Chest Radiographs Using a Context-Fusion Convolution Neural Network (CNN): Can It Distinguish the Etiology of Community-Acquired Pneumonia (CAP) in Children?

J Digit Imaging

Department of Radiology, National Center for Children' Health, Beijing Children's Hospital, Capital Medical University, Beijing, 100045, China.

Published: October 2022

Clinical symptoms and inflammatory markers cannot reliably distinguish the etiology of CAP, and chest radiographs have abundant information related with CAP. Hence, we developed a context-fusion convolution neural network (CNN) to explore the application of chest radiographs to distinguish the etiology of CAP in children. This retrospective study included 1769 cases of pediatric pneumonia (viral pneumonia, n = 487; bacterial pneumonia, n = 496; and mycoplasma pneumonia, n = 786). The chest radiographs of the first examination, C-reactive protein (CRP), and white blood cell (WBC) were collected for analysis. All patients were stochastically divided into training, validation, and test cohorts in a 7:1:2 ratio. Automatic lung segmentation and hand-crafted pneumonia lesion segmentation were performed, from which three image-based models including a full-lung model, a local-lesion model, and a context-fusion model were built; two clinical characteristics were used to build a clinical model, while a logistic regression model combined the best CNN model and two clinical characteristics. Our experiments showed that the context-fusion model which integrated the features of the full-lung and local-lesion had better performance than the full-lung model and local-lesion model. The context-fusion model had area under curves of 0.86, 0.88, and 0.93 in identifying viral, bacterial, and mycoplasma pneumonia on the test cohort respectively. The addition of clinical characteristics to the context-fusion model obtained slight improvement. Mycoplasma pneumonia was more easily identified compared with the other two types. Using chest radiographs, we developed a context-fusion CNN model with good performance for noninvasively diagnosing the etiology of community-acquired pneumonia in children, which would help improve early diagnosis and treatment.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9116701PMC
http://dx.doi.org/10.1007/s10278-021-00543-1DOI Listing

Publication Analysis

Top Keywords

chest radiographs
20
context-fusion model
16
distinguish etiology
12
mycoplasma pneumonia
12
model
12
pneumonia
9
context-fusion convolution
8
convolution neural
8
neural network
8
network cnn
8

Similar Publications

CXR-LLaVA: a multimodal large language model for interpreting chest X-ray images.

Eur Radiol

January 2025

Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea.

Objective: This study aimed to develop an open-source multimodal large language model (CXR-LLaVA) for interpreting chest X-ray images (CXRs), leveraging recent advances in large language models (LLMs) to potentially replicate the image interpretation skills of human radiologists.

Materials And Methods: For training, we collected 592,580 publicly available CXRs, of which 374,881 had labels for certain radiographic abnormalities (Dataset 1) and 217,699 provided free-text radiology reports (Dataset 2). After pre-training a vision transformer with Dataset 1, we integrated it with an LLM influenced by the LLaVA network.

View Article and Find Full Text PDF

Canine heartworm disease causes significant pulmonary abnormalities, even in asymptomatic cases. This study aimed to compare the chest radiographs of cases infected with with those of heartworm-negative dogs. Fifteen animals treated at a private veterinary clinic in the municipality of Maricá, Rio de Janeiro, underwent chest radiography, regardless of their serological status, for the presence of antigen, and none of them used preventive measures.

View Article and Find Full Text PDF

A review of imaging in the diagnosis and management of complicated paediatric pneumonia.

Paediatr Respir Rev

December 2024

Faculty of Medicine, University of Wollongong, Wollongong, NSW, Australia; Department of Respiratory Medicine, The Children's Hospital at Westmead, Westmead, NSW, Australia. Electronic address:

Paediatric pneumonia and its complications present substantial health and economic challenges. While chest radiographs are commonly used as the initial imaging modality for diagnosing uncomplicated pneumonia, they are less effective for complicated cases. In response, various imaging techniques, such as lung ultrasound, computed tomography (CT), and chest MRI, have been integrated into clinical practice to enhance diagnosis and guide management decisions.

View Article and Find Full Text PDF

The aim of our study was to evaluate the specific performance of an artificial intelligence (AI) algorithm for lung nodule detection in chest radiography for a larger number of nodules of different sizes and densities using a standardized phantom approach. A total of 450 nodules with varying density (d1 to d3) and size (3, 5, 8, 10 and 12 mm) were inserted in a Lungman phantom at various locations. Radiographic images with varying projections were acquired and processed using the AI algorithm for nodule detection.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!