Related Experiment Video
Updated: Aug 31, 2025
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
Ensemble of deep capsule neural networks: an application to pediatric pneumonia prediction
Jyostna Devi Bodapati1, V N Rohith2, Venkatesulu Dondeti2
1Department of Computer Science and Engineering, Vignan's Foundation for Science Technology and Research, Vadlamudi, Guntur, Andhra Pradesh, 522213, India. jyostna.bodapati82@gmail.com.
Insights
This study presents a new deep neural network for detecting pediatric pneumonia from X-rays. The model achieves 94.84% accuracy, aiding early diagnosis and improving child survival rates.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Pediatrics
Background:
- Pneumonia is a leading cause of death in children under five.
- Early detection of pediatric pneumonia is critical for improving survival rates.
Purpose of the Study:
- To introduce a novel deep neural network for evaluating pediatric pneumonia from chest X-rays.
- To develop a model that assists clinicians in diagnosing pneumonia.
Main Methods:
- The proposed model is an ensemble of deep neural networks with interleaved convolutional and capsule layers.
- Networks are combined using dense layers and trained to minimize joint loss.
- The model was validated on a benchmark pneumonia dataset.
Main Results:
- The model captures high-level abstractions and low-level features from radiographic images.
- Achieved an accuracy of 94.84% in pneumonia detection.
- Demonstrated more generic predictions compared to existing approaches.
Conclusions:
- The novel deep neural network model shows high accuracy in pediatric pneumonia detection.
- The model is a valuable tool for assisting clinicians in diagnosis.
- Improved detection can significantly impact child survival rates.
Abstract:
Pneumonia disease accounts for 15% of all deaths in children under the age of five and early detection of the disease significantly improves survival chances. In this work, we introduce a novel deep neural network model for evaluating pediatric pneumonia from chest radio-graph images. The proposed network is an ensemble of multiple candidate networks, each with interleaved convolutional and capsule layers. Individual networks are stitched together with dense layers and trained as a single model to minimize joint loss. The proposed approach is validated through extensive experimentation on the benchmark pneumonia dataset, and the results demonstrate that the model captures higher level abstractions as well as hidden low-level features from the input radio-graphic images. Our comparison studies reveal that the proposed model produces more generic predictions than existing approaches, with an accuracy of 94.84%. The proposed model produces better scores than the existing models and is extremely useful in assisting clinicians in pneumonia diagnosis.
Related Concept Videos
01:30Pneumonia I: Introduction
Risk Factors
Various factors influence the likelihood of developing pneumonia. Age plays a crucial role, with infants, children under two, and individuals over 65 at increased risk due to their...
01:29Pneumonia II: Pathophysiology
01:30Pneumonia V: Nursing management and Prevention
The nurse must practice strict medical asepsis and adhere to infection control guidelines to minimize healthcare-associated infections.
Enhance airway patency
Position the patient correctly to facilitate drainage of the affected lung segments. Manual or mechanical percussion and vibration can also be employed....
01:30Pneumonia III: Complications and Assessment
01:18Neural Control of Respiration
Respiratory Centers in the Brainstem
Two primary areas comprise the respiratory center: the medullary respiratory center in the medulla oblongata and the pontine respiratory group in the pons. The...
01:28Pneumonia IV: Management
Bacterial Pneumonia Treatment
For bacterial pneumonia, antibiotics serve as the cornerstone of therapy. Initial treatment often begins with empirical antibiotics, tailored to the anticipated causative organism and adjusted based on culture results. Key antibiotic choices include: