with artificial defects in order to analyze suitability and required network depth for such surface inspections. Experiments are performed using a set of 2500 camera images total, yielding a classification accuracy of up to 99 % with a single CNN. Thereby, the amount of actual defects that are falsely classified as negative are minimized. Results proof the general effectiveness of the methodology and motivate the application to specific inspection tasks.