Chest radiographs are primarily employed for the screening of cardio, thoracic and pulmonary conditions. Machine learning based automated solutions are being developed to reduce the burden of routine screening on Radiologists, allowing them to focus on critical cases. While recent efforts demonstrate the use of ensemble of deep convolutional neural networks (CNN), they do not take disease comorbidity into consideration, thus lowering their screening performance. To address this issue, we propose a Graph Neural Network (GNN) based solution to obtain ensemble predictions which models the dependencies between different diseases. A comprehensive evaluation of the proposed method demonstrated its potential by improving the performance over standard ensembling technique across a wide range of ensemble constructions. The best performance was achieved using the GNN ensemble of DenseNet121 with an average AUC of 0.821 across thirteen disease comorbidities.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC44109.2020.9176693 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
DDEvENet: Evidence-based ensemble learning for uncertainty-aware brain parcellation using diffusion MRI.
Comput Med Imaging Graph
January 2025
University of Electronic Science and Technology of China, Chengdu, Sichuan, China. Electronic address:
In this study, we developed an Evidential Ensemble Neural Network based on Deep learning and Diffusion MRI, namely DDEvENet, for anatomical brain parcellation. The key innovation of DDEvENet is the design of an evidential deep learning framework to quantify predictive uncertainty at each voxel during a single inference. To do so, we design an evidence-based ensemble learning framework for uncertainty-aware parcellation to leverage the multiple dMRI parameters derived from diffusion MRI.
View Article and Find Full Text PDFFinite-time H output synchronization for DCRDNNs with multiple delayed and adaptive output couplings.
Neural Netw
January 2025
School of Artificial Intelligence and Automation, Image Processing and Intelligent Control Key Laboratory of Education Ministry of China, Huazhong University of Science and Technology, Wuhan 430074, China. Electronic address:
This work concentrates on solving the finite-time H output synchronization (FTHOS) issue of directed coupled reaction-diffusion neural networks (DCRDNNs) with multiple delayed and adaptive output couplings in the presence of external disturbances. Based on the output information, an adaptive law to adjust output coupling weights and a controller are respectively developed to ensure that the DCRDNNs achieve FTHOS. Then, in the special case of no external disturbances, a corollary on the finite-time output synchronization (FTOS) of the DCRDNNs with multiple delayed and adaptive output couplings is provided.
View Article and Find Full Text PDFMulti-region infectious disease prediction modeling based on spatio-temporal graph neural network and the dynamic model.
PLoS Comput Biol
January 2025
Complex Systems Research Center, Shanxi University, Taiyuan, Shanxi, China.
Human mobility between different regions is a major factor in large-scale outbreaks of infectious diseases. Deep learning models incorporating infectious disease transmission dynamics for predicting the spread of multi-regional outbreaks due to human mobility have become a hot research topic. In this study, we incorporate the Graph Transformer Neural Network and graph learning mechanisms into a metapopulation SIR model to build a hybrid framework, Metapopulation Graph Transformer Neural Network (M-Graphormer), for high-dimensional parameter estimation and multi-regional epidemic prediction.
View Article and Find Full Text PDFAssessment of groundwater chemistry to predict arsenic contamination from a canal commanded area: applications of different machine learning models.
Environ Geochem Health
January 2025
School of Environmental Science and Engineering, Shandong University, Qingdao, 266237, China.
Groundwater arsenic (As), contamination is a significant issue worldwide including China and Pakistan, particularly in canal command areas. In this study, 131 groundwater samples were collected, and three machine learning models [Random Forest (RF), Logistic Regression (LR), and Artificial Neural Network (ANN)] were employed to predict As concentration. Descriptive statistics helped to conclude that all of the samples were inside the permitted limit of WHO for pH, Ca, Mg, Turbidity, Cl, K, Na, SO, NO, F and beyond limit of WHO for EC, HCO, TDS, and As.
View Article and Find Full Text PDFBiomarkers.
Alzheimers Dement
December 2024
Massachusetts Institute of Technology, Cambridge, MA, USA.
Background: Investigating age-related changes in MEG brain networks offers significant potential for comprehending aging trajectories and unveiling anomalous patterns associated with neurodegenerative disorders, such as Alzheimer's disease. In this study, we extended a deep learning model called Fully Hyperbolic Neural Network (FHNN) to embed MEG brain connectivity graphs into a Lorentz Hyperboloid model for hyperbolic space. Through these embeddings, we then explored the impact of aging on brain functional connectivity across multiple decades.
View Article and Find Full Text PDFWant 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!