Deep Learning and X‐Ray Imaging Innovations for Pneumonia Infection Diagnosis: Introducing DeepPneuNet

Computational Intelligence, Journal Year: 2025, Volume and Issue: 41(1)

Published: Feb. 1, 2025

ABSTRACT This paper aims to develop a new deep learning model (DeepPneuNet) and evaluate its performance in predicting Pneumonia infection diagnosis based on patients' chest x‐ray images. We have collected 5856 images that are labeled as either “pneumonia” or “normal” from public forum. Before applying the DeepPneuNet model, necessary feature extraction mapping been done input Conv2D layers with 1 × kernel size followed by ReLU activation functions make up model. These charge of recognizing important patterns features A MaxPooling 2D procedure is applied minimize spatial maps after every two layers. The sparse categorical cross‐entropy loss function trains Adam optimizer rate 0.001 used optimize it. provides 90.12% accuracy for set real‐life test With 9,445,586 parameters, exhibits excellent parameter efficiency. more lightweight computationally efficient alternative when compared other pre‐trained models. accuracies our proposed some state‐of‐the‐art advantageous than existing models respect accuracy, precision, recall, F ‐score, training execution time.

Language: Английский

---

Explainable hybrid transformer for multi-classification of lung disease using chest X-rays

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 24, 2025

Lung disease is an infection that causes chronic inflammation of the human lung cells, which one major death around world. Thoracic X-ray medical image a well-known cheap screening approach used for detection. Deep learning networks, are to identify features in X-rays images, diagnosing variety diseases, playing increasingly important role assisting clinical diagnosis. This paper proposes explainable transformer with hybrid network structure (LungMaxViT) combining CNN initial stage block SE improve feature recognition predicting Chest images multiple classification. We contrast four classical pre-training models (ResNet50, MobileNetV2, ViT and MaxViT) through transfer based on two public datasets. The LungMaxVit, maxvit pre-trained ImageNet 1K datasets, fine-tuning hyperparameters both LungMaxVit outperforms all mentioned models, achieving classification accuracy 96.8%, AUC scores 98.3%, F1 96.7% COVID-19 dataset, while 93.2% 70.7% 14 dataset. distinguishes by its superior performance terms Accuracy, F1-score compared other hybrids Networks. Several enhancement techniques, such as CLAHE, flipping denoising, employed our study. Grad-CAM visual technique leveraged represent heat map detection, explaining consistency among doctors neural treatment from X-ray. shows robust results generalization detecting lesions images.

Language: Английский

---

Advancing Pulmonary Infection Diagnosis: A Comprehensive Review of Deep Learning Approaches in Radiological Data Analysis

Archives of Computational Methods in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 13, 2025

Language: Английский

---

Fine-tuned deep transfer learning: an effective strategy for the accurate chronic kidney disease classification

PeerJ Computer Science, Journal Year: 2025, Volume and Issue: 11, P. e2800 - e2800

Published: April 8, 2025

Kidney diseases are becoming an alarming concern around the globe. Premature diagnosis of kidney disease can save precious human lives by taking preventive measures. Deep learning demonstrates a substantial performance in various medical disciplines. Numerous deep approaches suggested literature for accurate chronic classification compromising on architectural complexity, speed, and resource constraints. In this study, transfer is exploited incorporating unexplored yet effective variants ConvNeXt EfficientNetV2 efficient diseases. The benchmark computed tomography (CT)-based database containing 12,446 CT scans tumor, stone cysts, normal patients utilized to train designed fine-tuned networks. However, due highly imbalanced distribution images among classes, operation data trimming balancing number each class, which essential designing unbiased predictive network. By utilizing pre-trained models our specific task, training time reduced leading computationally inexpensive solution. After comprehensive hyperparameters tuning with respect changes rates, batch sizes, optimizers, it depicted that EfficientNetV2B0 network 23.8 MB size only 6.2 million parameters shows diagnostic achieving generalized test accuracy 99.75% balanced database. Furthermore, attains high precision, recall, F1-score 99.75%, 99.63%, respectively. Moreover, final ensures its scalability impressive 99.73% set original dataset as well. Through extensive evaluation proposed strategy, concluded design outperforms counterparts terms computational efficiency tasks. serves accurate, efficient, solution tailored real-time deployment or mobile edge devices.

Language: Английский

---

Diagnosis of pneumonia from chest X-ray images using YOLO deep learning

Frontiers in Neurorobotics, Journal Year: 2025, Volume and Issue: 19

Published: April 28, 2025

Early and accurate diagnosis of pneumonia is crucial to improve cure rates reduce mortality. Traditional chest X-ray analysis relies on physician experience, which can lead subjectivity misdiagnosis. To address this, we propose a novel method using the Fast-YOLO deep learning network that introduced. First, constructed dataset containing five categories applied image enhancement techniques increase data diversity model’s generalization ability. Next, YOLOv11 structure was redesigned accommodate complex features images. By integrating C3k2 module, DCNv2, DynamicConv, effectively enhanced feature representation reduced computational complexity (FPS increased from 53 120). Experimental results subsequently show our outperforms other commonly used detection models in terms accuracy, recall, mAP, offering better real-time capability clinical application potential.

Language: Английский

---

Deep learning approaches for classification tasks in medical X-ray, MRI, and ultrasound images: a scoping review

BMC Medical Imaging, Journal Year: 2025, Volume and Issue: 25(1)

Published: May 7, 2025

Language: Английский

---

Pneumonia Detection in Chest X-Ray Images with Deep Learning

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 257 - 271

Published: Jan. 1, 2025

Language: Английский

---

Attention-Enhanced Hybrid Cnn-Lstm Network with Self-Adaptive Cbam for Covid-19 Diagnosis

Published: Jan. 1, 2025

Language: Английский

---

FA-Net: A Fuzzy Attention-aided Deep Neural Network for Pneumonia Detection in Chest X-Rays

Published: June 26, 2024

Language: Английский

---

Enhancing Paediatric Pneumonia Detection and Classification Using Customized CNNs and Transfer Learning Based Ensemble Models

International Research Journal of Multidisciplinary Technovation, Journal Year: 2024, Volume and Issue: unknown, P. 38 - 53

Published: Oct. 30, 2024

Pneumonia is one of the most prominent causes mortality in children who are below age five years parts globe. Hence, adequate pneumonia diagnosis paramount importance and what drove this research effort which has led to development two transfer learning-based ensemble models. One proposed models classifies chest radiographs into normal cases with outputs being generated from VGG-16, Inception-v3, custom-made convolutional neural networks, PneumoNet-v1 PneumoNet-v2. The second model distinguishes bacterial viral help Xception, MobileNet-v2, PneumoNet-v1. To accomplish aim study, Guangzhou Women Children’s Medical Center dataset (Kermany Dataset) was used benchmark performance. PneumoNet-v2 were designed an emphasis for high classification accuracy have individual accuracies 96.2% 96.8%, respectively detection. first classifying between healthy infected images attained a 98.03%. differentiating demonstrated 91.93%. effectiveness as well custom CNN designs enhancing analysis paediatric facilitating better been explored research.

Language: Английский

---