Differential diagnosis of congenital ventricular septal defect and atrial septal defect in children using deep learning-based analysis of chest radiographs

• Published in: BMC pediatrics 2024-10, Vol.24 (1), p.661-10, Article 661
• Main Authors: Jia, Huihui, Tang, Songqiao, Guo, Wanliang, Pan, Peng, Qian, Yufeng, Hu, Dongliang, Dai, Yakang, Yang, Yang, Geng, Chen, Lv, Haitao
• Format: Article
• Language: English
• Subjects: Adolescent; Algorithms; Chest radiography; Child; Child, Preschool; Children; Congenital heart disease; Deep Learning; Diagnosis; Diagnosis, Differential; Differential diagnosis; Diseases; Female; Genetic disorders; Heart; Heart diseases; Heart Septal Defects, Atrial - diagnostic imaging; Heart Septal Defects, Ventricular - diagnostic imaging; Humans; Infant; Machine learning; Male; Medical imaging equipment; Methods; Radiography, Thoracic - methods; Retrospective Studies; ROC Curve; Sensitivity and Specificity
• ISSN: 1471-2431; 1471-2431
• DOI: 10.1186/s12887-024-05141-y

Children with atrial septal defect (ASD) and ventricular septal defect (VSD) are frequently examined for respiratory symptoms, even when the underlying disease is not found. Chest radiographs often serve as the primary imaging modality. It is crucial to differentiate between ASD and VSD due to their distinct treatment. To assess whether deep learning analysis of chest radiographs can more effectively differentiate between ASD and VSD in children. In this retrospective study, chest radiographs and corresponding radiology reports from 1,194 patients were analyzed. The cases were categorized into a training set and a validation set, comprising 480 cases of ASD and 480 cases of VSD, and a test set with 115 cases of ASD and 119 cases of VSD. Four deep learning network models-ResNet-CBAM, InceptionV3, EfficientNet, and ViT-were developed for training, and a fivefold cross-validation method was employed to optimize the models. Receiver operating characteristic (ROC) curve analyses were conducted to assess the performance of each model. The most effective algorithm was compared with the interpretations provided by two radiologists on 234 images from the test group. The average accuracy, sensitivity, and specificity of the four deep learning models in the differential diagnosis of VSD and ASD were higher than 70%. The AUC values of ResNet-CBAM, IncepetionV3, EfficientNet, and ViT were 0.87, 0.91, 0.90, and 0.66, respectively. Statistical analysis showed that the differential diagnosis efficiency of InceptionV3 was the highest, reaching 87% classification accuracy. The accuracy of InceptionV3 in the differential diagnosis of VSD and ASD was higher than that of the radiologists. Deep learning methods such as IncepetionV3 based on chest radiographs in the study showed good performance for differential diagnosis of congenital VSD and ASD, which may be able to assist radiologists in diagnosis, education, and training, and reduce missed diagnosis and misdiagnosis.