Related Experiment Video
Updated: Sep 6, 2025
Ultrasonic Assessment of Myocardial Microstructure
Published on: January 14, 2014
Explainable deep learning algorithm for distinguishing incomplete Kawasaki disease by coronary artery lesions on
Haeyun Lee1, Yongsoon Eun2, Jae Youn Hwang2
1Department of Electrical Engineering and Computer Science.
Insights
Deep learning algorithms can help diagnose Kawasaki disease (KD) by detecting coronary artery lesions. This technology shows promise in distinguishing KD from other febrile illnesses in children.
Area of Science:
- Pediatric Cardiology
- Artificial Intelligence in Medicine
- Medical Imaging Analysis
Background:
- Incomplete Kawasaki disease (KD) presents diagnostic challenges due to atypical symptoms, yet carries a high risk of coronary artery lesions.
- Accurate diagnosis of KD is crucial for favorable outcomes, especially when differentiating from other febrile illnesses like COVID-19.
Purpose of the Study:
- To validate a deep learning algorithm for classifying Kawasaki disease (KD) and other acute febrile diseases.
- To assess the utility of AI in identifying coronary artery lesions indicative of KD.
Main Methods:
- Echocardiography images of children with KD (n=138) and pneumonia (n=65) were collected.
- Six deep learning networks (VGG19, Xception, ResNet50, ResNext50, SE-ResNet50, SE-ResNext50) were trained using the image data.
Main Results:
- The SE-ResNext50 network demonstrated superior performance in classification accuracy, specificity, and precision.
- SE-ResNext50 achieved a precision of 81.12%, sensitivity of 84.06%, and specificity of 58.46%.
Conclusions:
- Deep learning algorithms show comparable performance to experienced cardiologists in detecting coronary artery lesions for KD diagnosis.
- AI-powered tools can aid in the timely diagnosis of Kawasaki disease, potentially improving patient outcomes.
Background And Objective:
Incomplete Kawasaki disease (KD) has often been misdiagnosed due to a lack of the clinical manifestations of classic KD. However, it is associated with a markedly higher prevalence of coronary artery lesions. Identifying coronary artery lesions by echocardiography is important for the timely diagnosis of and favorable outcomes in KD. Moreover, similar to KD, coronavirus disease 2019, currently causing a worldwide pandemic, also manifests with fever; therefore, it is crucial at this moment that KD should be distinguished clearly among the febrile diseases in children. In this study, we aimed to validate a deep learning algorithm for classification of KD and other acute febrile diseases.
Methods:
We obtained coronary artery images by echocardiography of children (n = 138 for KD; n = 65 for pneumonia). We trained six deep learning networks (VGG19, Xception, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) using the collected data.
Results:
SE-ResNext50 showed the best performance in terms of accuracy, specificity, and precision in the classification. SE-ResNext50 offered a precision of 81.12%, a sensitivity of 84.06%, and a specificity of 58.46%.
Conclusions:
The results of our study suggested that deep learning algorithms have similar performance to an experienced cardiologist in detecting coronary artery lesions to facilitate the diagnosis of KD.
More Related Videos
Related Concept Videos
01:20Imaging Studies for Cardiovascular System II:Types of Echocardiography
Types of Echocardiography
Transthoracic Echocardiography (TTE)
TTE is the most common type of echocardiogram which involves placing a transducer on the patient's chest, emitting sound waves to create heart images. TTE is invaluable for evaluating the heart's size, structure, and motion, making it particularly useful for...
01:17Imaging Studies for Cardiovascular System I:Echocardiography
Indications: Echocardiography is utilized to diagnose heart failure, valve disorders, and myocardial infarction. It also assesses cardiac structures' size, shape, and motion,...
01:30Acute Coronary Syndrome III: Diagnostic Studies