A Hybrid Prototype Fusion Network (HPFN) developed based on the ConvNeXt-Tiny architecture is proposed, and deep feature representation and prototype-based similarity calculation are combined in a single decision mechanism, outperforming both the compared deep learning architectures and traditional feature-based methods.
Abstract
Diagnosis of pneumonia from Chest X-Ray images holds a significant place in clinical practice due to its low cost and widespread availability. However, achieving high performance with deep learning-based methods generally requires a large amount of labeled data, which constitutes a significant limitation in medical image analysis. In this thesis, the performance of deep learning and traditional machine learning approaches for diagnosing pneumonia from Chest X-Ray images under conditions of low-label data is comprehensively evaluated. For this purpose, a Hybrid Prototype Fusion Network (HPFN) developed based on the ConvNeXt-Tiny architecture is proposed, and deep feature representation and prototype-based similarity calculation are combined in a single decision mechanism. Furthermore, the proposed model is compared with Xception, VGG16, and ResNet50 architectures, and traditional approaches consisting of Support Vector Machine, Logistic Regression, and Extreme Gradient Boosting classifiers using SIFT, KAZE, and HOG features are also analyzed on the same dataset. All experiments were performed using the Chest X-Ray (Pneumonia) dataset, and the models were evaluated using accuracy, precision, sensitivity, and F1-score measures. Experimental results showed that the proposed HPFN model achieved 96.38% accuracy, 96.23% precision, 97.95% sensitivity, and 97.08% F1-score, outperforming both the compared deep learning architectures and traditional feature-based methods. Literature comparisons also revealed that the proposed approach is an effective computer-aided diagnostic method providing reliable, stable, and high-accuracy data under low-label data conditions.
Pneumonia remains one of the leading causes of respiratory illness worldwide and requires timely diagnosis to reduce
disease severity and mortality. Interpretation of chest X-ray images is a routine diagnostic procedure; however, manual
examination can be time-consuming and is influenced by the experience of radiologists. Computer-aided diagnostic systems
based on artificial intelligence have therefore attracted considerable attention as supportive tools for clinical decision-making.
This research presents a hybrid framework that combines deep feature extraction with traditional machine learning techniques
for automated pneumonia detection from chest X-ray images. Initially, chest X-ray images are preprocessed and analysed using
an EfficientNetV2 convolutional neural network to learn representative image features. Instead of directly performing end-toend classification, the extracted deep features are used to train three supervised machine learning classifiers: Random Forest,
Support Vector Machine (SVM), and Extreme Gradient Boosting (XGBoost). This hybrid strategy combines the feature
representation capability of deep learning with the classification efficiency of conventional machine learning algorithms. To
improve model transparency, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed to highlight image regions
that contribute most to the prediction. Furthermore, the selected classifier is integrated into a Streamlit-based web application
that enables users to upload chest X-ray images and obtain real-time diagnostic predictions.
Experimental evaluation demonstrates that the Support Vector Machine classifier achieved the highest performance among the
evaluated models, with an accuracy of 89.74%, precision of 86.22%, recall of 99.49%, F1-score of 92.38%, and ROC-AUC of
98.21%, indicating strong capability for distinguishing pneumonia from normal chest radiographs. The proposed framework
illustrates that combining deep feature extraction with machine learning classifiers can provide accurate, interpretable, and
computationally efficient pneumonia detection while supporting practical clinical deployment.
K. H. Veen, Pravitha R Prasad· International Journal for Re...· 0 citations
Pneumonia is a significant cause of mortality, particularly in children under five. Accurate detection of pneumonia from Chest X-ray (CXR) images is crucial in mitigating diagnostic errors common in manual radiographic analysis. This study leverages deep learning models to enhance the detection of multiclass pneumonia (normal, bacterial, and viral) using CXR images. We utilized a dataset comprising 5,863 multiclass pneumonia CXR samples. Data augmentation and regularization techniques were applied to address class imbalance and overfitting. Pre-trained models, including EfficientNet, MobileNet, RegNet, and ViT, were fine-tuned using the PyTorch framework, with transfer learning employed to optimize training. Model performance was assessed using accuracy, precision, recall, and specificity. The fine-tuned models achieved high classification accuracy, with EfficientNet and ConvNext models achieving accuracy scores of 83% and 82%, respectively. Data augmentation and regularization significantly improved the models' generalization, reducing overfitting and improving predictive accuracy. The proposed deep learning models provide an efficient and accurate tool for multiclass pneumonia detection from CXRs. These models have the potential to support healthcare professionals in making more accurate diagnoses.
Timothy Karani, Stephen Waithaka· Journal of the Kenya Nationa...· 0 citations
Background: COVID-19, pneumonia, and TB (tuberculosis) are still the big killers of people suffering from chest disease and continue to be a serious health challenge globally. A timely diagnosis leads to timely treatment and improved patient outcomes. Chest X-ray (CXR) imaging is widely used for diagnostic purposes due to its speed, low cost, and availability in most healthcare facilities. Manual reading of CXR images is, however, challenging because of the similarity in the presentation of radiographic features across various chest diseases.
Methods: This research introduces a hybrid ensemble learning approach to classify chest X-ray images into four classes—Normal, COVID-19, Pneumonia, and Tuberculosis. Three Deep CNN network models, namely Xception, AlexNet, and EfficientNet-B0, were used for deep feature extraction. Additionally, texture features of the images were extracted using Gabor filters. The deep and texture features were combined and classified using logistic regression and a stacking ensemble learning approach. A publicly available chest X-ray image database containing 7,135 X-rays was used, with six-fold stratified cross-validation to assess the proposed approach.
Results: The ensemble models outperformed the individual CNN models. The Average Ensemble produced the best results with an accuracy of 91.18%, an Average Precision (AP) of 96.75%, and an Area Under the ROC Curve (AUC) of 98.87%. The proposed model performs well across all four disease classes. It exhibited high sensitivity in detecting Tuberculosis with considerable stability in classifying Normal, COVID-19, and Pneumonia.
Conclusion: The proposed framework demonstrates the effectiveness of integrating deep learning features, Gabor texture features, and ensemble learning for improved chest X-ray image classification. This can help computer-assisted diagnostics systems and aid medical workers in identifying chest diseases early.
Abdul Rehman Khan Tareen, Muhammad Laiq Ur Rahman Shahid, Muhammad Hamza Zafar et al.· Allied Medical Research Jour...· 0 citations
Pulmonary infections, especially pneumonia constitute a major worldwide health burden and need early and accurate diagnosis in order to minimize disease severity and death. Chest radiographs are regularly performed for screening of pulmonary infections; however, the interpretation of the radiographs by manual techniques is time consuming and subject to inter-observer variability, and this has motivated the need for automated and reliable diagnostic systems. In the current work, a hybrid deep feature learning framework for clinical-level differentiation of pulmonary infections from the chest X-ray images is proposed by effectively incorporating local and global feature representations. The proposed model consists of EfficientNet-B3 for extracting deep spatial features and a Vision Transformer to extract long-range contextual dependencies, a feature fusion strategy towards better representation learning. The framework is tested on a publicly available chest X-ray dataset of Normal and Pneumonia classes. Experimental results show the high classification accuracy of the proposed hybrid model is 98.3% with high precision, recall, F1-score, and AUC performance compared with traditional CNN, ResNet, auto-encoder and transformer-based model. The results underscore the clinical reliability, good generalization capacity and possible applicability of the proposed framework to automated pulmonary infection screening and decision support systems.
T. Srinivas, Faaleha Heba Fakruddin, Mettu Jhansi Rani et al.· 2026 International Conferenc...· 0 citations
Pneumonia screening from chest X-ray (CXR) images is clinically important but often suffers from limited data and class imbalance in public benchmarks. This work develops a transfer-learning-based binary classifier using ResNet50 pretrained on ImageNet. Images are resized to 224×224 and normalized to [0,1]. Online augmentation (rotation, zoom, and shifts) is applied during training. To mitigate imbalance, class weights computed from the training labels are used in the loss. We fine-tune the network by freezing the early layers and updating higher-level layers with a small learning rate (Adam, 1e- 4) and early stopping. On the held-out test set (624 images), the model achieves about 0.88 accuracy. For the pneumonia class, precision, recall, and F1-score reach approximately 0.93, 0.88, and 0.90, respectively. The results indicate that combining class-weighted training with fine-tuned ResNet50 provides a practical baseline for automated pneumonia screening on CXR images.
Danning Dong· International Conference on...· 0 citations
Background: Deep learning models, particularly convolutional neural networks (CNNs), have shown promising performance for pneumonia detection using chest X-ray images. However, the impact of preprocessing, architecture selection, data augmentation, and ensemble strategies has not been systematically evaluated. This study investigated how these factors affect model robustness and diagnostic performance. Methods: A public pediatric chest X-ray dataset was used to systematically evaluate pixel normalization methods, six CNN architectures, progressive data augmentation strategies for class imbalance, and both feature-level and decision-level ensemble approaches. Model performance was assessed by considering not only overall classification accuracy but also clinically relevant risk metrics, particularly false-negative rates. Results: Pixel normalization to the 0–1 range improved model convergence, while Xception and InceptionV3 achieved the best overall performance. Model-specific augmentation strategies were more effective than a fixed 1:1 class ratio for reducing false negatives. Feature-level ensembles tended to overfit, whereas decision-level ensembles provided more stable but only modest performance improvements. Conclusions: These findings demonstrate that reliable medical AI systems require systematic optimization of preprocessing techniques, model architecture, data augmentation strategies, and clinically meaningful evaluation metrics rather than maximizing a single performance indicator. The proposed framework provides practical guidelines for developing robust deep learning models for pneumonia diagnosis in clinical settings.
YongJun Kim, Ji-Yeoun Lee· BioMedInformatics· 0 citations