Related Experiment Videos
Multimodal deep learning fusion model for assessment of fetal lung development in gestational diabetes mellitus and
Yanran Du1,2, Chao Ji3, Jing Jiao4
1Department of Ultrasound, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.
Insights
This study developed a multimodal deep learning model combining ultrasound imaging with molecular and histological data to assess fetal lung development in conditions like gestational diabetes mellitus (GDM) and pre-eclampsia (PE). The integrated approach significantly improved diagnostic accuracy compared to imaging alone.
Area of Science:
- Perinatology and Fetal Medicine
- Medical Imaging and Artificial Intelligence
- Genomics and Molecular Biology
Background:
- Fetal lung development is vulnerable to intrauterine conditions like gestational diabetes mellitus (GDM) and pre-eclampsia (PE).
- Current ultrasound evaluation offers limited insight into histological and molecular changes in fetal lungs affected by GDM and PE.
- There is a need for advanced methods to comprehensively assess fetal lung development in high-risk pregnancies.
Purpose of the Study:
- To develop a multimodal deep learning framework integrating ultrasound imaging with molecular and histopathological data.
- To assess fetal lung development in rat models of GDM and PE.
- To validate the framework's efficacy in human fetal lung assessment using transfer learning.
Main Methods:
- Established rat models for GDM and PE, collecting fetal lung ultrasound images and tissue samples.
- Conducted histopathology, immunohistochemistry, Western blotting, qPCR, and gene sequencing on fetal lung tissues.
- Developed a multimodal deep learning model using automated segmentation, feature extraction, and fusion of imaging, molecular, and histological data.
Main Results:
- Significant differences in fetal lung development indicators were observed between normal, GDM, and PE groups in animal studies.
- The multimodal fusion model demonstrated superior performance over ultrasound-only and partially integrated models in rat models.
- Validation in human fetal lung images showed high accuracy and AUC values, indicating the model's clinical potential.
Conclusions:
- Integrating multimodal data significantly enhances the assessment of fetal lung development in GDM and PE.
- The developed deep learning framework provides novel methodological and biological insights.
- This approach offers a potential non-invasive strategy for monitoring fetal lung development in high-risk pregnancies.
Background:
Fetal lung development is highly sensitive to adverse intrauterine conditions such as gestational diabetes mellitus (GDM) and pre-eclampsia (PE). Current clinical evaluation mainly relies on ultrasound imaging, but it provides limited information on related histological and molecular changes. This study aimed to develop a multimodal deep learning framework that combined ultrasound imaging features with molecular and histopathological data to assess fetal lung development.
Methods:
Rat models of GDM and PE were established, and fetal lung ultrasound images were obtained. Fetal lung tissues were evaluated by histopathology. The expression of key proteins was analyzed by immunohistochemistry, Western blotting, and quantitative PCR. Gene sequencing was conducted, followed by differential expression and functional enrichment analyses. Deep learning algorithms were used for automated lung segmentation, quantitative feature extraction, and model development. By combining imaging features with molecular and histological data, a rat multimodal fusion model was constructed, which was then validated using human fetal lung ultrasound images through transfer learning and parameter optimization.
Results:
In animal studies, significant differences were observed in multiple indicators of fetal lung development among normal, GDM, and PE groups, including quantitative histopathology, immunohistochemical protein expression, qPCR results, gene sequencing profiles, and functional enrichment analysis. The performance of the multimodal fusion model was better than that of the ultrasound-only and partially integrated models, achieving accuracies of 0.935 (95% CI: 0.898, 0.973) and 0.948 (95% CI: 0.919, 0.970) and average AUC of 0.954 (95% CI: 0.919, 0.984) and 0.955 (95% CI: 0.932, 0.979) in mid- and late- gestation, respectively. In clinical studies, 1,183 images of human fetal lungs were analyzed, and the classification model based on transfer learning showed superior performance, with accuracies of 0.835 (95% CI: 0.786, 0.894) and 0.874 (95% CI: 0.828, 0.907) and average AUCs of 0.830 (95% CI: 0.772, 0.890) and 0.857 (95% CI: 0.824, 0.893) in early and late trimester pregnancy, respectively.
Conclusions:
This study demonstrated that integrating multimodal data improved the assessment of fetal lung development in GDM and PE. By linking imaging features with molecular and histopathological alterations, the proposed framework provides new methodological and biological insights and suggests a potential non-invasive strategy for monitoring fetal lung development in high-risk pregnancies.
