Pediatric Pneumonia Recognition Using an Improved DenseNet201 Model with Multi-Scale Convolutions and Mish Activation Function

• Published in: Algorithms Vol. 18; no. 2; p. 98
• Main Authors: Radočaj, Petra, Radočaj, Dorijan, Ma
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.02.2025
• Subjects: Accuracy; Algorithms; Automation; convolutional neural network; COVID-19; Croatia; Datasets; Deep learning; Diagnosis; Efficiency; Fatalities; Health aspects; Medical imaging; Mish activation function; Mortality; multi-scale convolution; pediatric pneumonia; Pediatrics; Pneumonia; Pneumonia in children; Public health; World health; X-rays; Croatia; South Asia
• ISSN: 1999-4893; 1999-4893
• DOI: 10.3390/a18020098

Pediatric pneumonia remains a significant global health issue, particularly in low- and middle-income countries, where it contributes substantially to mortality in children under five. This study introduces a deep learning model for pediatric pneumonia diagnosis from chest X-rays that surpasses the performance of state-of-the-art methods reported in the recent literature. Using a DenseNet201 architecture with a Mish activation function and multi-scale convolutions, the model was trained on a dataset of 5856 chest X-ray images, achieving high performance: 0.9642 accuracy, 0.9580 precision, 0.9506 sensitivity, 0.9542 F1 score, and 0.9507 specificity. These results demonstrate a significant advancement in diagnostic precision and efficiency within this domain. By achieving the highest accuracy and F1 score compared to other recent work using the same dataset, our approach offers a tangible improvement for resource-constrained environments where access to specialists and sophisticated equipment is limited. While the need for high-quality datasets and adequate computational resources remains a general consideration for deep learning applications, our model’s demonstrably superior performance establishes a new benchmark and offers the delivery of more timely and precise diagnoses, with the potential to significantly enhance patient outcomes.